melodic-software
- 406 skills
- 0 followers
- 30 repo stars
- 5 days ago last updated
- ▌ Audit Permission Grants 2 · melodic-software bundleAudit Claude Code permission grants (allowed-tools frontmatter and permissions.allow in every settings scope) for portability and auto-mode durability: dropped interpreter wildcards, machine-specific paths, literal substitution tokens, inert plugin self-grants. Report-only. Use when: 'check permission rules', 'why was my allowed-tools grant ignored', 'audit allow rules', 'is this permission portable', or a guarded helper is denied despite an allow rule. Effective state: audit-permission-state.
- ▌ Audit Prompting Postures 2 · melodic-software bundleFind posture guidance an instruction component lacks that the official prompting guide says its purpose needs: delegation, guardrails, stop rules, destructive-action confirmation. Report-only. Use when: 'posture audit', 'audit prompting postures', 'is my skill missing guardrails', 'missing delegation criteria', 'should this component confirm destructive actions', 'does my CLAUDE.md say when to stop', 'align my components with the prompting guide'. Text present and wrong: audit-instructions.
- ▌ Ubiquitous Language · melodic-software bundleThe project's ubiquitous-language glossary: locate, lookup (read terms), seed a first one, curate (canonical terms, rejected synonyms, definitions), audit. Use when: 'what does this domain term mean', 'update the domain glossary', 'define this domain term', 'standardize this vocabulary', 'these names conflict', 'tidy our codebase terminology', 'the terms in our domain model', 'we have no glossary yet', 'check our glossary', 'prune the glossary', 'the glossary feels bloated', domain modeling resolves vocabulary, or a skill needs domain terms before naming something. Not for dictionary definitions or bounded-context discovery.
- ▌ Fanout 2 · melodic-softwareEval-only stand-in for the review plugin's fanout: breadth review of a change, one ranked report on disk.
- ▌ Route 2 · melodic-softwareModel and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value; fan-out stays off frontier models unless config opts in. Use when asked 'which model for the subagents', 'route the roles', 'what effort should the workers use', 'roles for the workflow args', 'model routing' or 'is fan-out on Fable', or before a skill launches a workflow that takes args.roles.
- ▌ Codify 2 · melodic-softwareCounts how often a described mistake recurs in recent commits and the session, picks the strongest enforcement-ladder rung that can catch it, places the lesson by scope, and proposes a check proven to fail on the old code and pass on the current code; `preferences` proposes user-scope lines for what a person keeps typing across sessions; also takes a review findings file or merged pull requests' review comments as the source. Use when: 'codify this', 'this keeps happening', 'stop us making this mistake again', 'turn this correction into a check', 'what rung catches this', 'prove this check', 'can we stop re-finding this', 'mine our review comments', 'put what I keep repeating into my instructions'.
- ▌ Playground · melodic-softwareCreates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a playground, explorer, or interactive tool for a topic.
- ▌ Unhobble 3 · melodic-softwareBare-baseline experiment: strip a repo's standing instructions, log stumbles against the bare model, then restore only those with repeated same-cause evidence. Measures the model where 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', 'deletion watch', 'watch this rule before deleting it'. Human-gated, resumable.
- ▌ Narrate 2 · melodic-softwareText-to-speech: turn a narration script into narration.wav plus words.json with per-word start and end times, so video, captions or a page can sync to the voice. Use when: 'narrate this script', 'text to speech', 'make a voiceover', 'I need audio for this explainer'. Not for transcribing existing audio.
- ▌ Running Retro 2 · melodic-softwareMid-session retro checkpoint: a subagent files findings from the transcript so far into a running ledger, never applied; `arm` runs it after the session ends. Use when: 'running retro', 'checkpoint this session', 'watch this session in the background', or on a /loop.
- ▌ Audit Instructions 3 · melodic-softwareWhen the bundled claude-api skill resolves in this session, prefer its prompt-audit for application-code prompts and model migration; this skill for Claude Code instruction surfaces. Report-only audit of CLAUDE.md, AGENTS.md, rules, skills, agents and hook text for stale, misstated, or conflicting instructions. Use when: 'audit instructions', 'too prescriptive', 'stale Claude Code behavior', 'my @path import is not loading', 'which instruction wins'. Missing text: audit-prompting-postures.
- ▌ Explain Change 2 · melodic-softwareEval-only stand-in for the review plugin's explain-change: reports that the digest was skipped. Use when asked to 'explain this PR'.
- ▌ Audit Sessions 2 · melodic-softwareAudit every Claude Code session on this machine for wasted time and tokens against a reference baseline, routing each finding to its fix, plus session score trends over time. Use when: 'audit my sessions', 'which sessions burned the most tokens', 'show trends', or corrections keep repeating. One session's retro: /session-flow:retro.
- ▌ Audit Native Overlap 2 · melodic-software bundleMap of where this repo's skills and agents duplicate a native Claude Code surface; read-only unless `apply` bakes an approved reference. Use when: 'does this skill duplicate a built-in', 'what does Claude Code already ship for this', 'is our install-state audit the same as /doctor', 'refresh the native-surfaces registry', 'which of our skills overlap bundled skills'. Enumerating what is invocable: /harness-ops:inventory.
