Product & Planning

opendcai Skill

Use this skill when LoopAI needs dataset discovery, acquisition, web-page collection, DataMixer lakehouse operations, data processing, indexing, recipe planning, or production training-data export. In long-running Codex SDK loops, when Analyzer produces an analysis report, failure taxonomy, or user request that implies new training data is needed, Codex must activate this Obtainer skill, parse the data need into an intent, and delegate the whole workflow to the Obtainer Orchestrator agent (`dm obtainer-orchestrator start`), then poll its structured status. The orchestrator owns lake bootstrap and the dispatch/gating of the managed sub-agents (dataset-acquisition-agent, dataflow agent-run, sft-export-agent); the outer Codex context must not run lake init, acquisition bridges, download manifest, ingest, or export itself for a normal obtain task. The rest of this skill is the domain policy the orchestrator worker follows.

aeonbridge Bundle

Integrate with Ticketmaster Discovery API to search events, attractions, venues, and classifications. Use when building event discovery apps, ticket platforms, venue finders, or entertainment search features. Access 230K+ events across US, Canada, Mexico, Australia, UK, and Europe. Includes authentication, rate limiting, and comprehensive API examples.

andyzengmath Bundle

Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Convert a PRD into machine-readable quantum.json with dependency DAG, granular 2-5 minute tasks, and execution metadata. Use after creating a spec with /quantum-loop:spec. Triggers on: create plan, convert to json, plan tasks, generate quantum json, ql-plan.

andyzengmath Skill

Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Generate a structured Product Requirements Document (PRD) with user stories, acceptance criteria, and functional requirements. Use when you have an approved design and need formal requirements, or when starting from scratch. Triggers on: create spec, write prd, spec out, requirements for, ql-spec.

andyzengmath Skill

Intent-drift audit for quantum-loop. Compares the user's original intent (immutable snapshot) against downstream artifacts (design.md → PRD → quantum.json ACs → implementation) to detect semantic divergence. Flags drift with file:line evidence. Use before merge or when specs feel "rewritten."

bahayonghang Skill

Run the canonical governance lane for an Obsidian knowledge base. Use this skill whenever the user says "kb review", "kb health", "review gate", "health check", "approve drafts", "reject draft knowledge", "promote to live", "rebuild briefings", "lint live wiki", "clear archive backlog", "audit archived outputs", "检查归档内容", "检查风格约束是否冲突", "检查账号 briefing", "审校草稿", "批准草稿", "知识库体检", or uses Chinese-LLM-Wiki maintenance wording such as `lint`, `孤儿页`, `断链`, `旧结论被覆盖`, `output/reports`, `治理报告`, `先做 lint`, and `原文证据摘录是否充分`. This skill owns both the immediate gate and the longer-horizon maintenance lane through internal `gate` and `maintenance` modes. Do not use it for normal approved-layer retrieval or deterministic derivative rendering.

bahayonghang Bundle

Diagnose and route ambiguous, workflow-level review-gated Obsidian vault requests. Use this skill when the user is talking about an Obsidian vault workflow as a whole, asks which lifecycle step should run next, says things like "what should I run first", "which stage am I in", "LLM Wiki", "Karpathy wiki", "Obsidian IDE", "knowledge compiler", "creator knowledge compiler", "personal knowledge base", "second brain", "archive this answer", "归档这个回答", "存回知识库", "复用归档内容", "清理 archive backlog", "先读 wiki/index.md", "这个知识库下一步该做什么", "现在应该初始化/摄取/编译/审校/检索/发布/渲染/体检哪个步骤", or uses Chinese-LLM-Wiki wording such as `中文优先`, `来源页`, `主题页`, `实体页`, `综合页`, `output/analyses`, `output/reports`, `原文证据摘录`, `先读 wiki/index.md 再判断`, or `先判断该做来源页还是综合页` without making the operation explicit. Prefer the operation-specific skills when the user already clearly means init, ingest, compile, review, query, publish, render, or archive maintenance, and only route through this package entry skill when the workflow step is genuinely ambiguous.

openqa-cn Bundle

Turns a PRD, technical design, API spec, or knowledge base into a reviewable library of structured manual test cases. Every case gets a stable UUID, a business-semantic name, and engineering info (interface name, request parameters, DB / cache / MQ assertions), behind requirement, design, and coverage review gates. Also maintains that library: it diffs the PRD and the code under test against the last baseline and updates only the affected cases. Use this whenever the user wants test cases written, a case library initialized, coverage designed, cases refreshed after a PRD or code change, or an interrupted run resumed from pending entries — including Chinese phrasings such as 生成测试用例, 写用例, 用例设计, 用例库, 根据 PRD 出用例, 补充测试场景, 用例更新, and requests that never say "test case", like asking which scenarios a requirement needs covered. Not for unit-test or automation code, not for building the data that fills case placeholders (use testdata-generation), not for reviewing requirement quality or writing a gap register (use requ

