Product & Planning

limengzhe27-boop Bundle

完整项目规范（PRD）生成器——把一个产品想法转化成可直接喂给 Claude Code / Cursor 的 10 模块完整规范文档。自动检测并继承 BRD.md / MRD.md 的交接区数据，避免重复提问。当用户提到"帮我写个PRD"、"我想做一个XX"、"帮我梳理需求"、"我要vibe code一个产品"、"帮我写项目规范"、"coding spec"时立即触发。也适用于"帮我把这个想法变成可执行的文档"、"我想vibe code一个产品出来"、"帮我理一下做什么"等表达。即使用户只说"我想做个XX"或"帮我想想这个怎么做"，只要最终目的是产出一份可供 AI 编程 Agent 执行的 PRD，都应触发此 skill。与 ai-agent-prd-writer 的区分：ai-agent-prd-writer 是工作场景的正式 PRD（给开发团队看），本 skill 是给 AI 编程 Agent 看的项目规范（用户直接拿去 vibe coding）。

liquid4all Bundle

Skill for developing MCP servers for the LocalCowork project. Use this whenever building a new MCP server, adding tools to an existing server, debugging MCP communication issues, or implementing any tool from the PRD tool registry. MANDATORY TRIGGERS: "build the filesystem server", "add a tool to the document server", "implement the OCR MCP server", "MCP server", "tool implementation", or any mention of a specific server name (filesystem, document, ocr, knowledge, meeting, security, calendar, email, task, data, audit, clipboard, system). Also trigger when user says "implement UC-" since use cases require MCP tools.

liquid4all Skill

Skill for writing and running integration tests that chain multiple MCP tools together, simulating real user workflows from the PRD. Use when implementing or testing any of the 10 use cases (UC-1 through UC-10), verifying that MCP servers compose correctly, or building end-to-end test scenarios. MANDATORY TRIGGERS: "integration test", "use case test", "UC-1" through "UC-10", "tool chain", "end-to-end test", "workflow test", "compose tools", or any mention of testing a specific use case by name (receipt reconciliation, contract copilot, download triage, meeting pipeline, etc.).

opentabs-dev Bundle

Plan work and generate ralph task files for autonomous execution. Use when the user wants to plan tasks, create a prd, run ralph, or fix a batch of issues. Triggers on: ralph, create tasks, plan this, run ralph, prd.

openvinotoolkit Skill

Adds or modifies a camera backend under physicalai.capture. Use when implementing a new Camera type, extending create_camera in src/physicalai/capture/factory.py, discovery helpers, optional pip extras for vendor SDKs, SharedCamera transport, or tests under tests/unit/capture with fake devices.

othmanadi Bundle

Trigger the self-improvement loop after completing a task. Analyzes friction, extracts learnings, and updates AGENTS.md with new rules and preferences. Use after any task that involved struggle, correction, or discovery of a new pattern. Triggers on keywords like learn, self-improve, update rules, what did I learn, retrospective, post-mortem.

phelps-sg Skill

Kanban board of active work — backlog items, own PRs, review requests, related PRs, assigned issues, and sketches

pravidhi-net Bundle

Run a structured, adversarial multi-agent bug review pipeline on a codebase. Use this skill whenever the user wants to find bugs, audit code quality, review a codebase for issues, or run any kind of bug-finding or code analysis workflow. Also trigger when the user asks to 'review my code for bugs', 'find all issues in this repo', 'audit this codebase', or any similar request. The pipeline uses three sequential phases: a Bug Finder that maximizes issue discovery, a Bug Adversary that challenges false positives, and an Arbiter that issues final verdicts — producing a clean, high-confidence bug report.

primeintellect-ai Skill

Run interactive brainstorming across verifiers tasksets, evaluations, GEPA, and RL training. Use when the user wants ideation, literature scanning, concept teaching, roadmap planning, or research program design grounded in local CLI sources, verifiers, and RL trainer code.

pruthivim Bundle

Adversarial review of PRDs, specs, and requirements docs — plays a skeptical Lead PM / Principal Engineer / Senior QA reviewer who hunts for missing acceptance criteria, undefined success metrics, unhandled edge cases, scope creep, missing technical/operational constraints, unstated assumptions, ownership gaps, weak problem framing, and missing telemetry. Use this any time the user shares, pastes, or uploads a PRD, spec, or requirements doc and asks for feedback, a review, or a critique — and also proactively whenever someone is drafting a PRD in-chat and asks something like "does this look good?", "is this ready?", or "what am I missing?". Trigger even if they don't say "PRD" explicitly — "requirements doc", "spec", "one-pager for eng", and "feature doc" all count. Produces both an annotated copy of the document AND a standalone gap report.

