agentsclimarketplace
Sign in

Shelves

Plan & spec

10,946 rows from 2,522 repositories

Deciding what to build, and writing it down before building it.

What Plan & spec skills agree on

2,010 skill files read, by 1,360 of the 2,617 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 202 measured here is ~1.6k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Ask one question at a time73 of 1360also worded as Ask one question at a time during interviews; Ask questions one at a time
  2. Write the spec using the template22 of 1360also worded as Write the spec document; Write the spec file
  3. Ask clarifying questions if needed19 of 1360 in 18 filesalso worded as Ask only necessary clarifying questions; Ask clarifying questions
  4. Wait for user confirmation before proceeding19 of 1360also worded as Wait for user approval before proceeding; Wait for confirmation before filing issues
  5. Save plans to the plans directory17 of 1360 in 13 filesalso worded as Save plans to the specified directory; Save the plan to the docs directory
  6. Check for product marketing context first16 of 1360 in 5 files
  7. Read the plan file completely16 of 1360also worded as Read the plan file; Read the plan completely before starting
  8. Order tasks by dependency16 of 1360also worded as Create tasks in dependency order; Order tasks by dependency and mark parallel tasks
  9. Gather context from the conversation15 of 1360 in 9 filesalso worded as Gather context from conversation; Gather context from the conversation or issue tracker
  10. Explore the codebase instead of asking15 of 1360 in 13 filesalso worded as Explore the codebase to answer questions; Explore the codebase for facts instead of asking.
  11. Wait for explicit user approval14 of 1360 in 13 filesalso worded as Wait for user approval; Wait for explicit user approval before analyzing
  12. Quiz the user on the breakdown13 of 1360 in 7 filesalso worded as Quiz the user on the proposed breakdown; Present the breakdown to the user
  13. Present the plan to the user13 of 1360also worded as Present the plan and wait for user approval; Present the plan for user approval
  14. Read the full spec file13 of 1360also worded as Read the spec and plan; Read the spec and glossary
  15. Read the plan before deciding12 of 1360 in 9 filesalso worded as Re-read plan before major decisions; Re-read plan before decisions

What they tell it not to do

  1. Do not write code39 of 1360also worded as Do not write implementation code; Never write code
  2. Do not implement code34 of 1360also worded as Do not implement; Never write implementation code
  3. Do not batch multiple questions23 of 1360 in 18 filesalso worded as Never batch questions; Do not batch multiple questions together
  4. Do not skip steps20 of 1360also worded as Do not skip phases; Do not skip steps or output early
  5. Do not start implementation20 of 1360also worded as Do not start implementing; Do not use for implementation.
  6. Do not invent a plausible entry to fill a field19 of 1360also worded as Never invent a plausible entry to fill a field; Do not invent a plausible entry
  7. Do not use placeholders19 of 1360 in 16 filesalso worded as Do not use placeholders like TBD or TODO; Do not use placeholder code or stubs
  8. Do not interview the user17 of 1360also worded as Do not interview the user to gather new information; Never answer interview questions on the user's behalf
  9. Do not close or modify any parent issue15 of 1360 in 9 filesalso worded as Do not close any parent issue; Do not modify any parent issue
  10. Do not modify files15 of 1360also worded as Do not modify any file; Do not modify source code

What they expect to be installed

  1. git210 of 1360
  2. AskUserQuestion125 of 1360
  3. grep109 of 1360
  4. gh80 of 1360
  5. bash74 of 1360
  6. python368 of 1360
  7. Read66 of 1360 in 60 files
  8. Agent52 of 1360
  9. Glob49 of 1360
  10. node48 of 1360

What they ask it to produce

  1. plan.md101 of 1360also worded as Plans.md; final_plan.md
  2. spec.md87 of 1360also worded as spec; spec md
  3. Implementation plan75 of 1360also worded as Implementation plan file; Implementation plan document
  4. tasks.md43 of 1360 in 41 filesalso worded as task_plan.md; tasks/todo.md
  5. design.md27 of 1360also worded as architecture.md; security-design.md
  6. Pull request25 of 1360also worded as pull requests; pull request review
  7. Markdown file23 of 1360 in 21 filesalso worded as spec markdown file; markdown
  8. research.md22 of 1360 in 20 filesalso worded as findings.md; REPORT.md