openqa-cn Bundle

Constructs test data against real backends and writes it back into test cases as executable preconditions. Use whenever the user wants test data built, case materials or preconditions prepared, a data-build skill or tool reused, an API discovered, a construction script written, or a proven method recorded — including Chinese phrasings such as 构造测试数据, 准备测试数据, 造数据, 用例数据, 用例物料, 用例数据准备, 用例前置数据, 测试数据回写, 测试物料清单, 数据需求分析. Also use it for concrete requests that never say "test data", like "create this account from the OpenAPI", "build a script from these change APIs", "publish that script as a tool", or "scaffold a new domain from this OpenAPI directory". Not for authoring test cases from a PRD (that is testcase-generation) or finding defects in code (that is defect-detection). Bundled slots and sub-skills here are internal; reach them through this skill.

saltandsilicon Skill

Plan UX and UI before code. Runs a required multi-round discovery interview, uses visual probes when available, and produces a user-confirmed design brief for implementation.

subinium Bundle

Issue-driven development orchestrator. Turns improvement intent into a well-specified, bilingual issue set; clusters issues into milestones that map 1:1 to semver versions; enforces branch, commit, and PR conventions (GitHub Flow — `<type>/<issue-N>-<slug>`, Conventional Commits, mandatory PR template, rebase-first merge); generates changelog entries and release notes deterministically from closed issues; leaves a durable audit trail for the next AI session. Direct-call only — not part of the /vibesubin parallel sweep. Two tracks — **GitHub track** (default) on GitHub with authenticated `gh` CLI; **PRD track** on any other host, using local markdown files under `docs/release-cycle/vX.Y.Z/` as the durable audit trail. Operator picks at Step 1.5. Every external mutation follows preview → confirm → mutate; created resources carry idempotency markers so re-runs noop instead of duplicating.

jinplu Bundle

Use when the user asks for an implementation plan, task breakdown, checklist, roadmap, or handoff and the outcome and direction are already selected; do not use to choose the direction or execute changes.

nacholafuente Skill

Generate a tight pre-discovery-call prep brief from an intro email, referral, or company name. Outputs a 3-section scan doc (who they are, ranked questions, proof to drop) you can read in the two minutes before a sales or consulting call. Use when the user says "/disco-prep", pastes an intro email, or asks to "prep for the disco call", "what should I ask", or "disco agenda". Output goes to the chat, not a file. One-shot, no warehouse, no cron.

pranjay-kumar Bundle

Trigger when the user wants to collect, structure, evaluate, crawl, extract, refresh, or build reusable data acquisition pipelines from websites, APIs, portals, files, or rendered apps. Use for dataset design, source classification, feasibility, endpoint discovery, authorized/owned-session scraping plans, Patchright warm-session cookie generation, Playwright fallback, source probing, pagination analysis, scraper/pipeline architecture, sample validation, refresh design, and output contracts. Do not trigger for ordinary browsing, exploitative access, credential theft, CAPTCHA solving, auth bypass, rate-limit bypass, or non-data tasks.

pranjay-kumar Skill

Use when the user needs to decide what data to collect before scraping or API work: DatasetNeed, DatasetSpec, entity grain, required vs nice-to-have fields, freshness, history, coverage targets, join keys, exclusions, and uselessness criteria. Use for vague business goals, all data requests, and scope control before source discovery.

pranjay-kumar Bundle

Use for Patchright/Playwright-based public or authorized browser probing: warm-session cookie/storage generation, browser network capture, JSON/API route discovery from page loads, rendered DOM fallback, screenshots, tiny DOM samples, and user-owned storage-state workflows. Do not use for CAPTCHA solving, credential extraction, auth bypass, or rate-limit bypass.

pranjay-kumar Skill

Use for discovering and reverse-engineering data sources: official APIs, XHR/fetch, GraphQL, persisted queries, Algolia, Shopify, Salesforce Commerce Cloud, sitemaps, feeds, embedded JSON, hydration state, page-data routes, pagination limits, headers, params, and endpoint templates.

susomejias Skill

Create a PRD through user interview, codebase exploration, and module design, then save it as a local file. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.

anombyte93 Bundle

Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes /atlas, or wants task-driven development.

anombyte93 Skill

The Atlas engine — turn any goal into a validated PRD and an executable, verified task graph. Brand-name entrypoint; a thin alias for the `go` orchestrator. Use when the user types /prd:atlas, says "I want to build", or asks for a PRD / task-driven build.

