Product & Planning
Product & planning agent skills structure the thinking side of building: specs, PRDs, user stories, roadmaps, and prioritization frameworks. Install one and your AI agent produces planning documents with the same rigor and format every time.
-
fabio-barboza Bundle Do Create PrdCreates Product Requirements Documents (PRDs) from feature requests following a structured workflow of clarification, planning, and drafting. Outputs a standardized PRD to the project prds directory. Use when the user asks to create a PRD, define requirements, or document a new feature. Do not use for technical specifications, task breakdowns, or implementation planning.
-
fabio-barboza Bundle Do Execute QAValidates feature implementation against PRD, Tech Spec, and Tasks through E2E testing via available MCP tools, accessibility verification (WCAG 2.2), and visual analysis. Documents all bugs found with screenshot evidence and generates a comprehensive QA report. Use when the user asks to run QA, validate a feature, or test implementation completeness. Do not use for code review, bug fixing, or task implementation.
-
fabio-barboza Bundle Do Create TasksConverts PRD and Tech Spec into a detailed, sequenced list of implementation tasks. Each task is a functional, incremental deliverable with its own test suite. Outputs tasks.md and individual task files. Use when the user asks to create tasks, break down work, or plan implementation from an existing PRD and Tech Spec. Do not use for PRD creation, tech spec creation, or actual code implementation.
-
fabio-barboza Bundle Do Execute TaskImplements feature tasks by loading required skills, reading PRD/TechSpec context, analyzing dependencies, executing the implementation with tests, and performing an automatic code review. Marks tasks as complete in tasks.md. Use when the user asks to implement a task, execute a task, or start working on a specific task number. Do not use for creating tasks, running QA, or bug fixing.
-
fabio-barboza Bundle Do Create TechspecCreates Technical Specifications from existing PRDs, translating product requirements into architectural decisions and implementation guidance. Performs deep project analysis, uses Context7 MCP for technical research and Web Search for business rules. Use when the user asks to create a tech spec, define architecture, or plan implementation for a feature with an existing PRD. Do not use for PRD creation, task breakdowns, or direct code implementation.
-
flingjie Bundle Idea Discovery把个人证据(Commit/PR/测试)、零散思考(用户片段)、真实交流(已验证 ConversationEvidence) 或社区信号(同行共同主题 + 未解问题/分歧)提炼成一个值得继续发展的 Idea(IdeaCandidate)。 四种来源只是输入不同,判断同一件事:这里有没有「读者值得知道」的真实工程决策或问题。 用于「把我最近的提交 / 这个片段 / 这次交流 / 这些社区信号变成一个可写的想法」类请求。
-
flingjie Bundle Peer Discovery从公开讨论(Twitter/X 搜索)中发现值得长期交流的同行与有实践证据的 builder,生成轻量 交流机会(Opportunity)与 PeerProfile 候选。判断一条帖子背后的人是否值得持续交流—— 是否与用户问题/兴趣重叠、有实践深度、有可贡献空间、有延续潜力;新闻 / 融资 / 纯推广 / 最近已表达的内容跳过。用于「帮我看看今天有哪些人」「这个话题里有哪些人值得了解/交流」 类请求。
-
flingjie Bundle Sticky MessageTransform complex ideas, products, technologies, and strategies into messages people understand, remember, and repeat, using the SUCCESs framework from Made to Stick (Chip & Dan Heath). Use when a message isn't landing — it feels abstract, hard to explain, hard to remember, or reads like a feature list ("帮我把这个方案讲清楚", "这个文案怎么优化", "make this clearer", "写个 hook / one-liner / 开场白", "position my product", "turn this into a story"). The goal is to rediscover what the idea should truly say, NOT to polish prose. It communicates an already-formed idea; it does NOT validate demand (→ idea-validation) or discover Jobs (→ job-discovery).
