melodic-software
- 406 skills
- 0 followers
- 30 repo stars
- 5 days ago last updated
- ▌ Audit 11 · melodic-software bundleAudit a codebase for drift between docs, config, code, and architecture. Verifies every factual claim against reality via parallel subagent fan-out, severity-rates findings and reports read-only; remediation is delegated to the implementation/verification lanes (`--fix` hands the findings to `/implementation:implement` then `/verification:confirm`). Use when: 'audit codebase', 'check for drift', 'verify docs', 'full audit'. Flags: `--fix` (hand findings to the remediation lanes after reporting), `--docs-only`, `--code-only`, `--config-only`, `--arch-only`.
- ▌ Setup 47 · melodic-software bundleVerify and configure the codebase-health plugin for this repository. check inspects the tracked .claude/codebase-health.md config read-only across its merge layers (presence, dimension source lists, tracked-not-ignored); apply interviews the user, infers audit targets from the repo layout, and writes the config. Use when: 'set up codebase-health', 'is codebase-health configured', 'configure the audit', 'codebase-health setup', the audit skill reports missing or thin config, or audit dimensions need tuning. Re-runnable. Safe to invoke again to reconfigure.
- ▌ Diagnose 3 · melodic-software bundleDiagnose unexpected behavior from Claude Code's built-in computer-use MCP server (desktop screen control). Use when: 'computer use', 'control my screen', 'screenshot is blurry', 'why is the screenshot low resolution', 'zoom in on the screen', 'screenshot capture failed', 'empty capture', 'clicks are landing in the wrong place', 'the screensaver killed the session', 'UIPI', 'app is not in the allowed applications', 'escape is not closing this menu', or before driving a native desktop app. Resolves a symptom to a cause instead of retrying: the fixed screenshot pixel budget and when zoom recovers detail, the capture and input failure ladders, and the per-OS quirks that make synthesized input behave unlike a human's. Not for: browser work (use Claude in Chrome), shell work (use Bash), or a service with its own MCP server.
- ▌ Setup 48 · melodic-software bundleVerify the markdown-format hook's runtime prerequisites and configuration for this repository. Use when: 'set up markdown-format', 'configure markdown-format', 'is markdown-format working', formatting silently isn't happening, or the hook reported a missing prerequisite. Actions: check (read-only verification, default) | apply (resolve what check found). Re-runnable and safe.
- ▌ Audit 12 · melodic-software bundleAudit an existing enforcement surface. Agent hooks, standing instructions, repository and version-control hooks, CI lanes, gate scripts, branch protections, forge apps, declared integrations. Under an evidence-earned-keep model: every incumbent is a retirement candidate until evidence earns its keep, every verdict cites an empirical source or is classed UNPROVEN, and security-class items are capped at flag-for-human. Read-only: it walks and reports; unasked writes stay in the self-ignored memory tier, and its one tracked write (persisting the resolved artifact home to the concern file) happens only on explicit confirmation. Use when the ask is to assess the enforcement surface ('audit our enforcement surface', 'is our CI overengineered'), to find which incumbents can be retired ('are these hooks still earning their keep', 'do we still need this gate'), to name enforcement clutter or process cruft, or to reconstruct why a check exists. Pass one or more layers to scope a pass, or `unattended` for a dispatched o
- ▌ Workflow 2 · melodic-software bundleNavigate a staged development workflow (explore → research → plan → implement → test → review → verify → retro), suggest the next stage, and route the end-of-phase continuation mechanism (continue / clear / handoff / background / clean-stop / compact). Use when: 'workflow', 'what step am I on', 'what comes next', 'pre-pr sequence', 'wrap up', 'how should I continue', 'clear or compact', at session start, at a phase boundary, or whenever the next step is unclear. Routes the stage decision to exactly ONE owner; when the ask is instead for the ranked menu of every skill that fits the moment ('what are my options', 'what am I forgetting'), that is /session-flow:show-options.
- ▌ Audit 13 · melodic-software bundleRun diff-scoped mutation analysis and report surviving mutants, the code under test is restored and the restoration verified, tracked source is either byte-identical at the end or the run fails naming what it could not restore, and no test is written by this skill. Generates at most one mutant per changed line, executes the covering tests, then delegates the productive-versus-arid-versus-equivalent judgment to a fresh-context reviewer before reporting; ranks files by oracle gap and hands survivors to the test-authoring lane. Use when: the user asks to run mutation testing or wants a mutation score for a change ('run mutation testing'), doubts a suite whose coverage report looks healthy ('my coverage is high but I do not trust it'), asks whether the tests actually check the code, asks to audit test quality, or asks for the survivors persisted for the fix pass; after tests go green and before review. Flags: `--full` (whole configured scope, not the diff), `--paths <globs>`, `--max <n>`, `--no-suppress` (report
- ▌ Setup 49 · melodic-software bundleVerify and configure the mutation-testing plugin for this repository. check inspects the ecosystem's mutation tool (installed, runnable, supported test runner), the baseline suite's health, and the tracked .claude/mutation-testing.md config across its merge layers, read-only; apply detects the ecosystem, installs or names the tool, interviews for the diff target and operator set, and writes the config plus an empty arid-node suppression record. Use when: 'set up mutation testing', 'is mutation testing configured', 'which mutation tool for this repo', 'mutation-testing setup', or the audit skill reports missing config or an unavailable tool. Re-runnable. Safe to invoke again to reconfigure.
- ▌ Setup 50 · melodic-software bundleVerify the rate-limit-guard plugin's wiring on this machine: jq, the installed statusline shim, statusline wiring (including legacy version-pinned plugin-cache paths), tee freshness, and the StopFailure hook. Print the exact statusline edit for the operator to apply, and install the statusline shim. Use when: 'set up rate-limit-guard', 'is the rate-limit tee working', 'wire the rate-limit statusline', the tee file is stale, or a consuming loop lane reports guard mode unknown. Actions: check (read-only; never edits settings), apply (writes ONLY ~/.claude/rate-limit-guard/bin/statusline-shim.sh, on explicit request).
- ▌ Principles 2 · melodic-software bundleMetric literacy for what this plugin reports: what cyclomatic complexity, cognitive complexity, Halstead difficulty, lines per file, duplication, coverage, CRAP, and type debt mean, and what none of them can tell you. Four reference files carry the definitions and what each collector computes, each bundled reference value with its provenance (why cyclomatic 20, why 22 and 80 have no citation), the CRAP formula with its name history and coverage join, and an annotated bibliography (McCabe, Halstead, NIST SP 500-235, Campbell, Lewis 2013, ISO/IEC 5055 and 25023). Cross-metric caveats live here once; owners of the measures it leaves alone are named behind a presence gate. Use when: 'what does cyclomatic complexity mean', 'is CRAP a real metric', 'why is the cyclomatic reference 20', 'what is a good coverage number', 'which metric should I look at', 'code metrics principles'; for the numbers themselves run the /code-metrics:audit-* skills.
- ▌ Setup 51 · melodic-software bundleVerify the powershell-format hook's runtime prerequisites and configuration for this repository. Use when: 'set up powershell-format', 'configure powershell-format', 'is powershell-format working', PowerShell formatting or linting silently isn't happening, or the hook reported a missing prerequisite. Actions: check (read-only verification, default) | apply (resolve what check found). Re-runnable and safe.
- ▌ Audit 14 · melodic-software bundleCoordinate Git/GitHub hygiene across a cross-repository fleet: discover canonical repositories, collect and roll up cross-repository evidence (including merged remote-tracking heads still on origin), and hand an action plan to repo-hygiene/source-control, which own per-repository cleanup. The current collector is read-only and emits detailed exact handoffs; it never deletes, prunes, repairs, fetches, checks out, or rewrites. Use when: 'audit repositories across a fleet', 'stale branches across repos', 'orphaned worktrees across repos', 'merged remote branches still on origin', 'moved or renamed GitHub repos'.
