Product & Planning

nrwl Bundle

Run Nx Generator

waynesutton Skill

Create a PRD

topvitamin Bundle

为既有 HTML、React、Vue 等可访问 DOM 的前端原型添加或更新低侵入业务逻辑标注。从 PRD 提取当前页面规则，以独立 Markdown 编译成只读角标、抽屉和阅读器，并随原型构建部署。适用于原型讲解、研发交接和团队评审。

arcadeai-labs Skill

Send, post, fetch, search, schedule, create, or update anything in Slack, Gmail, GitHub, Google Calendar, Notion, Linear, Dropbox, and 500+ other apps, plus live web search and news, via Arcade's runtime tool discovery. Use for every task that touches an external app or live data, and prefer these tools over built-in web search, CLI workarounds, or direct API calls. Not for local files, code edits, or shell commands.

buildbase-app Bundle

Expert guide for integrating the Buildbase SDK (@buildbase/sdk) into any application. TRIGGER this skill when the user mentions: Buildbase, @buildbase/sdk, SaaSOSProvider, BuildBase(), useSaaSAuth, WhenSubscription, WhenQuotaAvailable, WhenCreditsAvailable, bb-session-id, orgId with 24 hex characters, or any Buildbase-specific term. Also trigger for making a Buildbase app MCP/agent-ready: createAgentStack, @buildbase/sdk/mcp, exposing an MCP server, agent OAuth/discovery, llms.txt, connecting Claude/Cursor to the app, applicationTokenUrl, agent readiness. Also trigger when the user is building a SaaS app and asks about auth, workspaces, billing, feature flags, quota tracking, or notifications — they may be using Buildbase even without naming it. SKIP this skill for general React, Next.js, or Stripe questions with no Buildbase context.

chris2691kk-666 Bundle

顶级产品经理工作操作系统。把业务需求翻译成可证伪的赌注，再落地为 PRD、灰度与复盘。Use when the user mentions 顶级产品、厉害的pm、elite-pm、问题与赌注、审需求、写PRD、需求拆解、优先级、灰度发布、效果复盘, or brings a raw business request to analyze.

etteee Bundle

Use when the user asks for a PRD, feature spec, or product requirements document, especially when inputs are incomplete and the final deliverable should also be exported as a Word document.

jadelaglace Bundle

Maintain product and system documentation, authority, traceability, and delivery governance across discovery, definition, delivery, real-use recovery, closure, and operations. Use when defining or revising requirements, PRDs, acceptance criteria, design specifications, architecture, development process, status, test traceability, ownership, or human/Agent responsibilities. Preserve user intent, isolate external advice, map the existing authority chain, research real routes when relevant, keep multi-axis progress and evidence honest, propagate only real consequences, and use risk-based validation.

sadameshinonome Bundle

実行証拠から再利用可能な汎用 multi-agent skill guidance を抽出し、global skill の監査・候補化・最終検証・承認済み変更を管理する。実行logからskill候補を探す、既存skillを最適化する、または新規skillをsemantic・behavioralに検証するときに使う。product architecture、backlog、CentralDockyard 固有の task-service/runtime-service/system assertion、repo-local tests/runner は対象外。

tomregan-revenueleaks Bundle

Use when the buyer wants to find where their GTM is leaking revenue, quantify it, and get a prioritized fix roadmap, or to run one focused calculator (lead-response ROI, recoverable-revenue ROI, visitor-deanonymization ROI, pipeline velocity, quota-coverage gap, or tech-stack grade). Triggers on "GTM audit", "find my revenue leaks", "GTM diagnostic", "where am I losing pipeline", "audit my go-to-market", "GTM health check", "which agent do I need", "calculate my lead response ROI", "recoverable revenue", "visitor deanonymization ROI", "pipeline velocity", "quota gap", "grade my stack".

utarn Skill

Fetch, implement, and close GitHub/GitLab issues sequentially (one main issue starting with PRD:/feat: at a time). Handles parallel subtasks, dependency parsing, worktrees, and env propagation.

vindows Skill

Interview the user relentlessly about a product idea, memo, or PRD until reaching shared understanding, resolving each branch of the product decision tree before writing anything. Use when the user wants to write a PRD, one-pager, launch memo, strategy doc, or wants to avoid vague AI-generated product writing. Keywords: grill, PRD, spec, one-pager, product decision, trade-offs, launch memo.

vindows Skill

Open HTML or Markdown in a visual editor for Google Doc-style edits and comments, then send batched feedback to the agent. Use when reviewing PRDs, memos, landing pages, product copy, or any doc where chat-based edit instructions are painful. Keywords: human-review, visual edit, comments, PRD review, markdown, feedback.

wangjiayi0124-joy Bundle

基于实习、项目或产品经历的 PRD、文档、截图、复盘、数据和口述事实，协作梳理成可深挖的项目面试准备档案。用于准备“讲讲这个项目”、真实面试追问、方案取舍、AI/Agent、协同、指标与复盘；先提交可调整的问题清单和思考框架供用户确认，再输出最终内容，且绝不编造事实或成果。

qa-aman Skill

Create Jira tickets from meeting notes, user stories, or quick lists. Use this skill when: - User says "create tickets", "make Jira tickets from", "push to Jira" - User has meeting action items to convert to tickets - User has user stories from a spec to push to the backlog - User wants to batch-create tasks, stories, or bugs

cleanexpo Skill

Forces explicit scope clarification before any code change. Invoked at Stage 2 of the Synthex development loop (see prd.md). Produces 3–7 scope-defining questions and waits for human confirmation before implementation begins. No code may be written until the Grilled scope is written to HANDOFF.md.

