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.
-
panix22 Bundle Prd WriterGuide product discovery conversations and produce standard PRD documents in Chinese. Use when the user describes a product idea, feature request, improvement request, vibe-coding project, MVP scope, or explicitly asks to write a PRD, product requirements document, 需求文档, 产品需求, or 功能规格. Enforce a staged workflow by diagnosing from user/business/technical perspectives, confirming page structure and navigation, outputting a concise concept PRD for alignment, freezing scope, then generating an implementation-ready PRD with flows, states, fields, copy, and exception handling.
-
paulkinlan Bundle Chrome DevrelPublic-alpha, stage-aware Chrome Developer Relations copilot for validating developer problems, rehearsing user and stakeholder perspectives, running friction and continuous-improvement loops, planning ecosystem adoption, protecting teams during contentious launches, and producing coherent enablement assets.
-
pc-style Bundle Search Cold SkillsUse when the user says "cold <skill-name or query>" (e.g. "cold to-prd", "cold something that writes prds"), "Search your skills", or asks to find/use a cold, hidden, or non-autoloaded skill. Searches ~/.agents/skills-cold and manually loads matching skill instructions on demand.
-
perhapsspy Bundle Purpose First DesignUse when product meaning or implementation-planning direction is materially open before solution structure is settled, including early direction for a new feature, reuse choices, temporary implementations, or another materially consequential product or implementation-planning choice. Choose a bounded provisional direction from user/domain purpose, locked decisions, explicit constraints, authority, current evidence, and observable success. Do not use for settled code structure, implementation execution, source discovery, or document editing.
-
perhapsspy Bundle Semantic Boundary DesignUse when cross-layer feature, migration, integration, port, refactor, review, bug fix, or design planning needs one owner for user/domain meaning across UI, route, client state, command, API, storage, realtime, adapter, or presentation layers. Trigger for identity aliases, lifecycle/status, permissions/capabilities, route/query grammar, command payloads, result/event projection, freshness/fallback/revision semantics across representations, compatibility translation, duplicated meaning rules, or multiple representations of the same user/domain meaning. Do not use for read-only owner discovery, local flow cleanup after owners are clear, pure async responsiveness/freshness work, or scope-control alone.
-
petar-nauka Bundle Search Science LiteratureUse when Codex must search, validate, rank, or synthesize scientific literature using open scholarly APIs and optional credentialed Web of Science Starter API. Trigger for literature reviews, state of the art, related work, newest papers, DOI/PMID/author/source-title checks, citation-aware reading lists, systematic-review starter sets, open-access discovery, "литературен преглед", "научни статии", and Web of Science metadata/times-cited validation. Accepts Bulgarian or English and must not invent papers, DOIs, venues, or metrics.
74 -
penghang1223 Bundle Test Case Generator通用测试用例生成引擎,支持从 PRD/API 定义/技术设计文档自动生成高质量测试用例;内置 46 种测试模式(风险/API/业务/错误),支持 5 种输出格式(XMind/Markdown/Excel/JSON/CSV);当用户需要生成测试用例、编写测试文档、设计测试覆盖方案时使用
-
phy041 Bundle Prd WriterMulti-turn PRD (Product Requirements Document) creation assistant. Asks clarifying questions one at a time to gather requirements, then generates a complete, professional PRD. Use when starting a new feature, product, or project. Triggers on 'write PRD', 'create PRD', 'new feature', 'product requirements', or '/prd'.
-
peterfei Bundle Okr SkillOKR(目标与关键结果)的结构化思维工具。基于6个一手来源的深度调研, 提炼6个核心原理和完整的操作协议。 触发词:「OKR」「目标管理」「关键结果」「目标对齐」「Objective」「Key Result」「季度目标」。
-
piercelamb Bundle Deep PlanCreates detailed, sectionized, TDD-oriented implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
-
pmyangkun Bundle Check PrdReview B端 PRDs, requirement docs, SaaS or enterprise product specs, and system design documents with a 14-dimension quality framework. Use this whenever the user asks to check, review, critique, improve, or find gaps in a PRD, 需求文档, 产品方案, B端系统设计, SaaS spec, or similar design document, even if they only say "帮我看看这个 PRD/方案/需求".