- ▌ Setup 52 · melodic-software bundleVerify and configure repo-fleet-hygiene for a consumer project. check inspects the optional .claude/repo-fleet-hygiene.conf read-only (presence, parse validity, path resolution); apply creates or updates it — adding bounded fleet roots, exact repositories, and remote-keyed canonical checkout overrides — preserving unrelated entries. Use when: 'set up repo fleet audit', 'is repo-fleet-hygiene configured', 'configure fleet roots', 'canonical repo override', 'dotfiles-manager checkout'. Re-runnable and safe.
- ▌ Setup 53 · melodic-software bundleVerify the desktop-notification hook's runtime prerequisites and per-OS channel configuration for this machine. Use when: 'set up desktop-notification', 'configure desktop-notification', 'is desktop-notification working', notifications silently aren't firing, or the hook reported a missing prerequisite. Actions: check (read-only verification, default) | apply (resolve what check found). Re-runnable and safe.
- ▌ Methodology 2 · melodic-software bundleEventStorming facilitation knowledge and reference across Big Picture, Process Modeling, and Design-Level formats. Use when: 'run EventStorming', 'model a domain', 'discover bounded contexts', 'Big Picture session', 'map domain events', 'find aggregates', 'DDD workshop', 'bounded context heuristics'. Actions: --big-picture / --process / --design-level (format guidance), --patterns (facilitation patterns/anti-patterns), --glossary, --notation, --remote. No args: interactive discovery — checks Miro for boards (if available), asks goal, recommends format. Not for agentic simulation — use /event-storming:simulation.
- ▌ Audit 15 · melodic-software bundleRead-only sweep for instruction content on the wrong surface. Conventions in an always-loaded CLAUDE.md/AGENTS.md really scoped to one file type or subtree (demote), and normative conventions stranded in ordinary docs Claude never loads (promote). Proposes a destination per candidate: a path-scoped `.claude/rules/` file whose `paths:` glob is machine-checked first, a nested AGENTS.md plus its CLAUDE.md shim, a skill, a linter, or deletion. Safety rails covering irreversible actions, secrets, data, publication, compliance, and agent authority are hard-denied from demotion and held back. Every proposal is priced: deferred content is invisible to subagents and absent after compaction until re-triggered. Use when: 'my CLAUDE.md is too long', 'convert this to rules', 'what should be a path-scoped rule', 'move conventions to .claude/rules', 'find conventions in our docs', 'nested CLAUDE.md candidates', 'audit instruction placement'. Emits a findings artifact; the sibling realign skill applies what you accept.
- ▌ Check 3 · melodic-software bundleDeterministic pass/fail gate over a repository's path-scoped instruction surfaces. Verifies every `.claude/rules/` glob actually resolves (matches at least one tracked file, valid bracket expressions, inside the documented 1,000-pattern / 4 MiB brace-expansion budget) and that the always-loaded rules index is in sync with the rules on disk. Every one of these failures is SILENT in Claude Code: a zero-match glob is a rule that never fires, an unbalanced `[` matches nothing, and an over-budget pattern is used unexpanded so its braces match no file. Use when: 'check my rules', 'are my path-scoped rules actually firing', 'is the rules index stale', 'validate paths frontmatter', 'why is my rule not loading', 'CI gate for .claude/rules', or after any change to a rule's `paths:` or to the rules tree. Read-only. Reports and exits non-zero, never edits; the sibling realign skill applies fixes.
- ▌ Delta 2 · melodic-software bundleRe-run the placement audit and report only what MOVED since the last run: new candidates, findings whose source content changed, rules whose globs stopped resolving, and index drift, above a configurable noise budget, so a repeat run costs attention proportional to what actually changed rather than re-presenting a finding set the operator already decided on. Declined findings stay declined and are never resurrected by a re-run, from this checkout or any other. Use when: 'what changed since the last placement audit', 'placement delta', 're-run the instruction-placement audit', 'anything new to move', 'did any rule glob break', 'weekly instruction-placement check', or from a scheduled lane. Read-only. Reports movement and writes nothing but memory-tier records (the refreshed findings artifact and its own spine baseline), never the tracked suppression surface; realign still owns every change.
- ▌ Setup 54 · melodic-software bundleVerify instruction-placement's prerequisites and resolve its effective configuration for this repository. Confirm that the index target exists AND is actually reachable by Claude Code (it reads CLAUDE.md, not AGENTS.md, so an unimported AGENTS.md index is inert while every other gate reports green), that `git` backs tracked-file discovery, and that the Claude Code CLI plus `jq` are present for the optional empirical load probe. Reports the resolved index target, breadth ceiling, and index row cap, naming which came from configuration and which from a default. Use when: 'set up instruction-placement', 'configure instruction-placement', 'where will the index go', 'why is my index not loading', 'is instruction-placement working', or before a first audit on a new repository. Actions: check (read-only verification, default) | apply (point at each remediation; writes nothing on its own). Re-runnable and safe.
- ▌ Principles 3 · melodic-software bundleAnswers mutation-testing questions from the primary literature (DeMillo/Lipton/Sayward, Jia & Harman, Google's ICSE-SEIP papers, and the Stryker/PIT/Infection tool docs), producing WHY reasoning about what a surviving mutant means. Use when: the user asks what mutation testing is or whether it is worth doing, asks how the score relates to coverage ('mutation score vs coverage', 'what is test strength'), asks what a mutant's state or disposition means ('equivalent mutant', 'what is an arid node'), asks which operators to use or why a score is low, asks whether to gate a build on the score, or names the underlying theory ('coupling effect', 'competent programmer hypothesis'); not for HOW to run a mutation tool in your project (use `/mutation-testing:setup` and `/mutation-testing:audit`).
- ▌ Realign 2 · melodic-software bundleExecute an instruction-placement audit's findings behind an explicit per-item human gate. Consumes the findings artifact the audit skill produced. It never re-judges the surface itself. For each finding the operator accepts, it performs the whole move atomically: create the path-scoped `.claude/rules/` file with its validated `paths:` glob (or the nested AGENTS.md plus its mandatory CLAUDE.md shim), excise the content from its source, regenerate the always-loaded rules index so the demoted surface stays reachable from subagents, and verify the result. Hard-denied safety content has no code path here. Use when: 'apply the placement findings', 'do the migration', 'move those conventions to rules', 'execute finding IP-004', 'realign our instruction layer', 'the audit says move it, do it'. This is the only skill in this plugin that changes anything, and there is no blanket-approve path.
- ▌ Humanize · melodic-software bundleRevise pasted writing or text-bearing files for natural, specific, context-aware prose while preserving meaning, evidence, citations, formatting, and the writer's legitimate voice. Use when a user asks to humanize, naturalize, de-AI, polish, rewrite, or audit formulaic writing in documents, Markdown, emails, articles, reports, comments, docstrings, or other prose-bearing artifacts. Do not use for a pure authorship-classification request with no editing goal.
- ▌ Verify Plugin · melodic-software bundleValidate a Codex plugin package or repo marketplace for manifest, catalog, skill, context-discovery, architecture, path, and portability defects. Use when reviewing, testing, publishing, migrating, or troubleshooting `.codex-plugin/plugin.json` or `.agents/plugins/marketplace.json` content.
- ▌ Migrate Plugin · melodic-software bundleTranslate a Claude Code, Cursor, or older Codex plugin into an independent Codex-native package. Use when porting skills, agents, hooks, MCP configuration, manifests, marketplace entries, scripts, or plugin behavior between agent hosts.
- ▌ Update Plugins · melodic-software bundleRefresh configured Codex marketplace snapshots and reinstall plugins after upstream or local changes. Use when a user asks to update, upgrade, refresh, reload, or pick up a new version of a Codex plugin or marketplace.
- ▌ Install Marketplace · melodic-software bundleAdd a local or Git-backed Codex plugin marketplace and install plugins from it. Use when a user asks to add, connect, configure, or install a Codex marketplace or a plugin from a marketplace source.
- ▌ Coordinate Codex Work · melodic-software bundleCoordinate multi-task, multi-agent, and long-running Codex work across local projects or projectless efforts. Use when the user asks Codex to direct parallel work, manage or monitor Codex tasks, reconcile dependencies, compare independent approaches, prepare handoffs, or turn a proven workflow into a scheduled task.