When Plan & spec authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 1,360 authors, with the skills that name each one

How Plan & spec skills are built

10,181 skill directories by 2,258 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 3 files, 13.9 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill879 of 2,258 authors, 5,238 of 10,181 skills
  2. files ship beside it1,379 of 2,258 authors, 4,943 of 10,181 skills
  3. executable scripts ship inside410 of 2,258 authors, 1,104 of 10,181 skills

The folders they converge on

  1. references/827 of 2,258 authors, 2,703 of 10,181 skills
  2. scripts/332 of 2,258 authors, 946 of 10,181 skills
  3. agents/288 of 2,258 authors, 788 of 10,181 skills
  4. assets/212 of 2,258 authors, 502 of 10,181 skills
  5. evals/154 of 2,258 authors, 522 of 10,181 skills
  6. templates/142 of 2,258 authors, 320 of 10,181 skills

  • Planning with files

    OthmanAdi/planning-with-files/skills/planning-with-files Skill

    26,165★ repo

    Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Claude Code, Codex, Cursor, Kiro, OpenCode and 60+ agents via the Agent Skills standard.

  • Ablation planner

    wanshuiyin/Auto-claude-code-research-in-sleep/skills/ablation-planner Skill

    14,663★ repo

    ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

  • Jira driven planning

    breaking-brake/cc-wf-studio/.claude/skills/jira-driven-planning Skill

    no license5,347★ repo

    CC Workflow Studio

  • Ab test plan

    indranilbanerjee/digital-marketing-pro/skills/ab-test-plan Skill

    734★ repo

    Open-source AI marketing plugin for agencies & in-house teams — 158 skills, 25 specialist agents, 12-Part Strategy Flow, Cowork team-persistent, EU AI Act Article 50 ready, 6-platform AEO/GEO incl. Google AI Mode. Installs on Claude Code, Cowork, Codex, Cursor, Copilot CLI, Antigravity. MIT-licensed.

  • Affiliate marketing strategy

    nexscope-ai/eCommerce-Skills/affiliate-marketing-strategy Skill

    675★ repo

    E-commerce skills for AI agents — product research, marketing automation, supply chain optimization, and business analytics for online sellers across Amazon, Shopify, Etsy, TikTok Shop, and all platforms.

  • Prd taskmaster

    anombyte93/prd-taskmaster Skill

    587★

    Zero-config goal-to-tasks engine for Claude Code (the Atlas engine). Graded PRD validation, dependency-ordered task graph, evidence-gated execution.

  • Adversarial spec

    zscole/adversarial-spec/skills/adversarial-spec Skill

    553★ repo

    A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.

  • Analyze and plan

    Optim-Agent/optim-plans/skills/analyze-and-plan Skill

    494★ repo

    Human-in-the-loop planning plugin for Claude and Codex: turn ideas into reviewed Markdown plans, record decisions, enforce explicit execution gates, and provide tested controller primitives for safer agent workflows.

  • Spec driven development

    formulahendry/mcp-server-spec-driven-development/io.github.formulahendry/spec-driven-development MCP server

    435★ repo

    MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

  • Llm council

    gcpdev/llm-council-skill/llm-council Skill

    408★ repo

    A skill to claude code that enables brainstorming with other LLMs (ChatGPT, Gemini) before presenting the implementation plan to the user

  • Plan skill

    owainlewis/youtube-tutorials/tutorials/codex-for-developers/resources/04-skills/plan-skill Skill

    340★ repo

    All my YouTube tutorials. Everything here is free - but please follow me on YouTube if you find these helpful. ❤️

  • Chunking strategy

    giuseppe-trisciuoglio/developer-kit/plugins/developer-kit-ai/skills/chunking-strategy Skill

    329★ repo

    Modular plugin marketplace for Claude Code and agentic CLIs, with validated, spec-driven skills, agents, commands, and workflows for Java, TypeScript, Python, PHP, AWS, and AI.

