Product & Planning

inkeep Skill

Scope a feature end to end and write an implementation spec under specs/ from an accepted proposal — current-system mapping, goals/non-goals, a Decision Log for one-way-door choices, a live Open Questions backlog, and a real migration + test plan. Read when asked to write a spec, scope this feature, turn this proposal into a spec, plan the implementation, or break this into tasks. Do NOT fire on frame a proposal or write the PRD (sibling frame-a-proposal — a PRD frames a change before it is accepted; this skill starts once one is), record a decision or write the ADR (record-a-decision), write a postmortem (write-a-postmortem), or review this design (review-a-design) — those are separate skills. Complements the platform open-knowledge skill; does not replace it.

nirholas Skill

AI agent integration layer for the Pump SDK — agent instruction files, .well-known discovery, LLM context documents, 15+ skill files, MCP server prompts, and terminal management rules for GitHub Copilot, Claude, and Gemini.

gemspecter Bundle

Use before telling a client or stakeholder "this is fixed", before deploying changes to a production site or service, before activating or modifying a live automation/workflow, before claiming an integration works end-to-end, before quoting pricing or API behavior in a comparison, or before running a destructive infrastructure command. Also use when the user says "confidence check", "how confident are you", "validate this", "pressure-test this", "/bs-check", or whenever a confident-sounding claim has not been directly validated by a query, observation, comparison, or quotable source. ALSO covers design-time reasoning audits via subcommands - "bs-check premise" (are we solving the right problem? premise acceptance - Socratic + Steelman), "bs-check approach" (did we commit too fast? - Burden of Proof, Cold Start, Alternatives, Pre-mortem), "bs-check fresh" (all 9 patterns, fresh-context sub-agent). Trigger phrases for those - challenge this, push back, devil's advocate, poke holes, steelman this, are we solving

adytm404 Bundle

Mengubah ide aplikasi singkat menjadi PRD dan spesifikasi teknis siap implementasi.

agenmod Bundle

OKR 协作 Skill：与用户把模糊目标写成可度量的 Objective + Key Results，并在周期内映射、周更与复盘。含 OKRClaw 四级十六域九十六实践原子索引。触发条件：(1) 定季度/迭代目标、写 KR、复盘；(2) 只有任务清单无成功标准；(3) 对话发散需对齐「做到什么算赢」。不替代公司绩效制度。

agent-sh Skill

Use when the user asks about plan drift, reality check, comparing docs to code, project state analysis, roadmap alignment, implementation gaps, or needs guidance on identifying discrepancies between documented plans and actual implementation state.

yahor-punko Skill

Run the MavP validator to check artifact sync between BACKLOG.md and TASK_STATUS.md. Use after any backlog changes or to confirm healthy state before starting new work.

addono Bundle

Merge Dependabot PRs intelligently: auto-detect the target repo, merge all green PRs, fix trivial breaking changes, and report non-trivial blockers in a summary table. Triggers on: "merge dependabot PRs", "clean up dependabot", "handle dependabot backlog".

petyosi Bundle

Create, review, clarify, execute, or verify concise Product Requirements Prompts (PRPs) and staged PRP roadmaps. Use when the user explicitly asks for a PRP or roadmap, when a feature needs a durable implementation contract before coding, or when existing PRP acceptance evidence must be reviewed. Do not use for small changes with an obvious implementation and validation path.

apoorvjain25 Bundle

Exhaustive production-readiness audit of any codebase or product. Runs diverse-angle discovery passes until two consecutive passes find nothing new, adversarially verifies every finding against the real code, and reports one flat severity-tagged list with file:line evidence. No summary, no hedging.

applification Bundle

Use StoryLoop MCP to inspect story maps, select or resume work, keep durable lifecycle state current, and draft owner-reviewed map improvements. Apply when a request names StoryLoop, supplies a StoryLoop story or session ID, or uses StoryLoop MCP tools. Do not activate for generic backlog writing, agile coaching, ticket systems, or repository work without StoryLoop.

ariccb Bundle

Sync Claude Code skills (plugins + personal) to Codex CLI by copying folders. Creates ~/bin/list-skills enumerator for skill discovery. Run after installing new Claude plugins.