-
pmyangkun Bundle Create Prd根据用户提供的业务上下文,生成结构化的 B端 PRD 文档(含初始内容)。当用户要求创建、撰写、生成 PRD、需求文档、产品方案、系统设计文档时自动触发,即使用户只说"帮我写个 PRD/方案/需求文档"。
-
pokefang Bundle MarketvalidationAudit a product idea, prototype, or shipped project against real market data and produce an investor-grade Market Validation report (executive summary, product, TAM/SAM/SOM with live model, competition and positioning map, positioning and brand, go-to-market, growth levers, business model and operations with a scaling calculator, risks and kill criteria, 90-day roadmap, assumptions, sources) as a self-contained interactive HTML document plus research markdown in <project>/marketvalidation/. Reads the repo, docs, site, history and any brief, then runs web research. Use when the user says /marketvalidation, "validate this idea", "is there a market for this", "audit this product idea", "market fit analysis", "should I build this", "is this worth pursuing", or asks for a market, competitive, GTM or business-model assessment.
-
ponylang Skill Add Linux Bootstrap PlatformLoad when adding a new Linux distro/version (e.g. Alpine 3.24, Ubuntu 26.04) — or both arches for an existing one — as a fully supported ponyup bootstrap-test target. Covers the bootstrap-tester Dockerfile, image build dispatch and tag discovery, CI workflow updates (tier 1 / tier 2), ponyup-init.sh detection, optional canonical-example promotion, and release notes.
-
psylch Bundle Hifi DownloadDiscover music, get personalized recommendations, and download high-fidelity audio files. Use when user wants to find new music based on their taste, search for songs/albums/artists, get recommendations similar to artists they like, or download lossless audio (FLAC/Hi-Res) from Qobuz or TIDAL. Trigger phrases include "find music like", "recommend songs", "download album", "lossless", "Hi-Res", "FLAC", "music discovery", "similar artists", "setup music".
-
qiran87 Bundle Web Search FreeSearch the public web and fetch readable HTML, JSON, CSV, text, and PDF content with a local-first, zero-paid-API workflow. Use when Codex needs current web evidence, topic discovery, official-source lookup, URL extraction, PDF text, source collection, or a free fallback before Tavily/Firecrawl. Also use when users mention WebSearch, WebFetch, DDGS, SearXNG, Jina Reader, local scraping, web research cost control, or avoiding paid search credits.
-
pranavred Bundle Logo DesignDesign and create professional SVG logos, brand marks, wordmarks, and icons. Use when designing logos, creating brand identity graphics, writing SVG path data, building icon variants, optimizing SVGs, or modifying existing vector graphics. Covers a full design process including discovery, metaphor exploration, structural variety, progressive preview, dark mode variants, and SVG authoring with path commands, shape primitives, styling, accessibility, gradients, masks, sprites, optimization, and animation.