-
fralapo Bundle UX UI ExpertUX/UI research and design knowledge base covering study plans, research roadmaps, the researcher's project cycle, usability-testing/card-sort/diary-study sample sizes, small-sample reporting, experimental design, research ethics (Belmont Report), stakeholder leadership/influence, the UX/UI/CX distinction with user-centred design principles, the ROI of UX, the Double Diamond design process, user flow diagrams, common beginner UI mistakes, visual/interaction design fundamentals (hierarchy, grids, typography, color, states), designing around user intent, and the psychology behind UI/UX (cognitive load, conditioning, reinforcement, hedonic adaptation). Use when planning UX research or design work, choosing methods or sample sizes, writing recommendations, leading/influencing stakeholders, scoping UX vs. UI vs. CX work, building a business case for UX investment, mapping a user flow, reviewing a UI for common mistakes, applying visual design fundamentals, or reasoning about why a design choice affects user behavio
-
fralapo Bundle Marketing MbaMBA-level marketing and startup knowledge base — segmentation, positioning, pricing, the 4Ps, value proposition design (the Four U's, the Three D's, MVS), business model design, product-to-company roadmap, B2B sales pipeline, negotiation, pitching, and founder/leadership frameworks. Use when defining a value proposition, segmenting a market, setting pricing strategy, designing a go-to-market plan, building a pitch deck, structuring a sales process, or reasoning through founder/startup-execution decisions.
-
fralapo Bundle Awesome ReadmeWrite awesome-list-worthy README.md files for GitHub repositories — project READMEs (library, CLI, app, research, template) and GitHub profile READMEs (username/username repo) — with prose that reads as human-written, not AI-generated. Covers section selection, shields.io badge stacks, banner/logo/GIF guidance, TOC patterns, expandable `<details>` blocks, back-to-top anchors, contributor widgets (contrib.rocks, star-history), typing SVGs, GitHub-readme-stats cards, Standard-Readme spec compliance, README-Driven-Development workflow, and a full anti-AI-slop audit pass on every draft (integrates the humanizer skill's Wikipedia "Signs of AI writing" patterns tuned for README prose). Triggers when user asks to generate, write, improve, refactor, humanize, or audit a README; wants badges, TOC, logo placement, demo GIF, feature list, install/usage blocks, contributing section, roadmap, "getting started", or profile README with stats/typing SVG/snake animation. Keywords - readme, README.md, github readme, profile re
-
full-stack-skills Bundle Full Stack DocScaffold, adapt, validate, and maintain example-rich full-stack product documentation: 10 product-level documents, 7 version documents, optional module PRD/Stitch/UI triplets, 5 delivery documents, and a detailed project README template family. Use when users ask to initialize a documentation repository, create product or version plans, write PRDs and architecture/UI documents, preserve and adapt detailed examples, audit document structure, or improve an existing product-docs tree, including Chinese requests such as 初始化文档、产品文档、写规划文档.
-
full-stack-skills Bundle API Doc GeneratorGenerate or update evidence-backed API documentation from OpenAPI specifications, framework routes, controllers, request/response models, validation rules, and tests. Use when the user explicitly asks for API or interface documentation, route inventory, endpoint reference, OpenAPI-derived docs, or synchronization between code and API docs. Supports OpenAPI-first projects and framework-specific discovery for Spring, FastAPI, NestJS, Express, and Gin; do not use for generic product documentation.
-
geeksfino Skill Lw ReflectUse index-first discovery to find synthesis, contradiction, gap, and output-promotion opportunities across wiki/, save a reflection report to outputs/, update reflect state, and create or recommend high-value canonical pages. Usage: /lw-reflect
-
guntherb7 Skill New ProposalGuided proposal generation. Asks discovery questions, references past pricing, generates document in your voice using writer agent.
-
haorantang97 Skill Polish Rule ContentRevise an existing AI skill or rule for clearer discovery, useful instructions, appropriate scope, and reliable execution. Use for a requested content improvement or a demonstrated behavioral problem; a review-only request produces findings without rewriting.