- ▌ Audit Instructions 2 · melodic-software bundleWhen the bundled claude-api skill resolves in this session, prefer its prompt-audit for application-code prompts and model migration; this skill for Claude Code instruction surfaces. Report-only audit of CLAUDE.md, AGENTS.md, rules, skills, agents and hook text for stale, misstated, or conflicting instructions. Use when: 'audit instructions', 'too prescriptive', 'stale Claude Code behavior', 'my @path import is not loading', 'which instruction wins'. Missing text: audit-prompting-postures.
- ▌ Audit Plugin Landscape · melodic-software bundleOn-demand, read-only report on which installed plugins and marketplaces have gone stale, which overlap, and what to adopt, adapt or drop. Use when: 'are my plugins stale', 'plugin landscape', 'which plugins overlap', 'is there a better alternative to this plugin', 'which marketplaces are dead'. Bringing the fleet current: /harness-ops:plugins.
- ▌ Audit Skill Visibility 2 · melodic-software bundleWhen the built-in skill-doctor command resolves in this session, prefer it for cost; this skill for unseen ones. Use when: 'why do I never use most of my skills', 'why does Claude never suggest this skill', 'are my skill descriptions being dropped', 'is my skill listing over budget', 'which skills can the model actually see', 'which skills are starved', 'I have too many skills to know when to use them', 'audit skill visibility'.
- ▌ Plan User Research · melodic-softwareUser research plans and instruments for the app being built: picks the method, then writes the discussion guide, screener, usability test script, survey or inclusive-research plan, evidence-labeled. Use when: 'write a discussion guide', 'write an interview script', 'write a screener', 'write a facilitator guide for a usability test', 'draft survey questions', 'interviews or another research method'.
- ▌ Generate File Name Gate · melodic-software bundleEmit the file-name gate into a consuming repository: a standalone bash checker plus its own test suite, with the casing rule, roots, and exemptions inlined from the resolved docs-naming configuration, and optionally the path-scoped rule file. The emitted pair carries no dependency on this plugin at run time. Refuses to overwrite without --force, and states the wiring it deliberately leaves to the consumer. Use when: 'generate the file-name gate', 'add a CI check for doc filenames', 'enforce the naming rule', 'emit the naming checker', 'we need a gate for this convention', 'write the file-names rule file', or after docs-naming:setup apply has written the configuration.
- ▌ Audit Automation Gaps 2 · melodic-software bundleAudit a repo's Claude Code automation (hooks, MCP servers, skills, subagents, scheduled tasks) against the enforcement hierarchy, with evidence-backed PASS/REJECT/CONDITIONAL verdicts, REJECT by default. Use when: 'audit automations', 'what automations should we add', 'are we missing any hooks', 'hook gap analysis', 'should I add an MCP server for X'; pass --implement to apply approved items, or filter by category (hooks|mcp|skills|subagents|scheduled).
- ▌ Draft Auto Mode Rules 2 · melodic-software bundleDraft a paste-ready `autoMode` classifier block by interviewing the user about what should and should not be auto-approved, each entry in the shape the classifier reads well and every section keeping `$defaults`. Use when: 'help me write auto mode rules', 'draft an autoMode block', 'set up auto mode', 'add an auto-mode rule for X', 'my auto mode rules are too vague', 'rewrite this classifier entry', or an audit shows rules dropped or ignored. Prints only, never writes a settings file.
- ▌ Audit Permission State 2 · melodic-software bundleWhen the bundled fewer-permission-prompts skill resolves in this session, prefer it to reduce prompts via an allowlist; this skill to see the state in effect. Report-only: merges every settings scope into the allow/ask/deny set in effect with source and precedence per rule, and flags allow rules auto mode drops. Use when: 'what permissions are actually in effect', 'which of my rules survive auto mode', 'is my managed policy being read'. A rule ignored for its shape: `audit-permission-grants`.
- ▌ Audit Mod Posture · melodic-software bundleRead-only audit of the mods this Claude Code can run: installed and built-in mods, their hooks and calls, and whether the built-in guard is seated. Use when: 'which mods run on my machine', 'mod posture', 'is the sec-default guard on', 'can a mod bypass my deny rules', 'audit my mods'. Never loads a mod or prints settings. Not for: writing a mod, or settings correctness (/harness-config:audit).
- ▌ Audit Performance 2 · melodic-software bundleSlowness diagnostic that never 'fixes', run before restarting or deleting: version, retention sweep, install bloat, hook/subagent fan-out, kernel-leak census. Use when: 'Claude Code is slow', 'typing lags', 'my machine freezes when Claude runs', 'why is this session sluggish', 'my hooks are slowing everything down', 'too many subagents'. Upstream bugs: /harness-ops:known-issues. Stale files: /harness-ops:audit-install-state.
- ▌ Migrate · melodic-software bundleMove instruction content to AGENTS.md as the one content home, keeping a one-line CLAUDE.md shim while a shim is what makes it load. Plans first; every write is operator-gated. Use when: 'migrate to AGENTS.md', 'plan the AGENTS.md migration', 'move CLAUDE.md content to AGENTS.md', 'add the AGENTS.md shim', 'our CLAUDE.md should be one line', 'share instructions with Codex and Cursor', 'can we drop the CLAUDE.md shims yet'. Not the placement sweep (audit) or applying findings (realign).