- ▌ Find Skill Candidates · melodic-software bundleFind evidence-backed opportunities to create or improve user-authored Codex skills by scanning a bounded window of local Codex session logs. Use explicitly when reviewing recent work for repeated workflows, skill friction, missed triggers, or reusable skill opportunities. Report recommendations only; do not modify skills.
- ▌ Manage Scheduled Tasks · melodic-software bundleExplain, recommend, list, inspect, create, update, pause, resume, or delete native Codex Scheduled tasks. Use when a user asks about recurring work, reminders, monitors, scheduled follow-ups, the Scheduled page, a task that should return to the current chat, or a standalone task that should start a new chat for each run.
- ▌ Be Concise · melodic-software bundleReshape prose so a scanning reader gets the point: bottom line first, no more words than the meaning needs, structure that survives scanning, factual tone. Two modes. Invoked bare it sets a standing posture for everything written afterwards; given any target it reshapes that text and reports before and after word counts. Never drops a decision, number, ask, error or warning, and never edits an already-posted record in place unless told to. Use when: 'write this for the PO', 'shorten this ticket', 'make this scannable', 'bottom line first', 'nobody will read this', 'rewrite this PR description for reviewers', or before writing anything a person reads in a tracker, a pull request, a doc, or a status update. Not for: in-flight chat and code terseness (discipline:tighten-your-output), word-level trimming of a repo .md (docs-hygiene:compress), restructuring without shortening (adhd:clarify), or doc genre and language standards at authoring time (docs-hygiene:write-for-humans).
- ▌ Blindspot · melodic-software bundleSurface the USER's unknown-unknowns before they work in unfamiliar territory, an unfamiliar codebase area OR an unfamiliar domain vocabulary, and coach a sharper prompt. Scans for gaps the user's framing missed, emits one blindspot card per gap (the gap, why it matters here, a copyable prompt-fix line), then assembles the fixes into one improved implementation prompt. Use when: 'what am I missing', 'find my blindspots', 'what do I not know here', 'sharpen this prompt', 'I am new to this area', or about to work somewhere you do not know well and the goal is a better prompt, not the codebase handoff artifact /discovery:explore produces.
- ▌ Grounding · melodic-software bundleGround an approach in how a Dometrain course teaches it, via the Dometrain MCP server, and cite lessons with timestamped deep links. Use when: 'implementing', 'designing', 'reviewing', or 'debugging' anything covered by a Dometrain course — C#/.NET, ASP.NET Core, EF Core, testing, design patterns, architecture, messaging, databases, cloud/DevOps, TypeScript, or AI development.
- ▌ Firecrawl · melodic-software bundleScrape, search, crawl, map, parse, or interact with web pages via the firecrawl-cli binary, writing results to disk instead of streaming them into context. Actions: scrape, search, crawl, map, parse, interact, agent, monitor, search-feedback, credit-usage. Use when: 'scrape this page', 'crawl this site', 'search the web for X', 'WebFetch is blocked', 'this page needs JS', 'extract the text from this PDF', when WebFetch returns 403 or 429 behind an anti-bot layer such as Cloudflare or PerimeterX, or for a natural-language web research task. Skip for plain unprotected pages (WebFetch suffices) or when you want synthesis rather than primary source.
- ▌ Manage · melodic-software bundleManage the Kindle for PC 2.8.0 + Calibre DeDRM workflow for personal-use ebook DRM removal on books you own (Windows only). Action router: setup (first-time provisioning — download, firewall block, ICACLS lock, Calibre plugins, keyfinder; delegated to the dedicated /kindle-dedrm:setup check/apply skill), sync (new purchases — disable firewall, sync Kindle, re-enable, re-run keyfinder), update (drift check — upstream version pins and tutorial URLs, no mutations), cleanup (reversible decommission — per-item confirmation, --soft or --full), status (diagnostic). Every state mutation has a documented compensating reversal. Use when: 'set up Kindle DRM removal', 'convert Kindle books to EPUB', or syncing, drift-checking, or decommissioning personal-use Kindle DRM removal; making an owned Kindle library readable on a non-Kindle device; or Calibre and Kindle are mentioned together.
- ▌ Brainstorm · melodic-software bundleDiverge before scoping. Turn a rough engineering/product problem into codebase-grounded candidate approaches ordered cheapest→most ambitious, capture which resonate, and hand off scoped. Use when: 'brainstorm', 'what are my options', 'places we could intervene', 'how could we approach X', 'ideas for this', 'explore some approaches', 'what could we do here', or any rough technical problem with no locked scope; skip when scope is already locked or the options are visual variations.
- ▌ Quality Gate · melodic-software bundleSingle-lens review checkpoint between 'code works' and 'code is ready'. Routes to self, code, architecture, security, spec, close-out, downstream, pr, criteria, slice, or restatement mode and delegates to the matching reviewer. Use when the user says 'review this', 'self-review', 'quality gate', 'code review', 'architecture review', 'security review', 'does this match the spec/issue/plan', or 'close-out review' / 'review the container' for a shipped spec container, or after implementation completes. Downstream mode covers 'what could this break', 'blast radius', 'what else does this touch', 'who calls this'. Breakage outside the diff on a change already written; assessing a plan's reach before implementation is '/planning:plan' and '/planning:devils-advocate', and a rename sweep is '/docs-hygiene:rename-references audit blast'.
- ▌ Orient · melodic-software bundleRead-only session orientation from durable + off-thread state, synthesize where we stand, what we are doing, and why, from the ledger files, handoff save-points, workflow checklists, running-retro ledgers, open PRs and work-items, and git state, not just the conversation. Complements the built-in /recap (conversation-only, auto-fires) by adding the durable state recap never sees. Use when: 'where were we', 'catch me up', 'orient me', 'get my bearings', 'what's the state', 'brief me', 'situation report', 'where do we stand', 'lay of the land'. Read-only: writes nothing, ends nothing, and does not verify freshness, recover off-thread work, or prescribe the next stage; it points at the sibling that does.
- ▌ Improve · melodic-software bundleScan an existing codebase for module-level friction and architecture improvement opportunities (shallow modules, seam leaks, locality gaps), present candidates as an HTML report, interview on the selected candidate with a Design-It-Twice branch that designs the interface several radically different ways in parallel, and hand off the agreed shape for planning. Use when: 'improve architecture', 'find deepening opportunities', 'shallow modules', 'Ousterhout deepening', 'design it twice', 'compare alternative interfaces', 'make code more testable', 'make code more AI-navigable', 'find refactoring opportunities', 'codebase friction', 'module seams', 'locality'. Skip when: a cross-dimension or evidence-driven improvement ask (a general 'what should we improve', 'highest-impact improvement', or 'find improvements' across code, product, process, or ops) routes to /improvement:find (this skill is the single-lens architecture-depth pass); also skip for mechanical code-level tidyings, reviewing a diff before merge, enfo
- ▌ Changelog · melodic-software bundleIngest Claude Code changelog entries and integrate them into the current repo. Fetch (read-only display), diff (impact analysis, no edits), status (applied versions), and apply (full integrate pipeline, explicit user intent only). Use when: 'new cc version', 'what changed in claude code', 'apply changelog', a new CC release is mentioned, or the user pastes changelog text.
- ▌ Inventory · melodic-software bundleEnumerate the complete Claude Code ECOSYSTEM this machine can invoke. Every built-in CLI command with its aliases and hidden/gated status, every bundled skill, and every component of every installed plugin (skills, agents, commands, hooks, MCP servers, LSP servers, workflows, output styles, themes, monitors, bin) across all marketplaces. Reads the shipped binary because the official docs publish no built-in command list. Reports; never changes anything. Use when: 'what slash commands do I have', 'list all my skills', 'what agents are available', 'show me every plugin component', 'what does Claude Code ship built-in', 'is /foo a real command', 'what changed after the update', 'show me only the plugin ones', 'what does marketplace X give me'. Not for: auditing the install DIRECTORY on disk (use /claude-ops:audit-install-state), updating or converging the plugin fleet (use /claude-ops:plugins), or checking settings and permission drift (use /claude-config:audit).