-
qkgecn93 Bundle Bys Learn Plan不一书学习路线图(bys-learn-plan):用户想掌握某样东西时,像朋友一样把需求聊清楚,联网搜集并核实资料, 设计一份从零开始的个人学习路线图(分阶段、有时间安排、有资料、有练习、每阶段一个"我能……"的里程碑), 输出 Markdown + 可分享的 HTML 旅程海报 + 打印版,之后还能陪用户按进度更新调整。 只要用户表达出"想学会 / 想掌握 / 想入门 / 想搞懂 / 想转行做 / 想考某个证 / 看到一个词或一篇文章想弄明白它属于什么、 该从哪学起 / 有个目标(想当咖啡师、想自己炒股、想做独立开发者)不知道该学什么 / 帮我做个学习计划 / 学习路线 / 成长路线 / roadmap / learning path / study plan",哪怕说得很模糊,都应触发本 Skill。 用户回来说"我学到第几阶段了 / 进度落后了 / 这本书不合适 / 帮我调整一下计划"时,也走本 Skill 的更新模式。 不要 undertrigger:用户只说"我想学一下 XX"也该触发——直接回答会给出一份没有经过沟通、资料没核实、没有时间设计的泛泛清单。 不用于:讲解某个具体知识点、写代码、做题、翻译资料。
-
qlhouseclub Bundle Design GrandmasterEnd-to-end design direction and execution with binding-spec and Design Token conformance, visual inheritance, code-value audits, CJK/Latin/numeral/icon baselines, spatial rhythm, editorial and creative image-text composition, masks/positioning/pseudo-elements, batch visual revision maps, progressive-loading decisions, responsive boundary safety, dependency authorization, taste discovery, live research, layout freshness, anti-convergence, high-craft judgment, trends, brand, accessibility, prototyping, critique, and handoff. Use for 设计规范与Token审计、改版语言承袭、代码视觉值、中英数字图标混排基线、空间秩序、文字与图文编排、创意排版、蒙版定位伪元素、页面区块修改点与视觉定位图、渐进式加载判定、运行环境与依赖授权、品牌/UI/UX布局、双端安全区、非装饰性贴边、滚动裁切与横向溢出、无规范调研、版式新鲜度与模板收敛、移动端重构、组件库、客户审美、全网视觉调研、高级审美、历史文化风格与视觉潮流、品牌视觉、交互、设计系统、体验审查、改版、原型和组件规范; or whenever work must remain coherent, accessible, build-ready, visually authored, and free of unauthorized system drift, unsafe edge contact, or habitual agent styling.
-
q00 Skill OpenwardenUse when the user wants a Warden review from an SSOT issue, roadmap, RFC, or brief. Turns a canonical source link plus active work surfaces into an evidence-backed alignment review without implementing, approving, merging, or force-closing work.
Audited -
quicksketcherz Bundle Session Log CompanionComprehensive project session companion for documenting work sessions, creating knowledge logs when discovering or learning something, teaching agent preferences, and improving collaboration. Use when user says "start a session", "create session log", "summarize this session", "document this discovery", "create a knowledge log", "I want to improve how you work with me", "remember this preference", "let's continue", "continue from last session", "pick up where we left off", "what should I work on next", or any session/documentation-related request. Also trigger when user mentions being stuck, hitting an impasse, needing to understand concepts, or wanting to capture learnings.
-
read2017 Bundle Business HTML Ppt生成适合职场汇报的商务风单文件 HTML 演示文稿,适用于工作汇报、业务复盘、项目进展、方案提案、周报月报、OKR 复盘、述职晋升、管理层汇报和客户汇报。当用户想把零散职场材料变成专业 PPT、幻灯片、HTML PPT、浏览器演示文稿、汇报 deck,或需要带目录、演讲备注、商务视觉和键盘翻页的职场演示文稿时使用。
-
reassignai Bundle Reassign SchedulingPlan, edit, and review the user's day on the Reassign circular 24-hour calendar. Use whenever they schedule, block, move, or find time, plan a day or week, reshuffle, protect focus, review where time went, or work on ADHD-friendly time management — or mention time blocking, deep work, pomodoros, body doubling, "eat the frog," or feeling overwhelmed, scattered, or behind. Use it when they connect, sync, or mirror a calendar (Google, Outlook) or task list (Todoist), ask why an imported event blocks, or want a non-blocking band (sleep, fasting) or see-only reference event. Use it for weather around a plan (a run or commute around rain or daylight), for energy and peak/dip windows, and when they look back on a past day or week and want to record that reflection. Use it when they capture a task with no time yet, park a block, jot into their backlog, pencil one in for a day or range, ask what they planned for today, or place a parked block on the dial. Use it when they break a block into steps or microtasks, tick o
-
ra1nyxin Bundle Immersive Vibration ResponseProvide autonomous, low-power haptic feedback and a playful, opinionated interaction style for players through the local ESP32 vibration bridge. Use for interactive games, embodied-agent play, roleplay, simulations, live narratives, and long-running creative or coding tasks whenever game events, decisions, task starts, progress, completion, errors, inactivity, tension, impact, discovery, or environmental changes can benefit from immersive vibration, including when the player has not explicitly requested a vibration.