  • Daily brief

    leiting-eric/DailyBrief/.claude/skills/daily-brief Skill

    320★ repo

    AI 每日新闻简报 · GitHub 热门 + X 热门文章 + 行情技术分析 · 23 个数据源聚合 + LLM 中文摘要 · 本地或 GitHub Actions 部署

  • Content brief

    inhouseseo/superseo-skills/skills/content-brief Skill

    249★ repo

    11 Claude skills for SEO: page audits, linkbuilding, article writing, E-E-A-T audits, semantic gap analysis, link building. Methodology from Koray Tuğberk, Kyle Roof, and Lily Ray, plus a generation-time anti-AI-slop ruleset. Production-tested at InhouseSEO

  • Prd

    golbin/agent-skills/skills/prd Skill

    no license209★ repo

    Reusable agent skills for Codex and compatible tools

  • Brainstorming

    arbiterForge/codeArbiter/core/surface/skills/brainstorming Skill

    141★ repo

    When you can't trust yourself with your code base, trust Arbiter.

  • Usage governor

    0xhimanshu/governor/skills/usage-governor Skill

    127★ repo

    Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

  • Brain jam plan

    elb-pr/claudikins-kernel/skills/brain-jam-plan Skill

    126★ repo

    SRE thinking applied to Claude Code, based on Boris Cherny's Q&A. It enforces a strict 4-stage pipeline with gates between each step. You literally cannot skip verification. You cannot ship without approval.

  • Breadth chart analyst

    BaggaT236/AI-Trading-Skills/examples/weekly-trade-strategy/skills/breadth-chart-analyst Skill

    118★ repo

    Ai agent claude trading skills for disiplined, repeatable trading workflows with a modern typescript platform

  • Cesium context7

    CesiumGS/cesium-ai-integrations/.github/skills/cesium-context7 Skill

    86★ repo

    Cesium AI Integrations is a collection of reference integrations and experiments connecting the Cesium ecosystem with AI systems including Model Context Protocol (MCP) tools, retrieval pipelines, and agent skills.

  • Skill

    DogInfantry/claude-skill-management-consultant-B1/skill Skill

    no license83★ repo

    Claude skill & plugin: turn Claude (or any LLM) into an MBB-grade management consultant. Case-interview coaching, strategy frameworks, market sizing, board-ready problem-solving. 129 reference modules. Free & open-source.

  • Travel guidebook

    geekjourneyx/travel-guidebook Skill

    75★

    AI agent skill that generates beautifully typeset travel guidebook PDFs — from research to print, powered by parallel agents and Amap MCP.

  • Brainstorm

    oprogramadorreal/optimus-claude/skills/brainstorm Skill

    71★ repo

    Primes your project for peak Claude Code performance

  • Mckinsey style visualization skill

    kgraph57/mckinsey-style-visualization-skill Skill

    65★

    Agent Skill that turns messy notes into rendered strategy-consulting visuals, with SVG examples and validation.

  • Artifact consistency checker

    GulajavaMinistudio/awesome-copilot-id/.agents/skills/artifact-consistency-checker Skill

    58★ repo

    A curated collection of custom agents, skills, rules, and prompts for GitHub Copilot, Google Antigravity, OpenCode, ChatGPT Codex, and Oh My Pi. Tailored for Indonesian developers to streamline SDLC workflows with AI.

  • Account research brief

    Othmane-Khadri/gtm-engineer-playbook/.claude/skills/gtm-playbook/account-research-brief Skill

    53★ repo

    10 installable Claude Code skills that turn your terminal into a GTM command center. ICP building, signal scanning, lead scoring, outreach sequences, battlecards. Built by Earleads.