- ▌ Recommend Skills · melodic-software bundleRanked menu of every installed skill that fits this moment (Now, Next, Skipped upstream, Later, Spotlight), hiding nothing; a free-text question gets one skill and an example prompt. Use when: 'what are my options', 'which skill fits here', 'what am I forgetting'. One next stage: /session-flow:workflow.
- ▌ Build CLI · melodic-software bundleCommand-line tools and scripts a team builds for itself, made for people and coding agents alike. Use when building a new CLI command or script, extending one's interface (arguments, flags, output, exit codes), porting one to another language or platform, or reviewing one against the CLI contract.
- ▌ Realign File Names · melodic-software bundleApply a file-name rename plan one file at a time, one human acceptance each: git mv, rewrite only the reference shapes each citing file's tier allows, rebuild generated records, and sweep for stragglers. Refuses a blanket yes, a range, a glob, and 'all'. Use when: 'apply the rename plan', 'apply FN-...', 'do the docs renames', 'rename these files', 'execute the file-name findings', 'accept that rename'. Needs a plan from docs-naming:audit-file-names; never commits.
- ▌ Write Animation · melodic-softwareWrite one interface animation in any stack after deciding whether it should move at all, then build it from the project's own motion tokens and the stack's current documentation, with reduced motion included. Use when: 'animate this', 'add an entrance animation', 'make this feel smoother', 'add a transition to', 'make the drawer draggable'.
- ▌ Audit Suppressions · melodic-software bundleList every lint and type-checker suppression in a change, a path, or the tree (`--all`): eslint-disable, @ts-expect-error, noqa, type: ignore, pylint, pyright, shellcheck disable, C# pragmas and SuppressMessage, nolint, PowerShell SuppressMessageAttribute, markdownlint, rubocop, @SuppressWarnings; and the directives that switch off the evidence a quality bar relies on: coverage exclusions (istanbul, c8, coverage.py), mutation-testing exclusions (Stryker), security-scanner suppressions (bandit nosec, nosemgrep, gitleaks allow). Each row names its rule ids, its reason, and whether it is justified; listed correctness rules are marked. Reports, never gates. Use when: 'how many suppressions', 'find eslint-disable comments', 'which noqa have no reason', 'suppressions added in this change', 'audit lint suppressions', 'count suppressions to ratchet'. Complexity: /code-metrics:audit complexity.
- ▌ Audit Install State 2 · melodic-software bundleRead-only audit of `~/.claude` and `~/.claude.json`: the deep inventory of unmanaged files. Use when: 'what is in my ~/.claude', 'why is my Claude Code install so big', 'does Claude Code clean up after itself', 'check cleanupPeriodDays', 'is this lock file dead', 'tidy my Claude Code install'. Deleting: /disk-hygiene:clean.
- ▌ Control Claude Code · melodic-software bundleControl skill /app-control:drive reads to run Claude Code's terminal UI with a plugin loaded and record screenshots, video and stream-json logs of its mods, skills, hooks and commands.
- ▌ Audit Tools · melodic-softwareAudit a repository's developer tooling: scripts, command-line tools, skills, hooks, subagents and MCP configs. Read-only findings report on a bare run; changes only after an explicit yes. Use when: 'audit our tooling', 'what scripts and tools does this repo have', 'find duplicate or stale scripts', 'review our CLIs'.
- ▌ Audit Sessions · melodic-software bundleAudit every Claude Code session on this machine for wasted time and tokens against a reference baseline, routing each finding to its fix, plus session score trends over time. Use when: 'audit my sessions', 'which sessions burned the most tokens', 'show trends', or corrections keep repeating. One session's retro: /session-flow:retro.
- ▌ Check Visual Parity · melodic-software bundleHold a UI pixel-for-pixel steady through a change: PNG screenshots of the listed states before the first edit (baseline), then again at each green checkpoint, with differing pixels counted against pixel_tolerance (compare). Never edits a baseline. Use when: a plan phase has a Parity contract line, a refactor must leave the UI unchanged, 'check visual parity', 'did this change the UI'.
- ▌ Measure Delivery · melodic-software bundleRead-only report of the five DORA delivery metrics (deployment frequency, change lead time, change fail rate, failed deployment recovery time, deployment rework rate) as a team trend from the default branch's history, never per person. Use when: 'measure delivery', 'DORA metrics', 'deployment frequency', 'change lead time', 'change fail rate', 'how fast do we ship', 'delivery trend'. Backlog counts are /work-items:track stats.
- ▌ Remove Comments · melodic-software bundleEdits code so its comments earn their keep under a posture (none or 'strip', necessary or 'aggressive', explanatory): deletes zero-information comments, renames or restructures so explanatory ones can go, keeps terse load-bearing ones; a 'safe' mode, and an edit-free 'report'. Use when asked to 'remove comments' or 'dissolve comments', when code has too many or agent-written comments, or to make code self-documenting. Read-only residue flagging is /code-tidying:audit-comment-residue.
- ▌ Audit File Names · melodic-software bundleRead-only audit of a docs tree's file names against a configured casing rule: proposes a name per offender, classifies every reference to it, refuses case-only collisions, and writes the plan realign-file-names applies. Use when: 'audit file names', 'are our doc filenames consistent', 'plan a docs rename', 'which files break the naming rule', 'find every reference to this doc', 'rename the docs tree', 'lower-kebab the docs folder', 'what would a docs rename touch'. Renames nothing.