Audited -
harsh719 Bundle Saas GuardrailsThe stack-agnostic engineering contract for building and extending a multi-tenant SaaS. Defines eight invariants every build must satisfy (a feature registry, one request chokepoint, tenancy enforced in one place, feature-oriented folders, one type source of truth, a grep index, a mandatory chokepoint test suite, migrations-only schema change), then binds each invariant to a concrete mechanism through a per-stack binding file (Next+tRPC+Prisma, Python+FastAPI+SQLAlchemy, or a new one from the template). Merges the process gates from the architectural-guardrail doc (discovery, stack selection, architecture approval, one-feature-at-a-time, version policy, deployment automation) with the enforced runtime patterns from the Web Prodigies starter kit, and closes the eight holes both leave open (no tests, missing tenancy indexes, a quota race, swallowed audit failures, fail-open auth rate limiting, no baseline migration, unpluggable logging, a stale grep pointer). Use for: starting a new SaaS in any language, adding
-
tikhomirovv Bundle SalesActs as a B2B sales expert for founders and small teams. Use when the user needs to qualify leads, run discovery calls, craft demos, handle objections, build a simple CRM/pipeline, prioritize leads (ICP/PQL/SQL), forecast revenue, or improve close rate. Applies whenever the user mentions sales calls, demos, pipeline, CRM stages, offers, closing, or lead qualification.
-
tikhomirovv Bundle ProductActs as a product manager for founders and small teams. Use when the user needs to choose a niche/idea, define ICP and problem, validate demand, design an MVP, write a PRD, plan a roadmap, set value-based pricing assumptions, or filter ideas with a lightweight GTM manifesto before building. Applies whenever the user mentions product management, MVP, PRD, roadmap, PMF, niche selection, or product strategy.
-
tikhomirovv Bundle Project WorkflowUniversal project workflows for software repos — brainstorm ideas, maintain docs, research and file backlog issues, implement with PR/MR. Works with GitHub and GitLab. Use when discussing features, exploring the codebase, creating or updating issues, writing documentation, or implementing tracked work.
-
tokugero Skill Write A PrdTransforms a conversation or idea into a Product Requirements Document (PRD) with user stories, then submits it as a Forgejo issue. Invoke with /write-a-prd when ready to formalise a feature or initiative.
-
tokugero Skill Prd To IssuesConverts a PRD (Forgejo issue or local file) into independently executable Forgejo issues organised as vertical slices through integration layers. Invoke with /prd-to-issues <issue-url-or-path>.
-
travsteward Bundle Blog WriterChannel-master writer for long-form blog posts. Owns the SHAPE of a post — beat structure, title/preview/slug commitments, per-post container layout, per-site voice anchor discovery — and delegates VOICE (prose generation) to /authors-voice and PUBLISH mechanics to the openwriter github plugin (`add_blog_site` + `post_to_blog`). Use when: "/blog-writer", "write a blog post", "blog draft", "brainstorm blog topics", "blog beats", "extract beats from this post", "write about this feature", "draft a post", "blog title", "preview text", "OG description", "blog image", "featured image", "OG image", "integrate", "create the files", "wire up the blog post", "publish to blog", "post to blog", "set up blog repo", "register blog site". Requires: OpenWriter MCP server configured + github plugin enabled + `gh auth login` set up locally. Project SHOULD have a `## Blog` section in its CLAUDE.md for writing-rules / image-style overrides (optional after setup).
-
truongduy2611 Skill Appshots CLI UsageCore CLI reference for the App Screenshots desktop app. Commands, flags, JSON output, port discovery, and connection management.
-
twistingmercury Bundle Ralph Loop Docs WriterCreate or update PRD.md and PROMPT.md files for agent-agnostic gralph loops driven by a checklist and a one-cycle execution prompt. Use when defining or maintaining iterative gralph automation.
-
uniswap Skill Argent Native ProfilerNative profiling for CPU hotspots, UI hangs, and memory leaks. Currently iOS-only (xctrace-backed); Android support (Perfetto/simpleperf) is on the roadmap. Use when diagnosing native-level performance issues.