- ▌ Sweep All · melodic-software bundleCompose this plugin's discipline correctors into ONE batched pass. Requires conversation-inheriting fork subagents (`subagent_type: fork`); without fork mode it degrades to the posture digest and audits nothing. At conversation start it instead reports a cheap posture digest (which disciplines are in scope) with no audit. Use when: 'sweep all disciplines', 'ground ourselves', 're-anchor everything', 'run the whole re-anchor bundle', 'posture batch', 'set our posture before we start', 'batch the correctors', or at conversation start to set posture across every standing discipline at once. Membership is each corrector's own tier metadata; for a single discipline, invoke that corrector directly.
- ▌ Wait What · melodic-software bundleStop. That last message did not land. Re-pitch it: back up as far as needed, add the context that was missing, write in ASD-STE100 Simplified Technical English, and use the project's own ubiquitous language. Type /discipline:wait-what the moment you notice you are skimming; only you know when you stopped following.
- ▌ Map Corpus · melodic-software bundleMap a multi-resource documentation corpus into a verified, classified, triaged slice BEFORE any digesting: bounded discovery (llms.txt + sitemap), a user-approved link map classifying every discovered URL, deterministic node manifests over immutable snapshots, and a per-node relevance inventory whose evidence a script gate verifies. Handing an approved queue to N runs of /knowledge:docpage-digest. Use when: 'map this corpus', 'map this docs site', 'digest this whole site', 'ingest these docs and the spec repo', 'multiple pages/URLs to digest', 'corpus mapper', or the user supplies a topic plus seed URLs covering more than one page. One single page routes straight to /knowledge:docpage-digest; books to /knowledge:book-distill, courses to /knowledge:course-digest, single videos to /knowledge:video-digest. Not ad-hoc summarization, the output is a corpus slice (link map, node manifests, inventory, approved queue) that proves its coverage instead of asserting it.
- ▌ Snapshot · melodic-software bundleCapture a baseline or post-change performance snapshot with the HOST QUALIFIED FIRST: repeated no-op spawns characterize the machine's own noise, and a wall-clock claim is REFUSED outright from a host carrying the bimodal contention signature, naming the drift-immune counter it can still report instead. Interleaves before/after arms within one run rather than comparing two passes, since a host that drifts 6x in an hour attributes its own drift to the change. Reports a counter alongside and ranked above any duration. Use when: capturing a before or after snapshot, running the comparison between them, or asking whether this machine can support a timing claim at all: 'capture a baseline', 'take a post snapshot', 'run the A/B', 'can I even measure here'. Runs after /performance:goal; hands off to /performance:verify. Skip when no goal with a computed floor exists yet (run /performance:goal), or when the claim is about code shape rather than runtime (that is /verification:measure metrics).
- ▌ Handoff · melodic-software bundleWrite a mid-session save-point for /clear-and-resume, a durable handoff file (default) or a copy-paste resume prompt when follow-ups are small. Use when: 'handoff', 'save state', 'checkpoint this', 'pause', 'come back later', the user reports the session is heavy, a context-measuring mechanism says to fork, or your own responses are visibly drifting, repeating, or looping. Never on your own estimate of the remaining window, a budget reading is not a decay signal. For delegating the continuation to a background agent, use the sibling continue-in-background skill.
- ▌ Co Write · melodic-software bundleRun a co-writing session and generate titles and high-volume options with Pat Pattison's methods, the No-Free-Zone co-write protocol and feedback discipline, the Title Game (chained vowel-cascade title generation), title generation from an idea, and high-volume brainstorm dumps for ONE line or ONE section. Use when: 'co-write tonight', 'co-write rules', 'no-free-zone', 'Title Game', '10 titles fast', 'title candidates for X', 'give me 30 options for this line', 'brainstorm the whole chorus'. For blank-page/idea/fragment starts use /songwriting:workflow; for rhyme dumps use /songwriting:rhyme.
- ▌ Metaphor · melodic-software bundleGenerate and diagnose metaphor with Pat Pattison's methods, the three types (expressed identity, qualifying, verbal), the three expressed-identity forms, collision drills (noun×verb, noun×noun, adjective×noun), playing in keys (fundamental → diatonic family → collisions), the two metaphor-finder questions, participles, transitive vs intransitive, simile as focus control, and grounded-metaphor diagnosis. Use when: 'I need a metaphor for X', 'generate metaphor options', 'metaphor or simile here', 'this metaphor feels dead', 'my song has no metaphor', 'sustain this image across the song', 'collide these words', 'what else has these characteristics'. For sensory raw material use /songwriting:object-writing; for cliche repair use /songwriting:object-writing cliche.
- ▌ Practice · melodic-software bundleBuild a songwriting practice habit with Pat Pattison's curriculum, the daily object-writing/craft routine and numbered exercises drawn from all four books (Essential Guide to Lyric Form and Structure structural exercises, Songwriting Without Boundaries 56-day curriculum, Essential Guide to Rhyming worksheets). Use when: 'daily practice plan', 'build a writing habit', 'give me a 90-second writing prompt', 'run me a numbered exercise', 'exercise 4.6', 'daily craft prompt'. For a one-off object-writing prompt use /songwriting:object-writing.
- ▌ Workflow · melodic-software bundleStart-here situation router for songwriting with Pat Pattison's methods. Picks the scenario for a blank page, an idea/seed, a stuck fragment, a co-write, a diagnose-only pass, or a daily habit, and runs step-by-step coaching dialog. Also applies Pat's response filter to AI-generated material and points to going-deeper resources (Coursera / Berklee / columns / podcasts). Use when: 'I want to write a new song', 'I have nothing — just want to write', 'I have an image but no title', 'this fragment is stuck', 'walk me through writing this', 'guide me', 'where do I start', 'review the rhyme list this AI gave me', 'how do I go deeper'. Craft-specific requests route to the concern skills below.
- ▌ Confirm · melodic-software bundleProve a change achieved its intended outcome: a mechanical build+test+lint prerequisite (delegated to /toolchain:check and /toolchain:lint, STOPs if broken), then outcome verification. Does the change match the plan/intent and function correctly, with the criterion auto-detected by change-type (feature, fix, refactor). Use when: 'verify changes', 'prove this works', 'did we build the right thing', 'is this done', 'check my work', 'did the fix actually work'; for quick mechanical-only checks use /toolchain:check, for measurable-improvement claims use /verification:measure.
- ▌ Measure · melodic-software bundleVerify a measurable-improvement claim against a baseline captured BEFORE the change. Two metric families (`performance`: wall time, memory, allocations, throughput, latency; `metrics`: complexity, coverage, coupling), each with a `baseline` phase at planning time and a `compare` phase after the change. Never claims improvement without a baseline (no baseline → honest 'cannot quantify'). Use when: 'is it faster', 'before/after', 'prove the improvement', 'did that actually speed it up', 'how much faster is it', 'measure this', 'capture a baseline', 'benchmark before and after', 'did complexity go down'; intent/outcome confirmation stays with /verification:confirm.
- ▌ Decompose · melodic-software bundleBreak a plan, spec, or PRD into independently-grabbable work items using vertical-slice (tracer-bullet) decomposition, with HITL/AFK classification and dependency ordering. Use when the user wants a plan, PRD, or brief broken (decomposed, split, vertical-sliced) into tickets or work items; wants the spec published to the tracker as a container; or wants an existing decomposition re-sliced or rerouted because the spec changed. Reads a PLAN.md, PRD.md, item body, or the conversation; drafts thin end-to-end slices, classifies each AFK (agent-ready) vs HITL (needs-human), gets approval, then publishes blockers-first via the seam with native dependency edges, optionally (opt-in at approval) under a spec container carrying the Brief with slices as native sub-items. Also owns re-decompose (rerouting) when mid-flight review shows the spec is wrong: close obsolete unimplemented slices, keep implemented ones, edit the spec, regenerate the rest. Sibling skills: /work-items:track (backlog CRUD), /work-items:work (auto-se
- ▌ Work Loop · melodic-software bundleRun the work-item backlog as a self-paced autonomous drain loop: each cycle sweeps raw intake through mechanical triage, admits items through the work-class gate (fail-closed), executes admitted items via /work-items:work under an adaptive item cap, and evaluates the drain exit condition. Worker lane of the loop-lane three-session topology. Authors PRs, NEVER merges. Use when: 'work loop', 'run the work loop', 'start the worker loop', 'drain the backlog', 'autonomous drain', 'loop the backlog', 'drain the issue backlog to done'. Launch via /loop (self-paced). Sibling skills: /work-items:attend-queue (attended escalation lane), /work-items:work (single-item pick + execute), /work-items:triage (raw intake), /work-items:track (backlog CRUD).