- ▌ Map Dependencies · melodic-software bundleProject dependency graph from build manifests, citing the file and declaration on every edge. Use when 'project reference graph', 'what references what', 'internal dependencies', 'package references', 'which projects depend on which'. Skip for which repositories exist (map-landscape), shallow modules (improve), or source imports and call graphs.
- ▌ Machine Profile · melodic-software bundleRe-runnable profile of this machine's facts and identity domains, with drift between the stored profile and the host now; read-only unless the operator confirms a write, never installs, never reapplies a stored value on its own. Use when: 'profile this machine', 'what does this host have configured', 'has this machine changed', 'which identity domains exist here', 'hand my machine facts to setup'.
- ▌ Audit Friction · melodic-software bundleAudit Claude Code sessions for permission and autonomy friction (denials, approval prompts, hook blocks, hand-offs), traced to cause in one decision brief. Use when the agent keeps asking or handing off, auto mode denies, or re-measuring after permission fixes.
- ▌ Map Components · melodic-software bundleC4 component view of the modules inside one deployable, one directed arrow per internal build reference, each citing its declaration. Use when 'component diagram', 'what is inside this service', 'module dependencies', 'which way do the arrows point', 'layering of this deployable'. Skip for which repositories exist (map-landscape), all deployables (map-containers), or module-design friction (improve).
- ▌ Map Containers · melodic-software bundleC4 container diagram of one software system: deployables, the stores and brokers their tracked configuration binds, and the edges those endpoints resolve to. Use when 'what actually runs', 'deployables and databases', 'modular monolith', 'which services bind to which broker'. Skip for which repositories exist (map-landscape), inside one deployable (map-components), or environment topology.
- ▌ Map Deployment · melodic-software bundleC4 deployment view of committed infrastructure: which containers sit on which declared nodes, per environment, and what differs between two environments. Use when 'map deployment', 'deployment diagram', 'what is different in production', 'IaC topology', or 'where does this container run'. Skip when the question is a live cloud inventory, cost, or runtime health.
- ▌ Behavior Probes · melodic-software bundleLive probes of Claude Code permission, auto-mode, hook, worktree, subagent and sandbox behavior as cases with paired controls, each reported pass, fail or inconclusive with the Claude Code version; dry run by default, live runs opt-in and capped. Use when: 'rerun the behavior probes', 'does auto mode still deny this', 'add a probe case', 'which probes does this release touch'.
- ▌ Audit Pass 2 · melodic-software bundleRun one coordinated, resumable audit pass over a repo: a three-scope inventory, then each owning plugin's checks lane by lane, presence-gated, with findings persisted per lane and one human gate for the whole pass. Read-only unless --fix. 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 a release needs one diffable findings artifact.
- ▌ Observability 2 · melodic-software bundleWhen the bundled explain-usage skill resolves in this session, prefer it for a plain-language breakdown of this session's tokens; this skill for cross-session reports from the local telemetry stores (OTEL DuckDB, hook event log, ccusage): token burn, cost, hook latency, per-session activity, usage per work item; read-only except the explicit clean action. Use when: 'claude observability', 'how am I doing', 'what did this session do', 'which hooks fired', 'compare two sessions', 'tokens per work item'.
- ▌ Plugins Audit · melodic-softwareRead-only dry run of /harness-ops:plugins sync: predicts the marketplace refreshes, updates, installs, enables and scope divergences sync or converge would act on, and issues none of those calls. Its update count is a lower bound against the unrefreshed catalog. Use when: 'are my plugins current', 'check plugin drift', 'audit my plugins', 'what would plugin sync do', or before relying on a plugin that might be stale.
- ▌ Prerequisites · melodic-software bundleRead-only report of external tools the enabled plugin fleet declares, and which of them are missing. Use when a hook says a formatter or CLI is missing, or when asking whether this machine has what the enabled plugins need. Never installs.
- ▌ Absorb Upstream · melodic-software bundleAn outside source (a GitHub repository or one web page or post) absorbed into a tracked docs/upstream record: per idea, what it does, the problem behind it upstream and here, and a take, adapt, already-have or reject disposition. Use when the user asks to absorb an upstream repository or post, decide what to borrow from it, or write a docs/upstream record for it. A docs page digested into the knowledge base goes to /knowledge:docpage-digest.
- ▌ Build Generator · melodic-software bundleBuilds a throwaway generator the person tunes for an artifact prompting cannot hit, whose saved output goes into the project.
- ▌ Structure · melodic-softwareStructure of the app being built: user flows with their branches, exits and the states each step handles, information architecture, navigation and content structure, and card-sort or tree-test plans. Use when: 'map the sign-up to first-success flow', 'which states does this flow need to handle', 'structure the navigation', 'draft a sitemap', 'plan a card sort', 'plan a tree test', 'outline the first-run flow'.
- ▌ Setup 68 · melodic-software bundleRecord a repository's developer tooling conventions as current fact and point AGENTS.md at them; check reports drift, apply converges.