-
rastian Bundle Design ThinkingGuide any team through the Design Thinking methodology — empathize, define, ideate, prototype, test, and implement. Core audiences: product & design teams (product designers, UX researchers, UI designers, service designers, product managers), entrepreneurs & startups (idea validation, customer discovery, lean prototyping), and business & strategy leaders (innovation workshops, service redesign, customer journey mapping, business model innovation). Trigger on: design sprint, HMW question, how might we, empathy map, affinity diagram, point of view statement, design brief, user journey, service blueprint, jobs to be done, usability test, problem statement, customer discovery, lean validation, innovation workshop, or when user describes a user problem and wants to explore human-centered solutions.
-
rafalr100 Bundle Enterprise ArchitectOperate as a world-class Enterprise Architect (FAANG / top-tier consulting calibre) grounded in TOGAF, Zachman, and modern EA practice. Opens with discovery — asks the clarifying questions that materially change the architecture before producing any deliverable. Activates when the user asks for enterprise-architecture work — target architectures, reference architectures, architecture patterns, standards, principles, capability maps, technology strategy, roadmaps, trade-off analysis, architecture decision records, governance, or audience-tiered architecture presentations (C-level/board, solution architect, or engineering decks), or any "should we build X / how should this be structured at enterprise scale" question. Decomposes heavy multi-workstream engagements into parallel threads (sub-agents where available, sequential threads otherwise) and owns the synthesis. Does NOT activate for narrow single-app coding, infrastructure ticket-level fixes, or non-architecture conversation.
-
remoet-labs Skill RemoetJob search and career discovery through your agent. Search the open tech job board directly, or star the companies that match your stack for an ongoing feed of their roles, all by talking. Backed by company-level tech stack data derived from the roles each company is hiring for now.
-
ravipalwe Bundle ThroughlineThroughline — turns messy UX research into a ranked, defensible backlog with the receipts attached. Takes raw research (interview transcripts, notes, usability sessions, survey exports) and runs the full synthesis-to-decision pipeline: clusters it into themes, then sharpens them into a PRIORITIZED, evidence-traceable backlog of actionable items (problems, opportunities, requirements) — each ranked by weight of evidence and linked to the verbatim quote and participant behind it. MANDATORY TRIGGERS: turn research into a backlog, what should we build, prioritize insights, research synthesis, synthesize interviews, ranked backlog, defensible decisions, insight to action, decision layer, "pile of interviews", "help me decide what to build", Throughline. Use whenever someone has raw qualitative research and needs to decide and DEFEND what to do about it — not just summarize. For personas, journey maps, or research reports without decisions, prefer PRISM; Throughline starts where summarizing ends.
-
rajann44 Bundle Product ManagementAct as an expert product manager whenever writing product requirements documents (PRDs), product one-pagers, specs, defining product strategy, prioritizing backlogs or feature requests, planning roadmaps, conducting customer interviews or user discovery, defining metrics, OKRs, and North Stars, analyzing product growth or retention, running sprint planning, or writing stakeholder updates. Use this skill even if the user does not explicitly say "product management."