anombyte93 Skill

Phase 0 of the prd-taskmaster pipeline. Resolves the active backend, initializes the project, configures the provider stack when the TaskMaster backend is active (DETECT-FIRST — never overwrite a working user config), and verifies the AI pipeline. Autonomous: zero user questions unless a hard block is hit. Declares the Setup phase complete so DISCOVER can follow.

anombyte93 Skill

Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a structured AskUserQuestion multi-option picker for user agency, and dispatches the chosen mode. Mode D (Atlas Fleet) is selectable only when detect_capabilities returns tier=premium (licensed atlas-launcher detected); otherwise it is a locked Atlas Pro teaser. Plan Mode is NOT used (spec section 13.5): AskUserQuestion is the sole user-agency mechanism. Declares HANDOFF complete so EXECUTE can follow.

anombyte93 Skill

Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

anombyte93 Skill

Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholders_found, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis, and expands every task into verifiable subtasks. Autonomous-safe. Declares GENERATE complete so HANDOFF can follow.

anombyte93 Skill

Expand all TaskMaster tasks with deep research before coding begins. Reads tasks.json, launches parallel research agents per task in waves using the research-expander agent. Writes findings back to tasks.json. Part of the prd-taskmaster toolkit. Use after PRD is parsed and before implementation. Invoke with /expand-tasks.

anombyte93 Skill

Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default provider, preferred execution mode, and template choice. For deeper tweaks beyond the curated questions, users can hand-edit files in .atlas-ai/customizations/. Use when the user says "customise workflow", "customize workflow", "adjust my PRD settings", "tune the skill", or wants to change how prd-taskmaster behaves.

coder Bundle

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

architect-4-citadell Skill

Run or re-run Elektra onboarding. Executes First Session Protocol (project discovery + user onboarding + memory init). Use on first install or to reset onboarding.

architect-4-citadell Skill

SO2 Project Management -- GitHub PM routine. Check issues, PR status, plan progress, triage, backlog grooming. Runs at P0/P8 of Godspeed, or standalone.

astropham1808 Bundle

Run a repository story through two isolated Codex sessions, with one implementer working in a Git worktree and one independent reviewer inspecting the branch, followed by a bounded fix pass, deterministic verification, and a human PR and merge gate. Use when the user explicitly asks for a dual-agent Codex workflow, an implementer-to-reviewer handoff, a story-ID delivery flow, an independent Codex review of an implementation branch, or repeatable scripts for story delivery. Do not trigger for ordinary one-off coding, generic backlog questions, or reviews that do not need a two-agent workflow.

aws-samples Skill

Use when the user wants to install, configure, or onboard the SDLC Agent Fleet (workitems, researcher, docwriter, and others) into a new project or AWS account. Drives the conversation from tool discovery through agent selection, provisioning, and verification. Delegates each step to the narrower sdlc-agents-* skills.

aws-samples Skill

Use when the user needs to pick which SDLC agents to install based on the tools they already use. Filters the full fleet roster against the user's integrations, presents a short opinionated recommendation, and records the selection to .sdlc-agents/selection.yaml. Invoked by sdlc-agents after tool discovery.

ayushgoel Skill

Use for direct Bitbucket pull-request and CI operations through atlas prflow, including PR discovery and review context, comments, approvals, merges, descriptions, retargeting, checks, pipeline status and logs, custom pipelines, and Renovate workflows. Use live command help for current flags.

ayushgoel Bundle

Use when implementing features, fixing bugs, refactoring, or making any requested code change. Guides scoped implementation, explicit side-effect boundaries, focused tests, risk-based verification, company-context discovery through TWG, and Bitbucket PR or CI work through PRFlow.

kangise Bundle

Research products and analyze markets. Use for product opportunity discovery, competitive landscape analysis, supplier evaluation, or market entry assessment.

gn00678465 Bundle

Scaffold (bootstrap) OR amend a ralph autonomous coding loop in a target git repo — writes prd.json + .ralph/prompt.md + .ralph/ralph.<sh|ts|js|py> + RUNBOOK + .gitignore. Pure scaffolder; does NOT execute the loop. Use for first-time setup OR to append more user stories to an existing scaffolded prd.json. Bootstrap trigger phrases: "init ralph", "set up ralph", "scaffold ralph", "bootstrap ralph", "建立 ralph", "初始化 ralph", "ralph 起手". Amend trigger phrases (every phrase MUST carry ralph/prd/meta-ralph context): "append stories to ralph", "add user stories to ralph prd", "extend the ralph prd", "extend ralph backlog", "grow the ralph prd", "在現有 ralph prd 補 stories", "追加 ralph stories", "在 ralph 加 user story", "ralph prd 新增 story". NOT for running an existing ralph loop (use ralph-loop:ralph-loop instead), NOT for explaining what ralph is (informational queries don't need this skill), and NOT for generic PRD editing, backlog grooming, or writing user stories outside an existing meta-ralph scaffold.