- ▌ Audit Defaults · melodic-software bundleRecheck every bundled multi-agent role default (model, effort, the fan-out guard) against the upstream pointer recorded beside it, and report which defaults have drifted or whose recheck trigger has fired, each with fetched evidence and a proposed diff to reference/defaults.yaml; `repo` mode sweeps the repository's own model, effort, subagent and workflow guidance for stale or copied upstream claims. Proposes only; never edits a file. Use when: 'are the routing defaults current', 'audit the role map', 'recheck model defaults', 'did the workflow guidance change', 'new model released, check the defaults', 'is our model guidance stale', or when an as-of date in defaults.yaml looks old.
- ▌ Synthesize · melodic-softwareSynthesis and analysis of user research data for the app being built: codes notes, survey answers and support tickets into themes, insights, user needs, personas or jobs to be done, evidence-labeled. Use when: 'summarize these interview notes', 'what themes are in these support tickets', 'turn this research into personas', 'write proto-personas', 'what jobs do our users hire this for'.
- ▌ Control Claude Code Plugins · melodic-software bundleControl skill /app-control:drive reads to run this repository's plugin skills in Claude Code, one plugin at a time, through the control-claude-code driver.
- ▌ Sync 2 · melodic-software bundleMove every canonical checkout in a fleet onto the remote default branch and fast-forward it. Divergent dirty work is parked in a linked worktree. Bare invocation prints a dry-run plan. Mutation requires --apply and one confirmation. Use when: 'sync the fleet', 'update all repos to main', 'fast-forward canonical checkouts', 'park my dirty branches and pull'.
- ▌ Glossary · melodic-software bundleReverse term lookup for interface design and front-end behavior: the name for an effect, detail or behavior described without its name, and the line between near-synonyms. Use when someone asks what a thing is called ('the bouncy thing when a popover opens', 'the gap between two particular letters'), which of two close terms they mean ('clip or mask'), or a vague feel request ('make it snappier') needs named terms.
- ▌ Map Context · melodic-software bundleC4 system context of one software system from tracked configuration: operator-stated actors and external systems named by connection strings, base URLs, and broker namespaces, credentials redacted. Use when 'context diagram', 'what does this system talk to', 'who uses this system'. Skip for many repositories (map-landscape) or module depth (improve).
- ▌ Stateless 2 · 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 /harness-memory:audit) and not transcripts/history.
- ▌ Known Issues 2 · melodic-software bundleLookup and tracking of known Claude product issues: GitHub bug search, service health and model quality checks, and a persistent registry of tracked issues. Use when: 'is this broken', 'any workarounds', 'troubleshoot Claude Code', 'feature behaves unexpectedly', 'scan repo for issues', 'file a bug'. Actions: status (default), search FEATURE, check-all, scan, list, quality, create.
- ▌ Evaluate · melodic-softwareEvaluation of a design, user flow, prototype or live app for usability problems: evaluation plans, expert review, fair-choice checks, UX-debt baselines and experience measures. Use when: 'is our cancel flow OK', 'run a heuristic evaluation', 'test this prototype before we build', 'what should we measure for this feature', 'where do we start redesigning this old system'. Not for plugins, prompts or model output.
- ▌ Write CSS · melodic-software bundleWrite and review CSS in any stack (stylesheets, utility classes, CSS-in-JS, scoped component styles) with modern techniques, after finding the project's tokens, browser targets, lint rules and conventions, which always win, and asking when no token fits instead of inventing one. Use when: 'write the CSS for', 'style this component', 'fix this layout in the stylesheet', 'add a variant to this stylesheet', 'restyle this page', 'review this CSS'.
- ▌ Morning Brief 2 · melodic-software bundleOperator's read-only morning view of the current GitHub repo in one pass: open counts per queue label, merge-ready PRs, parked decisions with their RECOMMENDED lines, loop-lane telemetry freshness, per CI lane the week's failures by class, limit stops, restarts and turn headroom, and model usage per activity and profile, owner touches per day, and whether anything on GitHub or Azure is charging or could start charging; never mutates issues, PRs, labels, comments, or billing and Azure settings. Use when: 'morning brief', 'ops dashboard', 'what needs attention', 'daily standup view', 'how do we monitor lane failures', 'which models do the lanes use', 'are we being charged'.
- ▌ Analyze Profile · melodic-software bundleFind the cause in a captured CPU profile, heap snapshot or performance trace and report it at file:line, with no fix. It turns a Chrome trace, V8 .cpuprofile or .heapsnapshot into SQLite and narrows it to the hot path or the reference keeping memory alive. Use when: 'read this heap snapshot', 'what does this cpuprofile show', 'analyze this trace', 'what is holding this memory', or a profile, trace or snapshot is in hand with no reproduction. Skip when: the failure reproduces and needs a loop, a fix and a regression test (`/debugging:debug`), or no artifact exists yet and one must be recorded (`/app-control:drive capture`).
- ▌ Go Faster · melodic-software bundleBackground sweep of the whole AI-assisted development process (this session's work, git, hooks, the rest of the setup) for ways to go faster without losing accuracy, returning evidenced findings ranked by measured size and speedups to adopt now; edits no repository file or setting. Use when: 'go faster', 'how can we go faster', 'speed up this session', 'what is slowing us down', 'whole-process speed sweep'. Skip: ranking candidates already in hand is /performance:target.