-
reolink Bundle Reolink CLIProvides the only correct mechanism for operating Reolink network cameras locally — the installed `reolink-cli` binary plus its gateway. **You MUST consult this skill whenever the user wants to do anything with an IP / network / surveillance / doorbell camera on their LAN, even if they never say "Reolink"** — e.g. "front-door cam", "garage camera", "IP camera at 192.168.x.x", "make it brighter", "stream URL", "too dark", "upside down", "sound the siren", "scare them off", "arm the house", "i am leaving", "set it to away mode", "disarm", "lower the bitrate", "change resolution", "switch to h265", "upgrade firmware", "flash firmware". Covers discovery, login, snapshots, live preview, PTZ, IR/spotlight/LEDs, image tuning, OSD, the manual siren, scene / arming modes on a hub, video encoder settings (resolution / frame rate / bit rate / H.264-H.265), motion + AI detection (person/vehicle/pet/package), recording + SD-card status, VOD search/download, alarm events, user accounts, reboot, firmware upgrade, and RTSP/R
-
riadchaban994-bot Bundle Tracking Plan DiscoveryWalk any app hands-on and build or update a real product-analytics tracking plan from what you actually see. Use this whenever someone needs an event taxonomy, a tracking plan, a measurement plan, an analytics spec, an event dictionary, instrumentation for GA4 / Firebase / Amplitude / Mixpanel / Segment / PostHog, or wants to audit or extend tracking that already exists. Use it when the ask is "what should we track", "our analytics are broken", "we have no funnel data", "design the events for this feature", "map the user journeys", or "the dev team needs a spec". It drives an Android emulator, an iOS simulator, a browser or a Figma file, screenshots every surface, groups parameters into reusable attribute packs, grades every event by how strong the evidence for it actually is, and ships a phased, buildable Excel workbook with embedded screenshots. Works for any app in any industry. Reach for it even when the person only says "events" or "instrumentation" and has not used the words tracking plan.
-
robzolkos Skill FizzyManages Fizzy boards, cards, steps, comments, and reactions. Use when user asks about boards, cards, tasks, backlog or anything Fizzy.
-
roy-tong Bundle Find Research ToolRoute research tasks to Roy Tong's open-source Agent Skills and local-first tools. Use when a user needs continuous research monitoring, source discovery, recurring research digests, evidence-led user-demand or voice-of-customer analysis, willingness-to-pay validation, Bilibili video-to-text or subtitles, Roy Tong's public AI product research, measurement-conformance checks on agent telemetry (retry accounting, operation vs attempt, token double counting), or asks which Roy Tong project, Skill, CLI, or research tool to use. 中文触发:选择研究工具、持续行业监测、信源发现、用户需求研究、评论挖掘、付费意愿、B站视频转文字、检索 Roy Tong 公开研究、遥测语义核查、重试计数、用量口径。
-
rodrigomardones Bundle HandymanInstall, analyze, bootstrap, run, review, or migrate a Handyman agent harness: leader/implementer/reviewer roles work one feature at a time with disk state and executable verification. Triggers: harness or subagent workflow, feature_list.json, AGENTS.md, CHECKPOINTS.md, progress/, backlog/, HARNESS_WORKSPACE, .handyman, $HOME/HANDYMAN, per-role models/tools, anti-telefono-descompuesto, Obsidian vault harness. DO NOT USE FOR generic coding without the harness workflow.
-
rivet-dev Skill Riveter Create RunConvert a spec into a Ralph the Riveter PRD and run folder for `riveter run`. Triggered by "riveter create run", "create a prd for riveter", "spec out", "plan this feature for riveter", or "convert this spec for riveter". Non-interactive — does not ask follow-up questions.
-
rqzhu-aide Bundle Causal ConsultantExplicit-use interactive causal consulting team. Use only when the user explicitly asks to use causal-consultant, the causal consultant skill/team, or an interactive persistent causal-consultant workflow for project intake, data audit, domain expertise, causal discovery, causal checking, report writing, methods/results interpretation, reviewer-response support, or project state tracking.
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 enterprise-architect, handyman, causal-consultant. 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.