Product & Planning

melodic-software Bundle

Macro-journey router over one spec container: say where the multi-session effort stands, which execution shape is in effect (per-item PRs vs integration branch → single PR) with that mode's discipline, and route the next step to the machinery that owns it. Use when the user says 'ship' about a spec or container, asks where a spec container stands or what is next in it, wants to drive or resume the multi-session effort, or wants to close out the container. Thin by design, it reads the container, its sub-item rollup, and its scoped frontier through the tracker seam, states the active execution shape's discipline, and ROUTES to /work-items:work (next item), /work-items:decompose (re-slice, container close ritual), planning/review close-out machinery, and session-flow, never duplicating their mechanics. Sibling skills: /work-items:decompose (publishes containers + records the shape), /work-items:work (executes one item), /work-items:track (backlog CRUD), /work-items:triage (raw intake).

melodic-software Bundle

Auto-select one development work item from the tracker frontier and execute it end-to-end through the project's development workflow. Use when the user asks to pick, grab, or work the next item, ticket, or issue from the backlog, or asks what to work on next. Selects exactly ONE item by priority tiers (due recurring, guardrails, highest-impact, then not-yet-due recurring), claims it race-safe via the seam (assignee + lease), then runs the full workflow. Sibling skills: /work-items:track (backlog CRUD, add, start, done, list, stats, search, due, recheck, audit), /work-items:triage (raw intake), /work-items:decompose (plan → tickets), /work-items:scan-todos (TODO sweep).

melodic-software Bundle

Evidence-first, cross-dimension improvement finder: scans code/architecture, performance, product-level behavior, config/automation outside the codebase (GitHub labels, Actions), and Claude Code operational setup, then returns a ranked candidate list. Every candidate cites its evidence (telemetry, CI failure rates, churn hotspots, or, weakest, model judgment) and carries an S/M/L size with a value-to-effort rationale; an unmeasured target makes 'instrument this' the top candidate. Interactive by default; caller-declared unattended mode persists the report and files top candidates as work items. Never edits anything itself; execution routes through the discovery/planning/implementation pipeline. Use when: 'what should we improve', 'find improvements', 'improvement sweep', 'improve <X>', 'highest-impact improvement', 'tech debt sweep', 'where is the highest-value work', 'what would move the needle', 'run an improvement scan'. Skip when: single-lens architecture deepening (`architecture:improve`), applying small

melodic-software Bundle

Chart a too-big, still-foggy effort as a shared decision map on the work-item tracker, then work its frontier one decision at a time, routing each resolved decision to the right skill until the map graduates to a Brief / PRD / PLAN. Use when a task is too big to hold at once AND parts are still too fuzzy to phrase as sharp tickets ('this is a huge foggy effort', 'I don't even know the questions yet', 'map this out', 'chart this program', 'plan-the-plan'); skip when the work is already a set of sharp, answerable tickets (use /planning:interview or /work-items) or small enough to just do.

melodic-software Bundle

Track development work items through the bound tracker (work-item-tracker seam), the backlog-CRUD multi-verb skill. Actions: stats, list, add, start, done, due, recheck, search, audit (default: stats dashboard). Use when the user wants to add, claim (start), or close a work item, ticket, or issue; list, search, or see a dashboard of open items; check or recheck what is due on the recurring schedule; or audit stale claims and label hygiene. Not for new bug reports, use /bugs:write first (read-only report), then chain to /work-items:track add via --context if filing is needed. Sibling skills own the other verbs: /work-items:work (auto-select + execute one), /work-items:triage (raw intake), /work-items:decompose (plan → tickets), /work-items:scan-todos (TODO/FIXME sweep).

melodic-software Bundle

Explore the local codebase before making changes. Read code, trace dependencies, scan git history, discover tests, and audit build and tool configuration, persisting an EXPLORE.md index plus sidecars. Dispatches a fresh-context subagent by default so the file reads stay out of the main conversation, with a documented inline escape hatch. Use when: 'explore the codebase', 'what exists for X' investigation, 'how does this work', 'where is X implemented', 'trace the dependencies', 'what tests cover this', or as step 1 before any code change. Skip when: the question is why a thing was built the way it was rather than what it is or how it works. Reconstructing the reasoning behind a past decision from review discussion, tickets, and design documents is '/discovery:trace-intent'; this skill's git mode reports what changed and by whom, not the intent behind it.