artvandelay Bundle

Decide API-vs-self-host LLM economics and fine-tuning ROI from any user context (code, PRDs, traffic logs, billing screenshots). Fetches live GPU prices from Runpod/Lambda/Modal, API prices from models.dev or vendor pages, and quality rank from lmarena.ai, then calls a deterministic local Python script for VRAM, billed-hours, and capex math. Use when the user asks "should I self-host", "API vs self-host", "fine-tune cost", "fine-tuning ROI", "what GPU do I need for <model>", "OpenAI bill too high", or pastes a billing screenshot / PRD comparing closed APIs to open-weight models.

asiridalugoda Bundle

Run an autonomous, self-directed build loop that keeps working across many goals without per-step prompting — design the system that does the work, then let it run (Addy Osmani's "loop engineering"). Use whenever the user wants to "keep going on your own", "run until done", grind through a backlog or goal-list unattended, set up a maker/checker agent workflow, run a self-improving or nightly loop, or build a durable externalized spine (goals + board + handover) so work survives context resets. Also covers Relay — the multi-node mode where two or more Claude instances on different machines run the same loop on the same repo and hand work to each other via GitHub issues. Trigger on phrases like "autonomous loop", "keep working without me", "no human intervention", "loop engineering", "self-improving loop", "run the loop", "ralph loop", "multi-agent coordinator", "agent roster", "autonomous-loop relay", "relay setup", "sync two claudes", or "cross-machine handover" — even if they don't say "skill".

ask-ayomide Bundle

Use this whenever the user mentions wanting to build, make, or create an app, product, feature, or tool -- even casually, even without using words like "PRD," "technical prompt," or "scaffold." Trigger on phrases like "I want to build...", "I've been thinking about an app for...", "I have an idea for...", "what if there was a product/tool that...". Also trigger when the user already has a finished PRD (pasted, uploaded, or referenced) and wants it turned into a project scaffold. Walks the user from a raw idea through a refined AI Technical Prompt, a PRD (both fixed templates), a full project scaffold (AGENTS.md, agent rules, skill files, design tokens), a hallucination audit of everything generated, and a handoff with copy-pasteable prompts to actually start building the MVP. Always start at the Technical Prompt stage for a new idea -- never jump straight to a PRD or scaffold unless the user already supplies a finished PRD.

askuma Bundle

FIRE this skill when the user's intent is to discover, list, visualize, document, or summarize the technologies used in a software project. This includes all of the following triggers: EXPLICIT COMMANDS: /generate-tech-stack; "generate tech stack"; "create tech stack"; "show tech stack"; "build tech stack"; "make tech stack page"; "tech stack report". DISCOVERY / INVENTORY INTENT: user wants to know what libraries, packages, dependencies, frameworks, tools, or services a project uses — phrased as: "what libraries does this use", "what packages are installed", "what dependencies does this project have", "list all tools", "what frameworks are in use", "show me the dependencies", "what's in requirements.txt", "scan my project", "audit the stack", "inventory the project", "what's this project built with", "what tech does this use", "show all packages", "detect the stack". VISUALIZATION / DOCUMENTATION INTENT: user wants an HTML page, visual report, or summary document of the project's technology choices — phrased

aspectrr Bundle

Find + validate new meal-prep recipes for a 2-person weekly rotation. Pulls from RSS feeds, web search, TikTok/reel videos, and a recipe MCP server; scores each on reheat quality, freezer stability, hands-on time, and scale to 10-12 portions; outputs 1-3 picks as Markdown cards (+ optional CookLang .cook). Remembers your tastes across runs. Triggers on "meal prep idea", "what should I cook this week", "find a meal prep recipe", "recipe from this video/tiktok/reel", "/mealprep".

chituai Bundle

帮助用户从零写出高质量的产品需求文档（PRD），或评估/改进已有需求文档。适用于 vibe coding 场景中的非产品经理用户——他们有产品想法但不懂如何结构化。当用户提到"需求文档"、"PRD"、"产品需求"、"功能文档"、"我想做一个产品/功能/App"、"帮我整理需求"、"AI 写的需求文档有没有问题"、"帮我补充需求"、"我想做个工具"等关键词时，必须使用本 skill。即使描述很简短，也要触发本 skill，不要跳过直接输出文档。

chokwinlee Bundle

Build and maintain a repo-local progressive context pack for large, legacy, or weakly documented codebases, especially when plain file discovery may miss relevant paths behind `.gitignore`. Use when an agent needs a repo map, hotspot analysis, module/file briefs, legacy-service onboarding, or better context discipline before non-trivial multi-file work and refactors.