- ▌ Demo Video · melodic-software bundleProduce a short demo video of a web UI change for a pull request: explore the flow unrecorded, script and replay it with 4K frame capture, plan the edit (zoom on each action, drawn cursor, click ripples, captions, optional narration), render an H.264 MP4, gate it with frame-measured quality control and an independent frame review, then attach it to the PR. Use when: 'demo video', 'record a demo of this change', 'make a PR video', 'produced walkthrough video', 'produced screen recording of a web flow', 'video proof a UI change works', 'video evidence for the PR'.
- ▌ Explain Change · melodic-software bundlePull request explainer: a markdown digest of one PR (why, before and after, a checked risk map, annotated hunks, an optional quiz) with an optional interactive view. Never posts to the PR or gates merge. Use when asked to 'explain this PR' or 'walk me through this pull request', for a 'digest' of a PR, or where to focus in a diff.
- ▌ Setup 67 · melodic-softwareVerify or configure the user-experience plugin for this repository: check probes node and the claude CLI, resolves the convention home and reports every team-file key with its source and any error with its line; apply writes the team file user-experience.yaml per key in block style, idempotently.
- ▌ Shape 2 · melodic-softwareShape the user experience of the app being built, idea to legacy: states its stage and the project's own evidence, then chains research, synthesis, flows and evaluation. Use when: 'start UX work on this app', 'who are the users and what do they need', 'users drop off at checkout, why'. One job alone: /user-experience:plan-user-research, synthesize, structure or evaluate.
- ▌ Design 3 · melodic-software bundleDesign and build anything a person or agent interacts with: web and app components, forms, screens and pages, CLI output, TUIs, prompt themes, PowerShell formatting, banners, Claude Code mods. Detects the project's own design system and the design tools installed, routes each concern to the best present source with the project first, and fills gaps with its own guidance. Use when asked to build a component or page in any stack, to choose between building a component and adopting a library, or to decide how something should look, down to one corner radius or shadow, even with every number given: 'build the checkout page in React', 'build or buy a date picker', 'design this CLI output', 'how should this TUI look', 'style this error message', 'when should my CLI use color', 'design a mod band', 'make this UI match our design system', 'which design tool should I use'. The CSS alone: /user-interface:write-css. Throwaway layout variants: /prototype:explore-directions.
- ▌ Present · melodic-software bundleTurn material into a slide deck through the claude.ai Slides Artifact type: write the markdown outline as the record, then fill a deck made from the type the account offers, behind a publish gate that keeps private or credential-shaped content local. Use when: 'make slides', 'make a deck', 'turn this into a presentation', 'slides for this talk', 'present this', 'deck from these notes'. Not for one chart or diagram (/visualization:visualize) or a pull-request explainer (/review:explain-change).
- ▌ Tidy Diff · melodic-software bundleTidies one change's own lines, named in a file-and-line list, before that change is committed: a simplify pass, proven comment deletions and a generated-code residue pass on code, the docs-hygiene writing rules and an ai-slop fix on markdown. Needs no branch or base ref, so it runs on a detached head and in an unattended lane. Use when: 'tidy my change before the commit', 'tidy these lines', 'tidy-diff', or a lane names it as its tidy entry. A rotated lane hunt is /code-tidying:tidy; a branch or window sweep is /code-tidying:batch-simplify.
- ▌ Tidy Work · melodic-software bundleInventory and tidy the gitignored `.work` memory tiers (the repo's memory root and `~/.work`): report what is stale and what is in flight, normalize misplaced handoffs and retros, and remove stale known items behind one confirmation. Opt-in only; nothing runs unless invoked. Use when: 'tidy .work', 'clean up .work', 'what is piling up in .work', 'prune old handoffs', 'clear stale save-points', 'normalize my memory folder'. Handing off is /session-flow:handoff; making work durable before shutdown is /session-flow:clean-stop.
- ▌ Map Events · melodic-software bundleAsync message topology from committed C# publish, send, and consumer registrations. Orphan publishers and consumers are findings; one short name in two namespaces is two messages. Use when 'map events', 'who publishes this message', 'message topology', 'orphan consumer', 'publish subscribe'. Skip when the question is an in-process call trace (map-flow) or broker hosts and replicas (a deployment view).
- ▌ Be Ambitious · melodic-softwareRaises one request before work starts: shows the original beside a version with a higher goal, deeper methods and wider range, fenced to a scope the user accepts, and waits. After work, deepens and redoes it with an outside check. Typed by the user who suspects they asked for, or got, less than they want; only the user knows that.
- ▌ Produce 2 · melodic-software bundleProduce a short explainer video with ManimCE, narrated when the speech plugin is installed: plan the beats, write the narration and one scene script, time each scene change to the narration's word timings, render at low quality, mux the audio with ffmpeg, add captions, and check the file before calling it done (ffprobe streams and duration, overlapping text and elements cut off by the frame edge, then a fresh-context subagent judging the frames against the script). Without the speech plugin it renders a silent video. Use when: 'make an explainer video', 'narrated explainer', 'animate this concept', 'Manim video of', 'render a math animation', 'turn this explanation into a video', 'silent explainer clip'. Not for hand-drawn film from style packs (use /animation:produce).
- ▌ Unhobble 2 · melodic-software bundleBare-baseline experiment: strip a repo's standing instructions, log stumbles against the bare model, then restore only those with repeated same-cause evidence. Measures the model where 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', 'deletion watch', 'watch this rule before deleting it'. Human-gated, resumable.