  • Backup strategy

    chaterm/terminal-skills/backup/backup-strategy Skill

    53★ repo

    Public Agent Skills for Terminal and Kubernetes

  • MoneyAtlas ClaudeSkill Agent

    ElmatadorZ/MoneyAtlas-ClaudeSkill-Agent Skill

    53★

    Money Atlas Skill.md (Claude Skill) For AI Agent A Genesis Protocol-powered intelligence system for financial markets, macroeconomics, and geopolitics. Core Systems - Genesis Protocol (First Principle + System Thinking) - SMC Layer Engine (Quant price structure)

  • Writing prds executable

    liqiongyu/lenny_skills_plus/samples/writing-prds-executable Skill

    51★ repo

    86 agent-executable skill packs converted from RefoundAI’s Lenny skills (unofficial). Works with Codex + Claude Code.

  • Research craft skill

    nik1t7n/research-craft-skill Skill

    50★

    Agent skill for better research loops

  • Speq audit

    marconae/speq-skill/.claude/skills/speq-audit Skill

    48★ repo

    A light-weight and straightforward system for spec-driven development with Claude Code or OpenAI Codex. Written in Rust 🦀

  • Canadian finance planner skill

    cjpatten/canadian-finance-planner-skill Skill

    46★

    A Claude skill that turns Claude into your personal financial planner — built specifically for Canadians. Interviews, budgets, action plans, interactive dashboards, and ongoing coaching.

  • Recursive decomposition

    massimodeluisa/recursive-decomposition-skill/plugins/recursive-decomposition/skills/recursive-decomposition Skill

    44★ repo

    Claude Code skill for handling long-context tasks through recursive decomposition

  • Anycap ai tool seo

    anycap-ai/anycap/skills/anycap-ai-tool-seo Skill

    42★ repo

    The capability harness for AI agents. Skills over SDKs.

  • Agent builder

    keysersoose/claude-agent-builder/agent-builder Skill

    41★ repo

    Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subagents, skills, hooks, commands & MCP configs.

  • Enterprise prd writer

    skinnerlee1225/enterprise-prd-toolkit/skills/enterprise-prd-writer Skill

    40★ repo

    把金融級 PRD 方法論工程化成四個 Claude Skills：找洞 → 寫規格 → 產測試。含交易所提現、自營交易挑戰賽的完整 PRD 範例。

  • Consulting

    yoichiojima-2/consultant/skills/consulting Skill

    34★ repo

    50+ consulting frameworks used by McKinsey, BCG, Bain, and Accenture — packaged as a Claude Code plugin

  • Spec flow

    echoVic/spec-flow Skill

    33★

    A Claude Code skill for structured, spec-driven development with phase-by-phase workflow and living documentation

  • Interview and create plan

    doeixd/opencode-ralph-rlm/skills/interview-and-create-plan Skill

    no license30★ repo

    OpenCode plugin: Ralph outer loop + RLM inner loop — iterative AI development with file-first discipline and sub-agent support

  • Brand asset

    sanky369/vibe-building-skills/skills/creative/brand-asset Skill

    29★ repo

    Open-source agent skills library for building SaaS, marketing systems, creative assets, and frontend design workflows

  • Docs context

    lujiafa/houtu-project-skills/skills/docs-context Skill

    26★ repo

    A curated collection of skills, practices, and tooling used throughout the project lifecycle — from development to testing and beyond.

  • Tandem agentic engineering

    Maxmedawar/tandem/skills/tandem-agentic-engineering Skill

    25★ repo

    Tandem is an MCP bridge that lets a chatbot (Claude.ai or ChatGPT) spin up and drive, interactive Claude Code sessions on your own machine. Runs 2 sessions in a lead/worker loop that works autonomously. Also makes claude code respond to the initial Chatbot through the browser so it can respond back.

  • Loop maker

    jbrazy480/loop-maker/loop-maker Skill

    25★ repo

    🔁 Write loops, not prompts. Free skill that generates overnight autonomous AI runs for Claude Code, Codex & Cursor: master prompt, plan, verifier, one command. By AI Guy Official.

  • Ql brainstorm

    andyzengmath/quantum-loop/skills/ql-brainstorm Skill

    24★ repo

    Spec-driven autonomous development loop for Claude Code. Combines structured PRD generation, dependency DAG execution, two-stage review gates, and Iron Law verification.