- ▌ Compress · melodic-software bundleCompress (tighten, shorten, trim) markdown files by dropping flavor, filler, hedging, articles, while preserving all content (directives, qualifiers, thresholds, examples), with a mandatory semantic-diff subagent that reverts any SEMANTIC LOSS or AMBIGUITY. Use when: 'compress this doc', 'tighten markdown', 'cut prose', 'shorten without losing meaning', 'trim onboarding doc', or verbose prose in docs/, READMEs, rule bodies, skill bodies, or third-party pasted text. Actions: default (snapshot → backend → semantic-diff subagent → revert-pass → markdownlint) and audit (read-only dry-run classifying SKIP/COMPRESS/UNCERTAIN per file); empty target + clean tree in an interactive session offers a confirmation-gated repo-wide run (audit-first interview with prescribed defaults) instead of the no-op; flags: --force (bypass <3% revert rule), --keep-snapshot; not for: session compaction (/compact), markdown noise classification (/audit-noise), code-comment trimming, or content relocation/SSOT consolidation (/extract-sso
- ▌ Name It Better · melodic-software bundleGenerate and evaluate fresh name candidates for anything: a variable, function, file, module, skill, repo, or domain term. Then let the human pick. Use when the target name is still UNDECIDED, whether the ask is a fresh name ('suggest names', 'what should I call this') or a retry on one just rejected ('name it better', 'that name is wrong', 'help me rename this to something better'). Not for an already-decided rename ('rename X to Y', 'I renamed X'). That routes to the rename-references sweep. Spawns blind fresh-context generators from distinct lenses; never auto-locks a name. Optional 'tournament' arg for high-stakes, hard-to-refactor names.
- ▌ Delta · melodic-software bundleReport only what changed in the enforcement surface since the last audit. Re-runs `overengineering:audit`, compares this run's findings spine against the one the previous cycle left behind, and captures a fresh baseline for the next run. The report covers new clutter, verdict moves, closures, and status changes, filtered through a configurable noise budget, so a recurring run is a short delta instead of the whole surface again. Read-only always: it never invokes or enters `overengineering:realign`, never writes a Status, and never touches the surface it reads; verdict changes queue for the human. A first run establishes a baseline and reports no deltas. Use when the ask is for what moved since the last enforcement audit ('what changed since the last audit', 'did any verdict move') or for a recurring, scheduled enforcement check ('run the enforcement audit on a schedule'). Pass layers to scope the pass and `unattended` for a scheduled or dispatched run; both pass straight through to the audit.
- ▌ Playwright · melodic-software bundleLive E2E browser automation via Microsoft's @playwright/cli: named sessions, accessibility-ref snapshots, click/fill by ref, screenshots, console and network capture, network mocking, tracing, video, and auth state, with artifacts written to disk so only paths enter context (far fewer tokens than Playwright MCP). Use when: 'playwright', 'E2E test', or any task that needs a real browser driven against a running app: testing a UI flow end to end, capturing a screenshot or video as evidence, reading console errors or network traffic, or mocking a response.
- ▌ Reanchor · melodic-software bundleVerify a session's working assumptions are still true before building on them. Referenced PRs/issues/branches still in the state a handoff or plan claims, base-branch drift, cited skills/plugins that were renamed or version-drifted, and memory-tier files whose subjects have since landed. Reports what drifted and re-anchors; does not resume the work. Use when: 'reanchor', 're-anchor', 'is this still current', 'verify my assumptions', 'has main moved since', 'are these premises still valid', 'is the handoff stale', 'resuming an old plan', 'check freshness'. Not for resuming work (use /session-flow:keep-going), the cross-worktree staleness inventory, PR feedback triage, or re-anchoring a standing behavioral rule (this re-anchors factual premises, not rules).
- ▌ Song Form · melodic-software bundleBuild and balance song structure with Pat Pattison's methods. Section identification (verse/chorus/bridge/refrain), forms (AABA, verse/chorus, verse/refrain), the candy-bar rewrite, hook placement and hot spots, repetition/repainting (You-I-We, Past-Present-Future, hidden questions/commands), verse development and the box model, bridge writing, and Essential Guide to Lyric Form and Structure worked examples. Use when: 'is this verse/chorus or AABA', 'where should the title go', 'my chorus does not land', 'my second verse repeats the first', 'what goes in verse 2/3', 'write me a bridge', 'do I need a bridge'. For stability/scansion use /songwriting:meter-prosody.
- ▌ Commit · melodic-software bundleCreate a git commit with a subject matching the resolved convention (layered `source-control.md` config → project convention → Conventional Commits default), a Claude Co-authored-by trailer, and surgical staging (never `git add -A`), feeding the message to git via Bash heredoc. Use when: 'commit this', 'make a commit', 'commit with message <hint>', not for push, branch creation, or PR creation (use /pull-request).
- ▌ Scan Todos · melodic-software bundleSweep the codebase's source comments, not tracker items, for actionable markers (TODO/FIXME/HACK/XXX) and resolve or file each one. Use when: 'scan TODOs', 'scan for FIXME', 'sweep the codebase for markers', 'find TODO comments', 'resolve TODO/FIXME/HACK', 'scan for tech-debt comments', 'clean up markers'. NOT the encouraged workflow for new work. Durable work belongs in the tracker at authoring time; prefer a commit-time hygiene gate. Sibling skills: /work-items:track (backlog CRUD), /work-items:work (auto-select + execute), /work-items:triage (raw intake), /work-items:decompose (plan → tickets).
- ▌ Unhobble · melodic-software bundleEmpirical bare-baseline experiment on a repo's standing instructions: reversibly strip project CLAUDE.md/rules/behavioral hooks/skills on a dedicated branch, work normally against the bare model logging observed stumbles to a ledger, then re-add ONLY instructions with repeated same-cause evidence, each restore citing its ledger rows. Measures the model where sibling audit-instructions judges the text. Use when: 'unhobble', 'run the bare experiment', 'delete my CLAUDE.md and see', 'does the model still need these instructions', 'new model dropped, re-baseline', 'instruction ablation experiment'. Human-gated mutations; resumable state.
- ▌ Trace Intent · melodic-software bundleReconstruct WHY something was built the way it was, from evidence outside the code, review discussion, tickets, design docs, incident records, and report what could not be found as a first-class result. Grades every claim on an intent-evidence tier (Direct / Supported / Inferred / Speculative / Unknown) and cites each one. Use when: 'why was this built this way', 'why did we pick X over Y', 'what were they thinking', 'design rationale', 'what problem was this solving', 'why does this still exist', 'archaeology on this decision'. Skip when: you want what the code DOES or where it lives (that is '/discovery:explore', whose git mode owns repo-local history); when the question is whether a convention should STILL hold rather than why it was adopted (that is '/discipline:reason-dont-recite'); or when the answer is a current external fact rather than a past decision (that is '/discovery:research').
- ▌ Book Distill · melodic-software bundleDistill a technical book (PDF or EPUB) into concept-organized skill reference files via a structured multi-session pipeline. Use when: 'distill this book', 'book to skill', 'PDF to skill', 'EPUB to skill', 'read this book for me', 'extract knowledge from this book', 'book distillation', 'turn this book into a skill', 'extract from PDF'; or when user provides a PDF/EPUB path and asks to create or extend a skill from it. Produces author-attributed reference files (60-160 lines each), named by concept not chapter, with routing table updates to the target skill's SKILL.md. Handles multi-author merges and Phase 3 shared-file consolidation. Not for ad-hoc book summaries. Output is structured developer-facing context files the target skill routes at query time.