chowjustin Bundle

Turn a vague software idea into a complete, build-ready specification set through a deep structured interview, then hand it to an AI coding agent. Use this whenever someone describes an app, product, system, or feature they want to build but hasn't nailed down the details — including phrasings like "I want to build X", "help me plan an app", "I have an idea for a system", "help me think through the features", "write a PRD/spec/requirements doc", or when they hand over a rough one-paragraph description and expect something buildable back. Also use it to extend an existing spec set with new modules, or to audit a spec that a coding agent keeps misinterpreting. The skill interviews module by module (roles, flows, rules, data, states, contracts, edge cases, UI), pushes back on gaps and scope creep, and emits numbered module specs plus a foundations doc, decision log, and progress tracker written specifically so Claude Code can build from them without guessing.

clement-972 Bundle

Shared product-team memory living in a structured Doc inside the team's documentation tool (ClickUp, Notion, etc.), reached through its connector. Use it to consult team knowledge when a request overlaps it (regulatory, functional specs, technical specs, skills, roadmap, ongoing topics), and when the user writes the keyword "MAJ cerveau" to file a stabilized piece of information. Memoire produit partagee d'equipe, posee sur un Doc structure dans l'outil de documentation de l'equipe et accessible via son connecteur ; ecriture uniquement sur le mot-cle "MAJ cerveau".

codestackr 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. Plans persist natively into Solo (scratchpads + todos, Solo-agent executors) when Solo is available — auto-detected — or to local files with --files. 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.

coleam00 Bundle

Generate a personalized Second Brain PRD from a completed requirements template. Use when the user has filled out my-second-brain-requirements.md and wants to generate their build plan. Triggers on "create my second brain PRD", "generate my PRD", "build my second brain plan", "/create-second-brain-prd", or after completing the requirements template.

bugmakesprogress Bundle

Use when the user asks for restaurant recommendations, food discovery, or dining suggestions for any location in China. This skill uses OSINT (Open Source Intelligence) methodology to find authentic, local restaurants by cross-referencing real human reviews from news, forums, and government websites — bypassing manipulated platform ratings. 当用户请求中国任意地点的餐厅推荐、美食发现或就餐建议时使用。

bukowski777 Bundle

Use when creating, modifying, debugging, hardening, importing/exporting, packaging, or reviewing Microsoft Power Automate cloud flows with optional FlowAgent MCP discovery and diagnostics, Dataverse solution workflow JSON, Power Platform CLI pac workflows, Microsoft 365 CLI checks, TRY/CATCH logging, runAfter paths, connection references, connector schemas, or Power Automate expressions from Codex, Claude Code, VS Code, or a local shell.

callahkate Bundle

Enforces a strict analysis-before-synthesis discipline rooted in human-centered design (HCD) methodology. Trigger this skill whenever the user shares research data of any kind — interview notes, transcripts, survey responses, observation notes, JTBD artifacts, usability findings, discovery outputs, or any qualitative or quantitative research material. Also trigger when the user says phrases like "analyze this," "slow down," "let's be methodical," or "don't jump ahead." If the user shares research data WITHOUT specifying a goal or workflow, always pause and ask whether they want analysis or synthesis mode before proceeding. Never skip to synthesis, conclusions, recommendations, ideas, concepts, action items, or next steps without explicit user permission. This skill has two mandatory gates: (1) confirm all data is collected before beginning analysis, and (2) ask permission before moving into synthesis.

cascade-protocol Bundle

Build with SATI (Solana Agent Trust Infrastructure) - on-chain agent identity, verifiable reputation, and blind feedback on Solana. Use when registering AI agents on-chain via Token-2022 NFTs, giving or searching feedback, querying agent reputation, building registration files (ERC-8004), encrypting attestation content, or integrating SATI into TypeScript/Node.js projects. Covers: CLI onboarding (create-sati-agent), agent registration, feedback (give/search), reputation summaries, agent search/discovery, validation attestations, EVM address linking, content encryption, and metadata uploading. Triggers on SATI, sati-sdk, create-sati-agent, agent registration solana, agent reputation, blind feedback, compressed attestation, Light Protocol attestation, ERC-8004 registration file, agent identity NFT, register agent CLI.