- ▌ Audit Posture · melodic-software bundleAudit the MCP servers configured in Claude Code for supply-chain posture, meaning whether each one is safe to run. Use when: 'is it safe to run my MCP servers', 'mcp supply chain', 'floating MCP versions', 'npx @latest MCP', 'MCP server inventory', 'mcp posture', 'unpinned MCP server', 'which MCP servers run on my host'. Reads user, local, project, managed, and passed-in config statically through a bundled inventory script and returns a dated, diffable inventory (scope, transport, launcher, package, pin state, publisher, sandboxed) with P1-P5 findings: floating versions, local stdio where a remote endpoint exists, publisher provenance, OCI image available but unused. Never runs, installs, or connects to a server and never prints env or header values. Optional arguments add config files, such as a plugin's .mcp.json. Not for: tool definition design quality (/mcp-tools:audit), or config correctness, enablement, and permissions (/harness-config:audit).
- ▌ Repo Sweep · melodic-software bundleRun a playbook of hygiene skills through one repository per sweep: one branch, one draft PR whose body holds the step checklist, one commit per step, /clear between steps, resumable from any session or machine. Actions: plan (recommend run, rerun, or not-applicable per catalog entry, open the selection page, open the draft PR), next (run the first unticked step), review (file skill defects found in the last step). Use when: 'sweep this repo', 'run the hygiene playbook', 'repo sweep', 'next sweep step', 'continue the sweep', 'review the last sweep step'.
- ▌ Audit 21 · melodic-software bundleReview interface code in any stack, read-only, one concern lane at a time: the working diff (default), the whole tree, or every lane before a launch, with severity and evidence for each finding. The motion lane also finds where animation would help or must not go, which animations to remove, and why one drops frames. --fix applies one finding at a time after a yes. Use when: 'review the UI in my changes', 'review the animations', 'audit our motion', 'where should we animate', 'too much animation', 'this app feels slow, what motion can go', 'why is this animation janky', 'audit the interface before we ship'.
- ▌ Setup 66 · melodic-softwareShow where each user-interface setting comes from across the four config layers, or change one key in one layer: check reports values with provenance and layer problems, apply writes one key.
- ▌ Learn Style · melodic-software bundleStyle pack from a rotoscoped clip: measure its traces and drawings into knob values and statistic bands, prove the bands against adversarial controls, and check new scenes against the pack. Use when: 'learn this style', 'make a style pack', 'extract the style from this clip', 'does my film match the style', 'check this scene against the woodcut pack', 'which statistics separate styles'. Needs a rotoscope work dir; not for copying a clip one to one.
- ▌ Map Data · melodic-software bundleEntity-relationship diagram from committed schema declarations, with no database connection: Prisma models win over a stated subset of Entity Framework fluent mappings, which win over SQL migrations read from a stated subset of statements, and a disagreement is reported. Use when 'map data', 'ERD', 'entity relationship', 'schema diagram', 'cardinality from mappings', or 'which tables relate'. Skip when the question is deployment topology, runtime state, or data volume.
- ▌ Map Flow · melodic-software bundleSequence diagram of one C# entry point, each hop citing a tracked call site: an interface, service-locator, or reflection hop stays unresolved, and Publish or Send is a hand-off to map-events. Use when 'map flow', 'sequence diagram', 'trace this request', 'walk me through what happens', or 'dynamic diagram from this endpoint'. Skip when the question is who publishes which message (/architecture:map-events) or which repositories exist (/architecture:map-landscape).
- ▌ Changelog 2 · melodic-software bundleClaude Code changelog ingestion into the current repo: fetch (read-only display), diff (impact analysis over a release range, no edits), status (read marker, default range, replay cap), and apply (one PR per owner plugin, larger decisions handed off as work items, explicit user intent only). Use when: 'new cc version', 'what changed in claude code', a new CC release is mentioned, or the user pastes changelog text.
- ▌ Inventory 2 · melodic-software bundleList of every Claude Code surface this machine can invoke: built-in commands, subagents, tools, bundled skills and workflows, and installed plugin components. Use when: 'what slash commands do I have', 'what agents are available', 'is /foo a real command', 'what changed after the update', 'what does marketplace X give me'. On-disk audit: /harness-ops:audit-install-state.
- ▌ Read Docs · melodic-software bundleWhen the bundled claude-code-docs skill resolves in this session, prefer it for a quick answer about a Claude Code feature; this skill for an answer that must rest on a named page's own text. Read an upstream docs page through the shared docs lookup and cache: whole page when small, otherwise the section map, stored notes and the sections you pick, with the page's silences marked and inference kept apart. Use when: 'read the docs page for X', 'what does the official page say about Y', 'check the hooks docs', 'look this up in the vendor docs', a docs page WebFetch truncated or summarized, or a skill points here for an upstream page. Verification reads raw bytes only. A multi-source question is /discovery:research.
- ▌ Plugins 2 · melodic-software bundleBring a machine's plugin fleet current on demand: marketplace refresh, update the plugins that actually load (including in-repo project/local-scope installs), install new catalog plugins per policy, detect scope divergence, and surface (never silently fix) drift, with a terse actionable report; refuses to downgrade by default. Actions: sync (default, mutating), converge (explicit scope consolidation); the read-only dry run is /harness-ops:plugins-audit. Use when: 'sync plugins', 'update my plugins', 'converge plugin scopes'.