- ▌ Video Digest · melodic-software bundleWatches a single public video from YouTube or X (Twitter). Extracts the transcript, harvests links, researches claims, and synthesizes prioritized repo-applicability recommendations. Use when: 'youtube', '/youtube-digest', 'watch this YouTube video', 'transcript for YouTube', 'watch this video', 'digest this video', 'digest this post', 'summarize this talk', or the user shares a youtube.com, youtu.be, x.com, or twitter.com URL for a single public video or video post. Actions: watch <url> (full pipeline), watch (dequeue epic queue), watch <n> (queue row), queue <url> (batch enqueue), transcript <url> (captions only), resume <slice-slug>. Do NOT use for auth-walled course platforms. Dometrain, Pluralsight, and Udemy courses go to /knowledge:course-digest.
- ▌ Audit Answers · melodic-software bundleAdversarially validate a completed /planning:interview's answers with independent fresh-context agents. Runs over any filled decision ledger, hand-answered or auto-accepted. Validators re-examine each answer with its rationale withheld and return a per-answer verdict (confirmed / challenged / reclassified-to-human), so only doubtful answers come back as real questions; open branches are filled with the recommended answers first, holding the never-auto floor. Use when: 'audit my interview answers', 'validate the interview answers', 'have agents check the answers', 'accept all and have agents check them', 'agent-validated interview', 'have subagents second-guess the recommendations', 'auto-answer then verify the ledger'. Not for stress-testing a plan artifact (that is '/planning:devils-advocate') or asking the human the first time ('/planning:interview'); needs a filled interview ledger.
- ▌ Questionnaire · melodic-software bundleTurn a decision another person holds into a Markdown questionnaire handed off async. Interviews the user only about the send (who it goes to, what they need back), never about the subject the recipient holds, then writes a discovery questionnaire aimed at the gap. Use when: 'make a questionnaire for X', 'I need to ask my DBA/the client/legal about this', 'turn this into a doc someone else fills in', 'I don't know, that's the client's call', 'send this to someone else to answer', 'write up questions for our security team', or when an interview branch defers to a person-arbiter; skip when the user can answer themselves (run /planning:interview) or when the answer is agent-lookupable.
- ▌ Security Review · melodic-software bundleCI security-review lane for a GitHub pull request. Logic, trust-boundary, and Actions security findings static analysis misses. Use when: 'CI security review', 'claude-security-review lane', '/review:security-review', or a reusable workflow invokes the org security-review plugin command.
- ▌ Reconcile · melodic-software bundleRetire finished off-thread work and reconcile this session's task ledger with reality, the prune-and-reconcile counterpart to keep-going's resume. Inventory the off-thread work this session spawned, inspect each item's REAL state, retire the genuinely finished, close the ledger items proven done, and report sibling-session liveness read-only. Auto-settles the provably-finished; GATES any kill of still-running work. Use when: 'reconcile the session', 'retire finished work', 'square up the task ledger', 'is anything still running that should be retired', 'close out finished tasks', 'prune done work', 'reconcile the ledger'. Boundary: 'is it stuck / pick it back up' is /session-flow:keep-going; a read-only 'where do we stand' glance is /session-flow:orient; making git/PR work durable before shutdown is /session-flow:clean-stop.
- ▌ Stateless · melodic-software bundleInspect and turn off Claude Code's auto memory, the notes Claude writes itself per repo under ~/.claude/projects/<project>/memory/. Use when: 'make Claude stateless', 'stop Claude remembering', 'disable auto memory', 'turn off auto-memory', 'purge/clear/delete auto memory', 'wipe what Claude saved about this repo', 'does Claude have saved memories'. Actions: status (default, memory + settings across all scopes), disable (autoMemoryEnabled:false + CLAUDE_CODE_DISABLE_AUTO_MEMORY), purge (destructive delete, confirm-gated). Auto-memory only, not CLAUDE.md/rules (use /claude-memory:audit) and not transcripts/history.
- ▌ Known Issues · melodic-software bundleLooks up and tracks known Claude product issues. Searches known GitHub bugs, checks service health and model quality, and maintains a persistent registry of tracked issues. Use when: 'is this broken', 'known CC bugs', 'troubleshoot Claude Code', 'any workarounds', 'feature behaves unexpectedly', 'scan repo for issues', 'file a bug'. Actions: status (default), search <feature>, check-all, scan, list, quality, create.
- ▌ Audit Size · melodic-software bundleMeasure lines per file for the changed files, a path, or the whole tree: total, blank, comment, and code lines when `scc` resolves, total and non-blank lines from a bundled counter otherwise, per lane (TypeScript/JavaScript, Python, Bash, Go; C# files are counted too). Each file is reported beside a configurable reference with its provenance (default 1000 non-blank lines, the plugin's own number and not ISO-backed; 500 selectable; an ISO/IEC 5055 §8.2.115 function-percentage mode selectable), and the report never emits a finding, a severity, or an exit-code gate. Use when: 'how long are these files', 'lines per file', 'file size audit', 'which files are too big', 'LOC per file', 'is this file over 1000 lines', 'count lines in the change'; for cyclomatic or cognitive complexity use /code-metrics:audit-complexity, and for a repo-wide dashboard this is the wrong tool (it measures a change).
- ▌ Hold My Hand · melodic-software bundleHold the user's hand through a long multi-step job. Partition the remaining work into phases and present ONLY the current one, never the phases after it beyond a one-line 'Phase 1 of 8' count. Each phase names where to be, numbered steps with exact commands, the expected output, the common failure, who performs each step, and the exact reply that advances. Once invoked, this holds for the rest of the session. Use when: 'hold my hand', 'walk me through this', 'one step at a time', 'one phase at a time', 'don't show me the next step yet', 'guide me through all of this', 'exact steps', 'hand-hold'. This is a STANDING posture that withholds later steps: adhd:shape sets action-first formatting for every response and shows the whole list, adhd:clarify reshapes one dense message already on screen, wizard:generate writes a bash script the human runs with no assistant in the loop, and session-flow:workflow routes to the next stage without scripting its steps.
- ▌ Research Deep · melodic-software bundleDispatch deep external research to the heaviest isolated execution tier available, a workflow engine, an isolated subagent, or inline as last resort, keeping the main conversation clean while the full research discipline runs. Itself runs in main context, the only place both the Workflow tool (absent from every non-fork subagent) and a dependable Agent spawn are guaranteed. Use when: 'deep research', 'research these N topics', 'broad multi-source research', 'compare these tools thoroughly', 'migration research', 'exhaustive research on X'; for a single small lookup use the research skill directly, which already dispatches its own subagent.
- ▌ Course Digest · melodic-software bundleExtract and synthesize online video courses into repo-applicable recommendations via browser automation (Playwright + claude-in-chrome), transcript extraction, frame analysis, and LLM synthesis. Use when: 'course digest', 'digest this course', 'analyze course', 'Dometrain', 'watch this course for me', 'course takeaways', 'extract from course', 'summarize course', user shares a Dometrain/Pluralsight/Udemy course URL, or wants course patterns applied to their codebase. Single public YouTube videos → use /knowledge:video-digest. Actions: full pipeline (default), extract (phases 1-2 only), analyze (phases 3-5 only), status (list all digested courses), resume <slug> (continue extraction), continue <slug> (resume from saved session state).
- ▌ Justify · melodic-software bundleJustify the existence of any artifact you point at: was there a reason for this when it was built, and does that reason still hold today. Walks one target you name (a path, a `path#heading`, or a kind-prefixed identifier) and reports a verdict on the evidence-earned-keep ladder, each row carrying how much evidence supports it. Read-only: it reports and then discusses, never applies a remedy, and writes its findings to the memory tier; the one tracked write, persisting the resolved home to the concern file, needs explicit confirmation. Use when: 'justify this', 'does this need to exist', 'why is this here', 'is this still valid', 'earn its keep', 'justify the existence of'. With no target it never sweeps; it uses what the session has been discussing, else offers to rank candidates by age, else asks. Not for the enforcement surface (hooks, CI lanes, gate scripts, branch protections), which routes to the sibling `audit` skill, and not for applying a fix, which routes to the owner named in the finding.