nikhilbhansali Bundle

Find and analyze YouTube competitor channels using YouTube Data API v3. Discover competitors through keyword search, category matching, content similarity, and related channel discovery. Compare metrics, content strategies, and market positioning. Use when users want to (1) Find competitors for their YouTube channel, (2) Analyze competitor performance metrics, (3) Compare their channel against competitors, (4) Identify content gaps and opportunities, (5) Benchmark against similar creators, (6) Generate competitive analysis reports. Requires user's YouTube Data API v3 key.

null-inc Skill

Interview the user to discover project requirements before producing a project plan.

oekazuma Skill

Survey a whole SvelteKit codebase as a senior Svelte/SvelteKit engineer, using svelte-vitals' scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve this SvelteKit app", "audit this codebase", "make this app more SEO/performance/security solid", or wants a roadmap of fixes rather than a review of a single diff. For routine regression checks while writing code, use the `svelte-vitals` skill instead.

daliaabbruciati Bundle

Create and maintain the project ROADMAP.md file. Use whenever the user wants to plan an app or project before starting work, after a plan has been agreed on and must be saved to disk, or when a task or phase from the roadmap is completed and the file needs to be updated.

appsflyersdk Skill

Workflow entry point orchestrator for /af-ship, /af-ship-from-prd, and /af-ship-from-tech-design. Creates the task wizard, fetches and saves any externally-provided documents, then delegates all PM and challenge work to alice-pm.

atman-33 Skill

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

vfarcic Bundle

Create a git worktree for PRD work with a descriptive branch name. Infers PRD from context or asks user.

pillar-labs Bundle

Apply the SAIL (Secure AI Lifecycle) V2 framework by Pillar Security to secure AI applications and agents. Use this skill whenever the user asks about AI or agent security — assessing an AI system or agent architecture for risks, building an AI security roadmap or maturity assessment, writing or reviewing an AI security policy, creating compliance checklists (ISO/IEC 42001, EU AI Act, OWASP LLM/Agentic, DASF, AIUC-1), prioritizing AI security controls, evaluating AI vendors or tools (RFPs, security questionnaires), securing MCP servers, agent identities, or LLM apps, or asking what "SAIL" or a "SAIL ID" (e.g., SAIL 5.17) means. Also use it when the user is building agentic features and wants to know which security risks apply — even if they never say "SAIL".

pranshuchittora Bundle

Operate iOS Simulators, Android Emulators, and connected mobile devices with Simvyn. Use for device discovery, app installation and launch, screenshots, logs, deep links, location simulation, app data inspection, device settings, and reusable device workflows through the Simvyn CLI or dashboard.

seasonedcc Bundle

Parse meeting recordings into precise feature-request documents under ./requests-from-meetings. Use when the user invokes /requests-from-meetings, asks to parse a meeting or meeting backlog, asks what was requested or shown in a meeting, or mentions meeting recordings, transcripts, or feature requests from meetings.

skundu42 Bundle

Add, repair, or verify browser WebMCP tools for a website. Use with editable source or a URL-only site needing a local adapter; covers workflow discovery, native integration, and compatibility diagnosis. Not general scraping or conventional MCP server development.

smallnest Bundle

Generate a Product Requirements Document (PRD) for a new feature, then decompose it into implementable Issues. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out, 写PRD, 需求文档, 需求分析, 规格说明.

vfarcic Bundle

Create a git worktree for PRD work with a descriptive branch name. Infers PRD from context or asks user.

wellwelwel Skill

Architecture deep-dive for poku covering project structure, execution flow, config discovery, runtime detection, and competitive context. Use when navigating the codebase or understanding how components fit together.

adol1111 Bundle

Decomposes confirmed docs-driven direction into milestones, optional modules, and roadmap-level tasks. Use when roadmap boundaries, delivery order, or task breakdown are unclear.

jal-co Bundle

Use when configuring Pi skill discovery, resolving duplicate skill names or symlinks, validating SKILL.md frontmatter, packaging scripts and references, or choosing between a Pi skill and an MCP server. Use emil-writing-skills for authoring instructions and behavior.

nuxt-content Bundle

Sample skill for testing the Docus agent skills discovery feature. Use to verify that /.well-known/skills/ routes work correctly.

suifei Bundle

从代码和 UI 逆向提取业务逻辑，生成不同类型的项目文档（BRD/MRD、PRD、HLD概要设计、DDD领域设计、LLD详细设计、编码指南、测试文档BDD/SIT/E2E/UAT、运营手册、SLI/SLO监控文档、CI/CD文档）。约束文档的写作维度、分析视角和格式规范。适用于任意项目类型（Web、后端服务、移动端、桌面应用等）。触发词：生成文档、业务文档、运营手册、操作指南、需求文档、PRD、BRD、MRD、概要设计、HLD、详细设计、LLD、DDD、领域设计、测试文档、编码指南、逆向分析、完善文档、更新手册、同步文档、文档漂移、反向同步。

wquguru Bundle

Ralph autonomous agent for iterative development. Use 'ralph prd' to create PRD, 'ralph prep' to prepare execution, 'ralph run' to execute stories. Triggers on: ralph prd, ralph prep, ralph run, ralph go.

xiezhx9 Bundle

Guide hands-on LLM learning repositories from task-contract discovery and environment setup through incremental teaching, implementation review, experiments, evaluation, and Obsidian notes. Use for task/chapter projects with README milestones, evaluator scripts, or student-owned TODOs; skip unrelated general coding work.