melodic-software Bundle

Evaluate raw intake, any untriaged item carrying the raw marker, whoever authored it (external bug reports, incoming feature requests, unsolicited PRs, and team-authored self-observation/dogfood issues), through a small state machine: raw → verified → briefed → autonomous-eligible, with side exits to needs-info, human-gated, and close. A PR is an item with attached code and enters the same intake as an issue. Use when: 'triage', 'what needs triage', 'triage this issue', 'triage this PR', 'evaluate this bug report', 'is this bug real', 'should we merge this unsolicited PR', 'attention view', 'what intake needs attention'. No number = attention view (untriaged intake). Sibling skills: /work-items:track (backlog CRUD), /work-items:work (auto-select + execute), /work-items:decompose (plan → tickets), /work-items:scan-todos (TODO sweep).

melodic-software Bundle

Multi-source external research in chained phases, corpus enumeration, broad, targeted + falsification, preferred sources, with per-claim source tiers, recency checks, a coverage ledger, and a binary outcome gate before presenting. Dispatches a fresh-context subagent by default so the research transcript stays out of the main conversation, with a documented inline escape hatch. Use when: 'research this', 'verify a technical claim', 'evaluate libraries or approaches', 'compare X vs Y', 'is this still current', 'find the authoritative source', 'what do the official docs say', or grounding any decision in current authoritative sources instead of training data. This is the right skill for a single topic, including a small one. For a multi-topic or workflow-driven pass that fans one question across several dispatches, use research-deep, which layers tiered execution on this same discipline.

bg-szy Bundle

Search the web through Tavily with bounded depth, domains, dates, and result counts. Use when the user needs current information or source discovery and does not already have a specific URL.

bg-szy Bundle

Legacy compatibility entry for prompts or documentation that explicitly name `using-superpowers`. Route new skill-discovery workflows to `using-skills`; do not activate both entrypoints for the same task.

bg-szy Skill

Hypera infrastructure URLs and endpoints reference. Use when user asks about URLs, domains, ingress endpoints, cluster API servers, application URLs, Helm repositories, Git repositories, or needs to check connectivity to services. Provides quick lookup of all external URLs across all environments (hub, dev, prd) and clusters (cafehyna, loyalty, painelclientes, sonora).

bromso Skill

Identify legal needs per business unit, product, and stakeholder group

gaelic-ghost Bundle

Install, launch, validate, and diagnose existing ACP agents across Zed, Xcode, and other clients. Use for registry discovery, custom launch commands, auth, capabilities, sessions, and logs.

gaelic-ghost Bundle

Guide Apple camera discovery, device and format configuration, focus, exposure, white balance, zoom, torch, stabilization, rotation, photo capture, RAW, Live Photos, depth and disparity, calibration, synchronized outputs, portrait and semantic mattes, computational capture, pressure, interruptions, and diagnostics with AVFoundation. Use when sensor, camera-control, photo, depth, or device-capability behavior is primary.

gaelic-ghost Bundle

Plan and safely automate officially supported Apple Developer provisioning and CloudKit workflows through the App Store Connect REST API, Xcode-aware local discovery, cktool, and CKTool JS. Use when inspecting or changing bundle IDs, capabilities, certificates, devices, provisioning profiles, CloudKit schemas, or sandbox test data while keeping portal-only configuration, credentials, dry runs, and confirmation gates explicit.

clowlove Bundle

深耕中国企业绩效管理体系的实战专家，精通 OKR/KPI 双轨制、360 度反馈、绩效校准会、PIP 改进计划等全流程绩效管理，帮助企业建立科学公正的绩效评估与人才发展机制。

clowlove Bundle

面向中国企业的会议管理与效率提升专家，精通飞书、钉钉、腾讯会议等协作平台，擅长会议纪要撰写、行动项追踪、议程设计、OKR 周会组织及跨时区会议协调，帮助团队将会议从"时间黑洞"变为"决策引擎"。

melodic-software Bundle

Surface 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.

melodic-software Bundle

Map 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.

melodic-software Bundle

Break 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

melodic-software Bundle

Run 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).

melodic-software Bundle

Sweep 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).

melodic-software Bundle

Reconstruct 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').

melodic-software Bundle

Turn 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.

melodic-software Bundle

Dispatch 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.

melodic-software Bundle

Attend 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).

melodic-software Bundle

Re-anchor the discipline that inherited content is evidence of what is, never self-justifying authority, then audit the work in flight for decisions coasting on precedent and re-derive them from first principles. Use when: 'reason don't recite', 'why is it this way', 'challenge that convention', 'you're deferring to precedent', "that's just how it's done", 'question the inherited design', 'stop reciting the docs', 'is this actually right', or at conversation start on legacy or inherited code. Note the shared phrasing: this skill challenges whether a convention should STILL hold and re-derives it from first principles; when the ask is instead to RECOVER the original reasoning from the historical record, review discussion, tickets, design documents, that is '/discovery:trace-intent' if the discovery plugin is installed, and otherwise read that record directly before challenging what it says.