pruthivim Bundle

Scores and prioritizes a backlog of features, ideas, or initiatives using the RICE framework (Reach, Impact, Confidence, Effort), producing a ranked table with a calculated score and a justification for every input. Use this whenever the user wants to prioritize a backlog, compare feature ideas, decide what to build next, rank initiatives, or mentions RICE, Reach/Impact/Confidence/Effort, or "prioritization score," even if they only paste a rough list of ideas and don't ask for RICE by name. Also trigger when a user asks "what should we build first" or shares a roadmap/backlog and wants it ranked objectively.

pruthivim Bundle

Evaluates whether a problem statement is genuinely well-defined before solutioning begins, catching cases where a PRD or spec would be built on a premise that's actually a disguised solution, an unvalidated assumption, or a vague target user. Proactively use this before writing a PRD, spec, or feature doc for any problem statement, user pain point, feature request, or "we should build X" idea that hasn't already been through this check — even if the user doesn't ask for it by name. Do NOT use for casual code requests, bug fixes, or small technical asks with no PRD/spec involved; those should proceed unblocked. Can also be invoked explicitly, e.g. "run a problem clarity check," "sanity check this problem statement," "is this problem well-defined," or "stress-test this premise."

quietdaemon Bundle

Instantly capture an idea, task, or note into a backlog file and commit it — capture-first, zero friction. Use when the user says /idea ..., add idea: ..., capture this, log this, or tosses out a concept they don't want to lose.

77652189 Bundle

Independently searches scholarly APIs, deduplicates and classifies papers, maintains a candidate library, and produces evidence-backed Chinese daily briefs. Use when the user asks for a paper daily brief, literature monitoring, scheduled paper discovery, manual academic search, or candidate-library review without relying on PaperSort.

gnurio Bundle

Guide user through defining initial PMF narrative with 6 dimensions, confidence scores, and validation priorities. This skill should be used when starting a new product-market fit discovery process or formalizing an initial product insight into a structured hypothesis.

joelhooks Skill

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

joelhooks Skill

Implement a piece of work based on a PRD or set of issues.

shiquda Bundle

Introduces roadmap-skill and routes roadmap work to the right workflow. Use when the user needs brief context about roadmap-skill, or wants help deciding between backlog task flow, planning views, and the web workspace.

shiquda Bundle

Captures, enriches, tags, and prioritizes roadmap tasks. Use when the user wants to note work quickly, add missing task details, organize a backlog, or reprioritize an existing list of tasks.

shiquda Bundle

Creates and organizes focused planning views from a subset of roadmap tasks. Use when the user wants to build a task graph, analyze dependencies, identify ready or blocked work, or group near-term and future work into a focused planning workspace.

shiquda Bundle

Opens and uses the local roadmap web workspace for visual review. Use when the user wants to inspect projects, tasks, kanban state, or planning views in the browser.

shrek-abaper Bundle

Use for SAP Transport Request pre-release gate review (QAS/PRD). Triggers on any TR number in input (pattern: uppercase letters + K + 6 digits, e.g., DEVK900123, ECDK943668). Asks user: code-quality-only or functional+code review. Performs 10-dimension risk review of ABAP/CDS/DDIC source, object list, dependencies, spec, and release evidence; detects evidence gaps; generates Release Readiness Report with GO / CONDITIONAL_GO / NO_GO / NEED_MORE_EVIDENCE. Also triggers for: "can this TR go to production", "release gate check", "audit TR before import", "transport risk assessment", "generate release readiness report". Do NOT use for: executing transports, SAP login, single ABAP file without TR context (use abap-code-review), or no transport artifacts.

skinnerlee1225 Skill

輕量版 PRD 撰寫工具 — 適合個人專案、單一功能、無合規/金流/風控需求、單團隊開發， 快速產出可直接交付工程的「施工藍圖」等級文件。 當使用者說「幫我寫 PRD」、「產品需求文件」、「寫 spec」、「功能規格」、「write a PRD」、 「product requirements」、「feature spec」、「產品設計文件」、「需求規格書」時， 一定要使用這個 skill。即使使用者只是說「幫我整理這個功能的規格」、「把這個想法寫成文件」、 「我要交一份產品文件給工程團隊」、「寫個規格讓工程師可以直接開工」，也應優先觸發此 skill。 也適用於使用者要求「補 AC」、「加驗收標準」、「補 Out of Scope」、「補畫面狀態」等 針對既有 PRD 的強化需求。這個 skill 確保每份 PRD 都包含驗收標準、複雜度標注、 畫面狀態規格、Out of Scope 邊界，讓工程師能直接開發、QA 能直接寫測試。 ⚠️ 版本選擇（重要）：本 skill 是「輕量版」，另有「企業版（enterprise-prd-writer）」 涵蓋權限矩陣、NFR、依賴、合規、Rollout/Rollback、UAT 等。當使用者說「幫我寫 PRD」 但未指明版本時，先問要用「輕量版（本 skill）」還是「企業版」再開始。判斷提示： 個人專案 / 單一功能 / 無合規需求 → 輕量版；多團隊 / 金流 / 風控 / 合規 / 需上線維運全鏈路 → 企業版。 使用者已明確指定版本時直接照做，不必再問。