  • Ai delivery spec

    franklinxkk/ai-delivery-spec Skill

    22★

    Requirement management Skill for one human-readable, AI-coding-ready baseline: intake, clarification, PRD/prototype contracts, change, traceability, and acceptance for ToC/ToB/ToG.

  • Abx strategy

    yannickYamo/skills/abx-strategy Skill

    20★ repo

    AI skills for Claude Code. Product marketing, strategy & GTM frameworks by a product leader and full-stack builder in the age of AI.

  • Add

    pilotspace/ADD/.claude/skills/add Skill

    18★ repo

    ADD - LOOP SKILL for AI Coding Agent

  • Mece

    uxderrick/mece-skill/skills/mece Skill

    17★ repo

    MECE (Mutually Exclusive, Collectively Exhaustive) validation and decomposition skill for AI agents. Works with Claude Code, Cursor, Copilot, Codex, Gemini CLI.

  • Act

    Jed-Tech/spar-kit/Research/research/example skills/act Skill

    17★ repo

    Specify → Plan → Act → Retain: SPAR-kit is a lightweight workflow that helps AI agents align with your intent, plan clearly, act with less drift, and retain durable project memory.

  • Sdlc 1 plan

    hackersandwizards/artificer/examples/sdlc/.claude/skills/sdlc-1-plan Skill

    16★ repo

    An artificer's kit for building minimal dark-factories on Claude Code. Compose small, gated agent steps into deterministic builds you can read end to end.

  • Codex implementation loop

    olddonkey/olddonkey-skills/skills/codex-implementation-loop Skill

    15★ repo

    Agent skills distilled from real-world usage — codex-implementation-loop: delegate coding to Codex, keep review/gate/ship judgment in Claude's hands

  • Business decomposition order quality

    spikeHongg/china-stock-research-skills/skills/business-decomposition-order-quality Skill

    15★ repo

    Open-source agent skills for China stock and A-share research: Chinese-first outputs, citation-first analysis, and orchestrated workflows.

  • Consulting gauntlet

    averma416/consulting-gauntlet Skill

    no license14★

    Full-stack consulting skill for Claude Code — 6 AI agents, 16 strategy frameworks, CPA-level financial modeling, zero hallucinations

  • Brainstorming and planning

    burhankhatri/e2e-testing/skills/brainstorming-and-planning Skill

    no license14★ repo

    A set of 8 global skills for Claude Code that enforce disciplined, test-driven agentic development. Install once, use in any project.

  • Breakdown tasks

    hungv47/meta-skills/forsvn-dev/skills/meta/breakdown-tasks Skill

    14★ repo

    Turn your coding agent into a full product team — composable skills across research, marketing, product, and process. One install, every editor (Claude Code, Cursor, Codex, Windsurf, Gemini CLI, VS Code).

  • Fathom

    ma-ziwei/fathom-mode-for-claude/plugin/skills/fathom Skill

    13★ repo

    Planning mode for Claude Code and Cowork. Claude pauses execution, clarifies intent, and compiles a reviewable plan before acting on complex tasks.

  • Specmint core

    ngvoicu/specmint-core Skill

    12★

    Persistent, resumable specs for AI coding agents. Deep research, iterative interviews, phased implementation, resume context. Claude Code plugin + universal skill (Codex, Cursor, Windsurf, Cline, Gemini CLI, Devin, Antigravity).

  • Code roadmap

    mirkobozzetto/arsenal/plugins/code-roadmap/skills/code-roadmap Skill

    12★ repo

    Mirko Bozzetto's curated skills for AI coding agents (Claude Code, Codex, Cursor, ...)

  • Architecting

    VidyFoo/antigravity-skill-engine/.agent/skills/1-dev/architecting Skill

    12★ repo

    Antigravity Skills Engine (ASE) - The ultimate Claude Skills library for AI agents featuring 16+ industrial-grade professional tracks.

  • Autonomous build

    labeveryday/claude-put-in-work/.claude/skills/autonomous-build Skill

    11★ repo

    This is a repo used to make claude put in work autonomously.

All 10,946 in the catalog