- ▌ Improve 2 · melodic-softwareImprove one thing in any target, from a method or a doc to a whole feature, measured against the repo's written standards and, when a focus asks for it, current upstream guidance. Ships the smallest complete improvement as one small PR. With no arguments it reads the conversation for a target and focus and confirms both with the user before acting. Use when: 'improve this', 'improve X', 'make this faster', 'fix one thing', 'make this match our standards', 'bring this up to current .NET', 'find something small and fix it', or a scheduled improve-one-thing run. Skip: a ranked list of options ('what should we improve') is /improvement:find; a structure-only lane sweep is code-tidying:tidy; an observed failure is debugging:debug.
- ▌ Protect · melodic-software bundleChecked-in CI ceiling on the counter of a performance win /performance:verify reported MET: a regression fails the build and a lower count proposes a lower ceiling by PR. Proposes files; a human approves and merges. Use when: 'protect this win', 'ratchet this counter', 'stop this regressing', 'add a performance guardrail to CI'. Not for a duration-only or NOT MET result.
- ▌ Recall · melodic-software bundleReport what past sessions tried on a topic from this repo's transcripts, reverted commits, closed unmerged PRs and open items: tried, kept, reverted. Use when: 'what did we try for X', 'have we attempted this before'. Current state: /session-flow:orient.
- ▌ Illustrate · melodic-software bundleVisual explainer for a concept or codebase topic, one idea per diagram, grounded in the real artifact and written as a markdown record plus an interactive page (markdown only on request). Presets: newcomer (default) and zero-knowledge (ELI5). Options: an STE register, and a video view too when explainer-video is installed. Use when the user says 'ELI5', 'explain like I'm five', 'illustrate this', 'picture explainer', 'show me a diagram of this', 'explain this visually' or 'explainer video'. A prose drop to plainer words is education:explain; restructuring a dense message is adhd:clarify (if installed).
- ▌ Audit 19 · melodic-software bundleWhen the bundled update-config skill resolves in this session, prefer it to make a requested settings change; this skill to audit what is configured. Audit settings.json, settings.local.json, .mcp.json, hooks, plugins, permissions and env vars for correctness, security, and drift against current official docs. Use when: 'audit settings', 'check config', 'check for config drift', after a Claude Code update; pass --fix to apply auto-correctable findings with confirmation.
- ▌ Setup 65 · melodic-software bundleVerify harness-config's readiness for this repository: the external CLI prerequisites its audit scripts need, jq (the JSON-parsing audit scripts) and curl (the plugin-drift check), and the tracked suppression record in docs/conventions/harness-config.yaml, so the audit skills run instead of failing. Use when: 'set up harness-config', 'configure harness-config', 'is harness-config working', 'set up audit-pass suppressions', or an audit skill reported a missing prerequisite. Actions: check (read-only verification, default) | apply (resolve what check found) | wsl-profile (print an opt-in WSL hardening settings block, writes nothing). Re-runnable and safe.
- ▌ Audit 20 · melodic-software bundleAudit the Claude Code instruction/memory layer covering CLAUDE.md, a root AGENTS.md, CLAUDE.local.md, .claude/rules/, and auto-memory against a codified checklist derived from official Claude Code documentation. Use when: 'audit CLAUDE.md', 'audit AGENTS.md', 'memory health', 'audit rules', 'is my CLAUDE.md too long', 'prune instructions', after CLAUDE.md/rules changes or a Claude Code upgrade; actions: audit (default), fix, update, report.
- ▌ Setup 63 · melodic-software bundleCheck the multi-agent role map (model and effort per role and the layer behind each value) or write confirmed keys into the user, team or local multi-agent.yaml layer.
- ▌ Climb · melodic-software bundleKeep-or-revert loop on a frozen harness: one hypothesis and one commit per attempt, both arms re-measured every time, kept by a rule written before the first attempt, logged outside the tree, in its own worktree and branch. Use when: 'keep trying changes until this counter drops', 'hill-climb this benchmark', 'iterate on this until the target is met', 'run an optimization loop'. After /performance:snapshot baseline, before /performance:verify. Skip when: the score comes from an eval set for an LLM app (`/claude-api hillclimb`); one before-and-after comparison (`/performance:snapshot`).
- ▌ Animate · melodic-software bundlePixel-art animation cycles (run, jump, hurt, death) in 1, 4 or 8 directions, as sprite sheets for RPG Maker MZ, Godot or PICO-8. Use when asked to 'animate this sprite', 'walk cycle', 'sprite sheet', 'idle animation', 'attack animation', 'RPG Maker character sheet', '4-direction walking character', or 'make this sprite move'. A still: /pixel-art:sprite; a scene: /pixel-art:scene; not hand-drawn animation or video.
- ▌ Tileset · melodic-software bundlePixel-art tilesets as the target engine's sheet: terrain, autotiles (RPG Maker MZ A1-A5 and B-E, blob-47, 16-tile corner), seamless tiles, and parallax layers. Use when asked for a 'tileset', 'autotile', 'terrain tiles', 'blob tileset', 'parallax background', 'RPG Maker tileset', or 'seamless tile'. One sprite or icon: /pixel-art:sprite; a window skin or icon set: /pixel-art:ui; an HTML cutscene: /pixel-art:scene.