skinnerlee1225 Skill

測試案例產生器 — 把 PRD 的驗收標準（Acceptance Criteria）與規則，轉成 QA 可直接執行的 測試案例：正常路徑、邊界值、異常路徑、併發/冪等、權限與安全。 當使用者說「幫我寫測試案例」、「這份 PRD 的 test case」、「QA 測試計畫」、「幫我補測試」、 「這功能怎麼測」、「寫測試」、「test cases」、「test plan」、「QA checklist」時， 一定要使用這個 skill。即使使用者只是丟一份 PRD、一段 AC、一個功能描述說 「幫我想想怎麼驗收」、「工程做完了要測什麼」，也應觸發此 skill。 這個 skill 輸入 PRD / AC，輸出結構化測試案例；不寫 PRD、不寫程式碼，只負責「怎麼驗證」。 接力關係：enterprise-prd-writer / prd-writer 產出 AC → 本 skill 把 AC 展開成測試案例 → QA 據以執行。PRD 的每條 Given/When/Then 是輸入，測試案例是輸出。

skinnerlee1225 Skill

企業 PRD Writer — 受監管 / 金流 / 風控 / 跨職能團隊等級的產品需求文件撰寫與強化工具， 用於產出可直接進入 Refinement、Engineering Design、Development、QA 與 UAT 的 「施工藍圖」等級文件。相對於輕量版 prd-writer，此版本額外涵蓋權限矩陣、NFR、 依賴管理、合規、Analytics/Observability、Rollout/Migration/Rollback 與 UAT/Release Readiness。 預設以 interactive-html-report 規格輸出互動式 HTML（含常駐目錄側欄、捲動高亮）。 ⚠️ 版本選擇（重要）： 當使用者說「幫我寫 PRD」但未指明版本時，先問使用者要用「輕量版（prd-writer）」 還是「企業版（本 skill）」再開始。判斷提示：個人專案 / 單一功能 / 無合規需求 → 輕量版； 多團隊 / 金流 / 風控 / 合規 / 需上線維運全鏈路 → 企業版。使用者已明確指定版本時直接照做，不必再問。 當使用者提出以下需求時，應優先使用此 skill： - 幫我寫 PRD - 產品需求文件 - 寫 spec / feature spec - 功能規格 / 需求規格書 - write a PRD / product requirements - 產品設計文件 - 幫我整理這個功能的規格 - 把這個想法寫成文件 - 我要交一份產品文件給工程團隊 - 寫個規格讓工程師可以直接開工 - 補 AC / 驗收標準 - 補 Out of Scope - 補畫面狀態 - 補 Edge Cases - 補權限矩陣 - 補 NFR - 補 Rollout / Rollback - 強化既有 PRD 此 skill 的目標不是產出冗長文件，而是建立可執行、可測試、可追蹤、 可討論且邊界明確的產品規格，降低因需求模糊造成的返工與認知落差。 核心強制項目包含： - Acceptance Criteria - Edge Case Analysis - Screen / System States - In Scope / Out of Scope - Assumptions / Open Questions / Decisions - Dependencies - Roles & Permissions -

skinnerlee1225 Skill

需求補洞助手（探路模式）— 專用於「白紙一張、還沒有 PRD」的場合：站在 PM、UIUX、 Backend、Frontend、QA 五個角色，掃描需求的缺漏、容易誤解的敘述、沒考慮到的 Edge Case， 以及開發前一定要確認的問題，把還沒想到的東西攤開。 ✅ 適用場合（符合任一才觸發）： - 全新產品 / 全新架構，還沒有任何 PRD 可審 - 面試 take-home、產品設計題，且風險/邊界識別本身就是交付物 - 使用者不熟的領域，需要靠五角色補自己的盲點 - 沒有可問的需求方，使用者要自己扮演甲方 當使用者說「幫我找需求缺漏」、「這個需求有什麼沒想到的」、「補洞」、「盤點 Edge Case」、 「這是白紙設計，幫我掃一輪」、「find gaps」、「what am I missing」時，觸發此 skill。 ❌ 不適用（改用別的 skill）： - 已經有一份 PRD，要檢查完整度 / AC 能不能測 / 缺哪章 → 用 enterprise-prd-writer 的 Gap Analysis 與 Definition of Ready，不要用本 skill - 要把需求寫成正式文件 → 用 prd-writer（輕量版）或 enterprise-prd-writer 這個 skill 只負責「發散——把問題找出來」，不做格式檢查、不寫 PRD、不替使用者做決定。

solpbc Skill

Guides agents through reading and writing ATProto records, DID resolution, and PDS discovery. Activates when working with AT Protocol, Bluesky, or decentralized identity.