- ▌ Realign · melodic-software bundleExecute an enforcement-surface audit's findings behind an explicit per-item human gate. Consumes the findings artifact either producer wrote. It never scans or re-judges the surface itself. For each finding the operator accepts, it drives interview → explore and research → plan → implement through presence-gated skill composition, executing every removal down the rollback ladder: config-disable first, observe for a window with a stated end date, delete last with a recorded rationale. Unproven items route to a time-boxed ablation batch; security-class items surface the capped verdict's evidence and wait for the human's own call; remediation owned by an upstream or a forge control plane becomes a delegation rather than a local patch. Use when the ask is to act on an enforcement-surface audit's findings ('realign our enforcement surface', 'the audit says retire it, do it'), to retire or peel back automation already judged, or to start or advance an ablation window ('disable this gate and observe it'). This is th
- ▌ Design Handoff · melodic-software bundleGate and package a finished design for /planning:plan: binary check that every thread in design-threads.md is RESOLVED, directional, or TAGGED-DEFERRED, then an advisory six-dimension coverage table, then emit the plan-ready summary and resume prompt. Use when: 'design handoff', 'hand off the design', 'is the design ready', 'plan-ready summary', 'design gate', /planning:design discussion rounds stop surfacing gaps, or entering /planning:plan from a completed design session. FAILs on any thread that is unresolved AND untagged. Names it and routes back to /planning:design. Skip when: still exploring the design space. Use /planning:design; mid-session save-point to clear and resume later. Use a session-handoff capability.
- ▌ Pressure Test · melodic-software bundleBuilds a throwaway interactive terminal app to pressure-test business logic, a state machine, a data model, or an API surface before committing to it. Use when the question is whether a state model, reducer, or data shape holds up under real cases: 'does this state machine handle X then Y', 'sanity-check this data model', 'feel out the API'. Any question answered by driving state by hand and watching it change. Produces a portable pure logic module (liftable into production) behind a disposable shell, a terminal app by default, or a self-contained HTML demo a non-developer can drive by clicking buttons when no terminal fits. Captures the validated answer in a durable note. Not for visual or design questions. Use /prototype:explore-directions for those.
- ▌ Clean Stop · melodic-software bundleGet a session to a clean stopping point before the machine may go away. Everything durable, everything linked, nothing stranded on local disk. Sweep every repo and worktree touched for uncommitted, unpushed, or PR-less work, push it durable, put follow-ups and context in PR/issue bodies a cold agent could resume from, prune only what is provably safe, then give a free-and-clear verdict. Use when: 'clean stop', 'get to a clean stopping point', 'safe to shut down', 'wrap up before I lose this machine', 'make everything durable', 'stopping for the day', 'is anything stranded', 'leave it clean'. Makes durable freely; gates destructive cleanup.
- ▌ Keep Going · melodic-software bundleRecover and continue after an interruption, rate limit, crash, disconnect, or gap, or when live off-thread work looks stalled and you are asked to check on it. Inventory off-thread work, inspect its REAL output, act only on evidence (resume / rerun / kill-and-restart), then continue the main task where it stood. Use when: asked to keep going, continue, resume, or pick up where you left off; after being cut off or interrupted ('what were you doing'); or asked to check on, poke, or judge whether off-thread work is stuck ('check the monitor', 'is it stuck', 'stop staring at it'). Infers intent from the conversation; arguments optional. After a usage limit lifts it continues rather than summarizing-and-stalling; it gates killing or re-firing side-effectful work. To retire finished off-thread work and reconcile the task ledger rather than resume, use /session-flow:reconcile.
- ▌ Worktree · melodic-software bundleManage git worktree lifecycle for parallel-session isolation: create (guided naming via EnterWorktree), status (PR + staleness inventory), cleanup (file-lock-aware removal), audit (infrastructure health). Use when: 'create worktree', 'worktree status', 'clean up worktrees', 'orphaned worktrees', or proactively when on main before writing code, not for PR lifecycle (use /pull-request).
- ▌ Visualize · melodic-software bundleDecide the best visual form and medium for what is in the conversation right now, then render it. Use when asked to visualize, diagram, chart, draw, sketch, or render something, or which visual form fits it best. Infers the target from the conversation, picks a form (a mermaid diagram, a markdown table, a hand-authored SVG/CSS chart, ASCII/Unicode art, code-shape sketches, a rich rendered page, or, where the bundled design skill is available, a hand-editable design canvas) and a medium (inline terminal, a local HTML file, or a published Artifact), renders good defaults, and asks only when the target is genuinely ambiguous and no form was named. It routes chart craft and artifact-design fundamentals to those capabilities when installed. It does not teach them. Not for polishing a specific chart's colors/axes (a chart-craft/dataviz capability owns that) or restating dense text in plainer words (a comprehension/digest concern).
- ▌ Attend Queue · melodic-software bundleAttend the human-in-the-loop queue for loop-lane operation: ONE attention view merging worker-escalated items (human-gated role label + machine-marked escalation comment) with untriaged raw intake, then drive each row to resolution, answer escalated questions via interview, write answers back as issue comments, ratify first-drain C3 admissions, and flip unblocked items to the autonomous-eligible role label. Use when: 'attend the queue', 'attend queue', 'answer escalations', 'work the escalation queue', 'what needs my attention across the lanes', 'HITL queue', 'ratify admissions', 'clear the human queue'. Attended lane of the loop-lane three-session topology, judgment only; never executes work items, never merges. Composes /work-items:triage (attention view + machinery) and /planning:interview. Sibling skills: /work-items:work-loop (autonomous drain), /work-items:triage (raw intake), /work-items:track (backlog CRUD).
- ▌ Audit Pass · melodic-software bundleRun ONE coordinated, ordered, resumable pass over a named target repository: a three-scope inventory first (managed policy read-only, user scope routed as recommendations, project scope), then delegated checks lane by lane, findings persisted per lane so an interrupted run resumes instead of restarting, and one human gate for the whole pass instead of one per skill. Adds run semantics, not checks: every check belongs to the plugin that owns it and is invoked presence-gated. Read-only on bare invocation; edits only behind an explicit --fix override, and never to managed policy or user-scope files. Use when: 'audit pass', 'run one pass over this repo', 'coordinate the audit skills', 'audit this repo end to end', 'resume the audit', 'one reconciled findings report', 'sweep all three scopes', or before a release that needs a single diffable findings artifact.
- ▌ Morning Brief · melodic-software bundlePrints the operator's read-only morning view for the current GitHub repo in one pass. Open counts per queue label (needs-triage / ready / needs-decision / needs-human), the gh-native merge-ready PR list, parked decisions with their RECOMMENDED lines, and loop-lane telemetry freshness (last-cycle age + flags). Use when: 'morning brief', 'morning view', 'ops dashboard', 'what needs attention', 'daily standup view', 'operator morning pass', 'queues and merge-ready'. Read-only and gh-based, never mutates issues, PRs, labels, or comments.
- ▌ Observability · melodic-software bundleRead and report on locally captured Claude Code telemetry, OTEL DuckDB store, collector, optional Aspire dashboard, the per-session hook event log and hook-event JSONL, ccusage, with cross-session trend reports, a per-session report, and store pruning. Use when: 'claude observability', 'OTEL', 'collector', 'token burn rate', 'hook latency', 'cost breakdown', 'how am I doing', 'what did this session do', 'hook event log', 'which hooks fired'; read-only except the explicit clean action.
- ▌ Audit Noise · melodic-software bundleClassify tracked markdown for nine noise shapes — historical citations, ghost refs to ephemeral paths, "Why this file exists" preambles, hard-coupled consumer lists, scope/loading meta-commentary, plan/changeset references, conversational antecedents ("as you asked"), tracker/PR back-references, and prohibitions with no positive alternative — emitting Tier 1 (remove/relocate), Tier 2 (review needed), and Tier 3 (likely legitimate) findings with per-shape treatment guidance; read-only on audited files. Use when: 'audit markdown noise', 'declutter', 'check for stale citations', 'find ghost refs', 'classify preamble', 'strip conversational residue from a doc', 'find negations without a positive', 'sweep a rule/skill/convention doc for noise', or before editing any tracked .md — not for prose flavor/compression (use /compress), structural markdown lint (your repo's markdown linter), or the same residue shapes inside code comments (use /code-tidying:audit-comment-residue, which owns non-markdown files).