melodic-software Bundle

Actively maintain a consuming project's ubiquitous-language glossary as domain understanding changes: resolve ambiguous or overloaded terms, choose canonical language, record rejected synonyms, sharpen what-it-IS definitions, and route terms to an already-known bounded context. Use when: 'update the domain glossary', 'define this domain term', 'standardize this vocabulary', 'these names conflict', domain modeling resolves vocabulary, or planning resolves domain language worth preserving. Not for passive glossary lookup, general dictionary definitions, or bounded-context discovery.

golemcloud Skill

Develops shared Scala source generation for the Golem sbt and Mill plugins. Use when changing source discovery, validated codegen IR, generated RPC/tool clients, auto-registration, or plugin generation hooks under sdks/scala.

golemcloud Skill

Adding prompt and description annotations to TypeScript agents and their methods. Use when the user asks to add descriptions, prompts, or documentation metadata to agent classes or methods for AI/LLM discovery.

bg-szy Bundle

Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.

robsonkades Bundle

The network stack under a JVM service: listen backlog and accept queues, Nagle and delayed ACK, socket buffer sizing against bandwidth-delay product, congestion control choice, keepalive and timeout alignment along the path, and diagnosing retransmissions and queue drops. Use when a small request/response protocol shows a stable ~40 ms latency floor, when a client throws BindException or EADDRNOTAVAIL under burst, when SYNs are dropped at peak, when one core saturates while the others idle on a multi-core server, when throughput plateaus far below a high bandwidth-delay link, when somaxconn was raised and nothing changed, when TIME_WAIT sockets accumulate, or when someone proposes switching to BBR or DCTCP. Does not cover host memory, CPU and signals (linux-for-jvm), the data-movement path itself (io-uring-and-zero-copy), or application-level connection reuse (connection-pool-sizing).

robsonkades Bundle

Designing advanced JMH experiments: shared and asymmetric state topologies, groups, parameter matrices, auxiliary counters, fixture arbitration, fork/JVM controls, profilers, hardware counters, annotated assembly, compiler controls, cold-state protocols, and multi-modal variance diagnosis. Uses runtime capability discovery and separates diagnostic profiled runs from decision runs. Use when a benchmark is concurrent, fork-dependent, profiler-sensitive, cold/startup-oriented, or produces unexplained clusters. Basic benchmark validity, statistical gates, assembly interpretation, and load tests have separate owners.

robsonkades Bundle

Separating what is actually established about a feature request from what has been filled in: a ledger in which every fact carries its source, every assumption carries what would falsify it, and every unknown carries the impact of getting it wrong. Use at the start of a feature, when a request is one sentence long and the work is not, when a plan or an estimate is being built on statements nobody has checked, when two people describe the same feature differently, when picking up a feature someone else analysed, or when an answer is about to be written as fact because it is probably true. Does not decide which unknowns to ask about or how (feature-requirement-clarification), does not investigate the repository to close them (feature-context-analysis), and does not restate the requirement without its solution or write acceptance criteria (requirements-and-acceptance).

robsonkades Bundle

Choose or review a local outbound proxy when discovery or routing changes require client releases, a canary or shadow needs routing outside the app, or retries overlap across app, proxy and mesh. Define the listener, policy ownership, deadlines and failure behavior. Covers shard-map consumption and experiment routing, not shard algorithms (sharding-and-partitioning), container lifecycle (sidecar-pattern), or output normalization (adapter-sidecar-pattern).

robsonkades Bundle

How one slow dependency becomes a total outage: the amplification loop and the four points that close it — retry storms, unbounded queues, thread and connection exhaustion, an inner timeout longer than the outer one. Covers why cutting offered work is usually the first stabilization step in a cascade, metastability sustained by backlog, recovery herds and criticality separation. Use when one dependency's latency rise took down services that never call it, when the dependency recovered and the system did not, when adding replicas mid-incident made it worse, or when queue depth grows while goodput falls to zero. Does not cover the breaker (circuit-breakers), shedding policy (rate-limiting-and-load-shedding), bulkheads (concurrency-limiting-and-bulkheads), retry policy (retries-and-backoff), queue arithmetic (littles-law-and-queueing), replica routing (load-balancing-and-routing), or the fault model (failure-models).