-
hoangvantuan Skill Pk InitKhởi tạo dự án mới hoặc sửa KR target/mục tiêu/constraints/tools (cấu trúc mục tiêu). Tạo cấu trúc .cockpit/ lần đầu. Dùng khi user bắt đầu dự án từ đầu, sửa OKR, thêm/bớt công cụ, thay đổi constraints, hoặc cần thiết lập lại mục tiêu. KHÔNG dùng khi cập nhật KR current tiến độ hàng ngày (dùng pk-track).
-
nowledge-co Bundle Nmem Skill LoadSearch Nowledge Mem for skills matching a query and load or inject them on-demand into the current conversation turn or workspace. Triggered by /nmem-skill-load <query> or proactive task discovery.
-
zhijunio Bundle Codebase AuditRead-only codebase health audit — MECE pillars architecture (A1–A6), code (C0–C3), security (S1), verification (V1–V2), dependencies (D1), operations (O1). Chat-only P0/P1/P2 roadmap; effort snapshot, standard, or deep; variants simplicity, anti-pattern, branch, direction, cicd, and pillar-scoped review. Use for codebase audit, architecture review, security hygiene, CI/CD review, over-engineering and anti-pattern scan; not article writing, topic learning, implementation edits, or plans/.
-
primefoldtools Skill Open Loop HarvesterIdea capture and triage system that processes scattered thoughts, voice memos, and raw notes into structured idea captures ready for pipeline evaluation. Use when: (1) User dumps multiple ideas at once, (2) User has scattered notes or voice memos to process, (3) User says 'I have this thought' or 'here's an idea', (4) User wants to clear mental backlog, (5) User asks to 'harvest open loops' or 'process ideas'. HARVESTER extracts distinct concepts, clarifies them, structures minimally, and classifies readiness for SEF evaluation—preventing idea debt accumulation.
-
ahnchen1983 Skill Skill BuilderGuide any user through deliberately constructing a production-quality SKILL.md from scratch with role-aware questions. Use when the user says "I want to build a Skill", "help me create a Skill for [task]", "I have a workflow I want to automate", "help me write a SKILL.md", or wants to make a task repeatable with AI. Also activates after skill-self-discovery or conversation-to-skill when the user wants to refine further.
Audited -
ahnchen1983 Skill Skill Self DiscoveryInteractive guided discovery that reveals non-technical users already possess every component needed to build an AI Skill. Use when the user says "I want to learn Skills but I'm not technical", "Can AI help with my work?", "help me turn my workflow into a Skill", "I don't know how to write prompts", or expresses doubt about their ability to work with AI. Also use when a non-engineer is exploring Skills for the first time.
Audited -
aimonj0729-ai Bundle Idea To PrdUse when converting a rough product, workflow, agent, skill, or developer tool idea into a lean PRD with scope, user stories, acceptance criteria, and launch plan.
-
aimonj0729-ai Bundle Prd To IssuesUse when converting a PRD, product brief, or feature spec into GitHub-ready issues with labels, acceptance criteria, dependencies, and verification steps.
-
knvpk Bundle BrainstormRun a structured AI brainstorming session using one of 6 proven methods — Big Mind Mapping (broad idea generation), Reverse Brainstorming (invert the problem), Role Storming (multiple personas), SCAMPER (systematic transformation), Six Thinking Hats (balanced analysis), or Starbursting (question-first discovery). Use when the user wants to generate ideas, explore a problem, make a decision, or scope a project.
-
zuozh11 Bundle To Prd将当前对话上下文转化为 PRD。适用于用户要求产出 PRD、需求文档,或说「写个 PRD」「出需求文档」「to-prd」等场景。
Frequently asked questions
What are Product & Planning agent skills?
Product & planning agent skills structure the thinking side of building: specs, PRDs, user stories, roadmaps, and prioritization frameworks. Install one and your AI agent produces planning documents with the same rigor and format every time.
Which Product & Planning skills are most installed?
Popular Product & Planning skills on SkillMD right now include ralph-loop-docs-writer, do-create-prd, do-execute-qa. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Product & Planning skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.