strapi Bundle

Run a structured, business-value-first product-planning interview that turns a fuzzy idea into a build-ready spec — BEFORE any code is written. Use this the moment someone is still figuring out WHAT to build and says things like "I have an idea for an app, help me think it through", "help me plan/scope/design my product", "where do I start?", "let's spec this out before I write code", or "turn this into a PRD". Covers any new app, site, SaaS, MVP, marketplace, or feature. Trigger on the planning intent alone — the user need NOT mention Strapi, a CMS, or any tech; a Strapi v5 + Strapi Cloud backend (overridable, with your choice of frontend and auth) is assumed by default. It nails value, users, and requirements before any tech decision, then produces six markdown files ending in a build spec you can hand to any coding agent (Claude Code, Cursor, etc.). Do NOT use once a spec or project exists and the user wants to scaffold, configure, migrate, add pages, wire auth, or debug — those are build tasks, not idea-s

xiaowen-0725 Skill

openerp 发现层：用 objects 搜索任意业务对象 FormId、用 schema 发现其字段、再用 query 查数据。当要查询的对象没有现成领域命令、或不确定 FormId/字段名时使用。

zarubinvibe Bundle

Мнемозина — агентный конвейер знаний. Превращает все, что попало в $HOME/Desktop/Mnemazine Inbox/ (скриншоты, PDF, ссылки, видео, аудио, заметки), в проверенные классифицированные Obsidian-ноты с блоком «как это поможет мне», обновляет оглавления разделов и мастер-индекс, возвращает справку к действию. Use whenever the user runs /kb, /mnemazina, /kb find, /kb fix, /kb backlog, /kb migrate, or says anything about processing collected material — «обработай входящие», «разбери инбокс», «разложи по базе знаний», «process my inbox», «ingest this». Also use when the user pastes a link, text, or screenshot asking to save/remember it («сохрани это в базу», «добавь в vault», «запомни на будущее»), and when the user asks what their knowledge base holds on a topic («/kb find <query>», «найди в базе знаний», «что у меня есть про…»). Trigger even if the user never names Мнемозина or /kb — any request to file material INTO the personal vault ($MNEMAZINE_VAULT) or retrieve knowledge FROM it belongs here.

zhitongblog Bundle

Scan competing markdown editors' user feedback (GitHub issues/discussions/releases + closed-source forums) and synthesize themes cross-referenced against SoloMD's own gaps and roadmap. Surfaces unmet demand SoloMD could win on, and features competitors ship that SoloMD lacks. Supports a "subscribe" mode that reports only what's new since the last scan. Use when asked to "check competitor feedback", "what are users complaining about in Obsidian/Logseq/etc.", "competitor watch", or "subscribe to competitors' GitHub".

vellum-ai Skill

Generate a board-meeting-style weekly briefing summarizing recent decisions, stuck items, OKR drift, and recommended focus for the next period. Activates when the user asks for a weekly review, a status update, "what happened this week," board prep, or when a scheduled weekly trigger fires.

wcgomes Skill

Use only in coordinator sessions to orchestrate planning or execution of work, including execute, continue, or resume-plan requests. Covers role definition, specialist discovery, dispatch, review, learning, and synthesis. Never use in Session type: DELEGATED executor sessions; those agents perform their handed scope directly without orchestration.

pratiyush Skill

Maintain an llmwiki-style open-source project across the full framework pipeline. Use when the user says "maintain the project", "check my tasks", "update progress", "run phase gate", "do a monthly verify", "lint my wiki", "check stale entries", or invokes any form of ongoing project-keeping chore. Reads _progress.md, tasks.md, docs/roadmap.md, and .github issues to figure out what's next and what's drifted.

prime-radiant-inc Bundle

Use when executing the next pending iteration from an iterative-development roadmap — picks the iteration, decomposes into code and evidence tasks, runs sentinel corpus baseline, dispatches implementing-tasks, runs impacted + sentinel scenarios, and updates artifacts.

prime-radiant-inc Bundle

Use when turning extracted requirements into a roadmap — selects the walking skeleton iteration with its first journey scenario, orders remaining work into follow-on iterations, and applies story splitting when ACs have different dependency profiles.