casemark Bundle

Development skill for CaseMark's discovery-desktop application - a legal e-discovery platform for document upload, OCR processing, and semantic search. Built with Next.js 16, React 19, Drizzle ORM, and Case.dev APIs. Use this skill when: (1) Working on or extending the discovery-desktop codebase, (2) Integrating with Case.dev APIs for OCR, semantic search, or vault management, (3) Modifying the database schema or queries, (4) Building e-discovery workflow features, or (5) Deploying/configuring the application.

cathrynlavery Bundle

Close captured agent-improvement work: triage fleet learnings, select a bounded evidence-backed batch, implement and live-verify fixes, and record leader decisions. Use for 'learn loop', 'fix the learnings', 'process the backlog', or when asked what recurring agent/tool friction to improve.

analogdevicesinc Bundle

Use the pyadi-dt adidtc CLI to inspect, generate, validate, and safely deploy Analog Devices Linux device trees. Trigger for Vivado XSA-to-DTS generation, built-in board profiles, Kuiper support discovery, DTS include analysis, local DTB inspection, live-board property reads, SD-card updates, or pyadi-jif clock updates.

ankitjha67 Bundle

Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan hiring, launch, set up operations, prepare for IPO, or write a compliance policy. Also triggers on market research, does this exist, product marketing, positioning, pricing, packaging, sales, RevOps, partnerships, developer relations, user research, growth, PLG, data engineering, data governance, privacy, DPO, DSAR, incident management, OKRs, program management, docs, localization, investor relations, M&A, procurement, RAG, LangGraph, AI agents, LLM features, customer support, backend and distributed systems, enterprise architecture, developer productivity, FinOps and cloud cost, business continuity, physical security, facilities, regulatory affairs, hardware, internal comms, vendor risk, market exp

antbotlab Bundle

Create a construction plan for a multi-step engineering task that requires multiple PRs or a phased approach. Produces a self-contained plan file with dependency graph, review gates, and step-by-step execution instructions for coding agents. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex task, or describes work that clearly needs multiple PRs. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, user asks to modify/update an existing plan, user says "just do it", or user asks for code review/audit.

antoninfatty836 Bundle

Guides users through a stricter 7-step agile PM workflow. Invoke when users have a rough product idea and need interactive HTML prototype, PRD, mermaid flowcharts, and versioned delivery.

digidai Bundle

PM skill for Claude Code, Codex, Cursor, and Windsurf. Diagnoses SaaS metrics, critiques PRDs, plans roadmaps, runs discovery, coaches PM career transitions, pressure-tests AI product decisions, and designs PLG growth strategies. Seven knowledge domains, 12 templates, 40+ frameworks, and an opinionated interaction style that labels assumptions and names tradeoffs.

digitizers Bundle

Production-grade WordPress REST API integration for managing posts, pages, media, WooCommerce products, Elementor content, SEO meta, ACF, and JetEngine fields. Use when you need to retrieve, draft, create, or update WordPress content programmatically on sites where the user has provided explicit credentials. For any operation that writes to a live site, get explicit user approval for the target site, post/product IDs, and final action before executing. Prefer drafts first. Run batch operations in dry-run mode first; use --execute only after review. Remote URL media downloads and local file reads are restricted by safety boundaries. Also includes a no-auth Tier-1 site audit (PageSpeed, SSL, security headers, CMS/PHP fingerprint, SEO basics) for cold pre-sale checks, and authenticated plugin/SEO-stack discovery.

dimayip Bundle

A harness for guiding humans through the full lifecycle of an X.509/TLS certificate renewal, replacement, or migration in complex infrastructures (CDN / LB / K8s / self-hosted gateway / mTLS). The skill turns "generate a renewal script" into a rigorous assistant workflow: (1) split review into L3 / L2 / L1 layers so every reviewer has a bounded time budget; (2) treat the Agent as "safety officer + document engineer + trusted executor", not an autonomous SRE; (3) enforce a six-gate protocol before any write API is executed on behalf of the user, and never execute Delete; (4) classify asset discovery as a graph closure (domain ↔ certificate), with wildcard fan-out, cross-zone authorization boundaries, and shadow certificate provenance; (5) adapt to the upcoming CA/B Forum validity shrinkage timeline (398 → 200 → 100 → 47 days). Use this skill whenever the user's question is about renewing, migrating, auditing, or hardening TLS certificates across real production systems — especially when the risks "expire = out