- ▌ Implement · melodic-software bundleExecute approved plans, fix bugs, and make code changes inline with incremental validation. TDD by default, build+test after each logical block, commit at green checkpoints, and divergence detection that routes back to planning instead of pushing through a broken approach. Use when: 'implement this', 'execute the plan', 'fix this bug', 'refactor', 'build this', 'write the code', 'make this change', 'apply the plan', or whenever code is about to be written; modes: feature, fix, refactor, config.
- ▌ Docpage Digest · melodic-software bundleIngest a single online documentation page (a docs-site URL) into a verified knowledge slice. Fetch the original, inventory it into a SOURCES.md, fan out per-section digest agents, run dual verification (one cross-vendor verifier), and hand off an interview-ready decision artifact. Use when: 'digest this doc', 'ingest this documentation page', 'run the doc pipeline on <url>', 'docpage digest', 'pull this vendor doc into the knowledge base', 'distill this docs page', or the user supplies a documentation URL to turn into durable corpus artifacts. Remote documentation PDFs (model cards, system cards) DO belong here; book files (PDF/EPUB books) route to /knowledge:book-distill, video courses to /knowledge:course-digest, single YouTube videos to /knowledge:video-digest; not ad-hoc summarization, the output is a durable verified corpus slice plus an interview handoff, not a chat summary. Publisher profiles live under context/ (first: Anthropic docs).
- ▌ Devils Advocate · melodic-software bundleStress-test plans and proposals via systematic adversarial review. Assumption extraction, evidence check, failure scenarios, operational gotchas. Before implementation begins. Use when: asked to attack a plan or proposal ('devil's advocate', 'stress test', 'poke holes', 'what could go wrong'), or before implementation on new dependencies, infrastructure/CI/build changes, or any architecture decision with cross-module blast radius. An `incumbent` mode turns the same adversarial lens on the status quo ('is there a better way now', 'should we still use X'), surveying alternatives before a plan commits to keeping an existing tool or approach. Not for code correctness bugs or pre-PR verification.
- ▌ Apply · melodic-software bundleApply a prior /repo-fleet-hygiene:audit action-plan JSON behind one fleet confirmation: default dry-run re-derives branch/worktree tips and prints the ordered batch; --apply mutates only after interactive confirmation or --yes. Owns batched merged-local-branch deletion with fail-closed OID refresh; cleans merged/prunable/missing worktrees in plan order (branches before worktrees). Use when: 'apply fleet plan', 'execute fleet cleanup', 'batch delete merged branches', 'one confirmation for fleet cleanup'.
- ▌ Orchestrate · melodic-software bundleArm the CURRENT session for an orchestration-heavy task by loading seven proactive-orchestration imperatives (delegate/fan-out, spec-every-spawn, fresh-context verify, run-workers-well, nested subagents, surface drift, calibrate-to-conditions) as active standing instructions; optionally export them as a paste-ready brief for a spawned worker or fresh session. Use when: 'orchestrate', 'orchestration brief', 'prime this session', 'arm for orchestration', 'about to do heavy delegation', 'worker spawn prompt', 'delegation preamble'.
- ▌ Extract Ssot · melodic-software bundleDeduplicate repeated markdown content, rule files, skill bodies, ADRs, docs, into a single named source of truth and migrate every call site to cite it by exact heading. Use when the same prose, literal, or concept appears (or is reworded) across files: 'DRY this prose', 'extract a shared rule', 'single source of truth for X', a value-bump diff touching several files. Reports duplication at every multiplicity in rule-of-one / rule-of-two / rule-of-three buckets, offering only non-abstracting remedies below three. Creating a NEW SSOT artifact still refuses below the Rule of Three.
- ▌ Simulation · melodic-software bundleAgentic AI-driven multi-persona EventStorming simulation on Miro. Use when: 'simulate a workshop', 'run an EventStorming simulation', 'agentic EventStorming', 'multi-persona domain modeling on Miro'. Actions: --simulate [domain] (full multi-persona agentic workshop), --process-model / --design-level [board] (deep-dive against an existing board), --evaluate, --retrospective, --induction, --value, --crc, --ux, --discover-bcs (BC heuristics vs Miro board). Needs a Miro MCP server; degrades to structured-markdown output when Miro is absent. For methodology / facilitation reference use /event-storming:methodology.
- ▌ Skill Authoring · melodic-software bundleAnthropic's internal skill-authoring playbook. 9 skill categories, gotchas-section pattern, progressive disclosure (SKILL.md hub + spoke files), description-as-trigger discipline, config.json first-run setup, persistent CLAUDE_PLUGIN_DATA storage, CLAUDE_EFFORT effort-aware behavior, helper scripts, on-demand session-scoped hooks, distribution, and composition. Use when: creating or reviewing a SKILL.md, choosing a skill's category or structure, writing its description or gotchas section, or asking for skill-authoring best practices: 'create a skill', 'how to write SKILL.md', 'skill best practices'.
- ▌ Find Handoff · melodic-software bundleRecover a lost handoff after `/clear`. Find the save-point file or resume prompt when the resume prompt was written but never copied and the fresh session has zero context. Read-only detection ladder: known-location glob of `<memory_dir>/handoffs/`, then a bounded, recency-ranked scan of transcripts (excluding the current session's own file) for the handoff directive and dashed-rail markers, then a confirm-before-resume gate. Use when: 'find my handoff', 'recover the handoff', 'I lost the resume prompt', 'forgot to copy the resume prompt', 'I cleared without saving the prompt', 'where's my handoff', 'recover after /clear', 'get back the handoff'. Surfaces only the resume prompt + handoff metadata, never raw transcript content; hands to `/session-flow:keep-going` when the recovered session ended mid-work rather than at a clean save-point.
- ▌ Show Options · melodic-software bundleLay out which skills fit this moment as a decidable menu, a ranked shortlist per bucket plus the complete remainder by name, so nothing is hidden and the human chooses. Buckets: Now, Next, Skipped upstream (artifact-grounded), Later (the in-domain remainder, named-only), and a rotating Spotlight of three. Never omits an option because it judges the step already done or unnecessary; that judgment becomes an annotation and may affect rank, never presence. Resolves candidates from the full installed catalog rather than the in-context skill listing, which omits every manual-only skill and truncates most descriptions. Use when: 'what should I run next', 'what are my options', 'what am I forgetting', 'which skill fits here', 'what else could I run', 'show me my options', 'what skills apply now'. Writes one small rotation ledger per invocation so the Spotlight advances; otherwise read-only. Not the staged-workflow navigator that routes to exactly one next stage (/session-flow:workflow), not a situation report (/sess
- ▌ Meter Prosody · melodic-software bundleScan lines and make structure serve meaning with Pat Pattison's methods. Meter (scansion, Paradigms I/II/III, Pentad, Goldilocks, the 'into' rule, In Memoriam quatrain, pitch-stress), prosody (motion-emotion, greedy spots, tone-of-voice, three phrasing types), section stability (stable/unstable scan), and lyric-melody alignment. Use when: 'scan this line', 'can this be common meter', 'is this verse stable or unstable', 'my words don't fit the music', 'greedy spot in line 2', 'set lyrics to this tune', 'does my song feel right'. For song sections/form use /songwriting:song-form; for rhyme use /songwriting:rhyme.
- ▌ Map Landscape · melodic-software bundleChart a set of repositories as a C4 System Landscape plus an application-portfolio table: discover the repositories, collect owner/runtime/framework/dependency/last-touched facts from a tested script, draw only relationships a cited fact supports, and write both artifacts into the consumer's declared architecture home. Use when: 'map our landscape', 'system landscape', 'what systems do we have', 'application portfolio', 'who owns which repo', 'what runtimes are we on', 'chart our repositories', 'C4 context across repos', 'inventory our systems'. Skip when: the question is inside ONE codebase (module friction, shallow modules, seam placement) which is /architecture:improve, or the goal is fleet cleanup (stale branches, orphaned worktrees, moved remotes) which is /repo-fleet-hygiene:audit.