Plan & spec
10,741 rows, by stacks then stars
2,010 of these skill files have been read, by 1,360 distinct authors, and what they tell an agent counted. What Plan & spec authors agree on, and what they forbid
uzysjung/uzys-agent-harness/templates/skills/strategic-compact Skill
3★ repoSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
uzysjung/uzys-agent-harness/templates/skills/ultracode-service-audit Skill
3★ repoRun a multi-agent, adversarially-verified full-service audit across 7 dimensions (code / UX / scalability / planning+north-star / security / promotion / extensible), separating findings into confirmed / unverified / rejected and producing a priority-ranked, M-numbered milestone roadmap (as many milestones as the findings warrant). Use when the user says "ultracode 전체 서비스 점검", "전체 서비스를 점검하자", "코드·UX·확장성·기획·북극성지표·보안·홍보 문제점을 파악하고 우선순위에 따라 개선", "다차원 서비스 감사", or in English "audit the whole service / full multi-dimensional service audit / find code, UX, scalability, planning, security, and marketing problems and prioritize fixes". The heavyweight superset audit — orchestrate it as a Workflow with fan-out finders and an adversarial verify pass. NOT for a single-artifact prose/README review (use multi-persona-review) or a single-axis gap-vs-benchmark loop (use gap-analysis-e2e) — those are the lighter siblings.
tjmaynes/skills/skills/otto Skill
3★ repoUse for significant coding work that should move from idea to approved design, approved implementation plan, and automated build execution. Do not use for read-only review, quick one-file edits, direct bug fixes with an obvious patch, exploratory questions, or tasks where the user only wants planning.
JayRHa/AgentSkills/event-planner Skill
3★ repoPlans events end-to-end — birthdays, weddings, dinner parties, offsites, conferences, fundraisers — with a budget breakdown, guest and venue logistics, a backward-planned timeline, vendor checklist, run-of-show, and contingency plans. Use this skill when a user asks to "help me plan a party / wedding / event", "organize an offsite or conference", "throw a dinner for X people", "make an event timeline / checklist", or wants a budget and run-of-show for a gathering.
JayRHa/AgentSkills/meal-plan-builder Skill
3★ repoBuilds balanced weekly meal plans with calculated macros, calorie targets, ingredient variety, batch-prep steps, and a consolidated grocery list organized by store aisle. Use this skill when a user asks to "plan my meals", "make a meal plan", "weekly menu", "what should I eat this week", "meal prep plan", "create a grocery list from meals", "plan meals for X calories/macros", or wants help with budgeting, dietary restrictions (vegan, keto, gluten-free, halal, etc.), family meal planning, or reducing food waste.
JayRHa/AgentSkills/okr-writer Skill
3★ repoWrites strong OKRs (Objectives and Key Results) with outcome-focused, inspiring objectives and measurable, ambitious, time-bound key results. Use this skill when the user asks to write, draft, review, critique, or improve OKRs, goals, or quarterly/annual objectives, when they mention "objectives and key results", "set goals for the team", "turn this strategy into OKRs", "are these good key results", or when distinguishing outcomes from outputs/tasks for planning and performance.
JayRHa/AgentSkills/personal-budget-planner Skill
3★ repoBuilds a realistic personal or household budget from income and expenses — choosing a budgeting method (50/30/20, zero-based, envelopes), categorizing spending, setting savings and debt-payoff targets, and producing a monthly plan with an emergency-fund and debt strategy. Use this skill when a user asks to "make me a budget", "help me manage my money", "where is my money going", "save more / pay off debt", "monthly budget", or wants a household spending plan.
JayRHa/AgentSkills/project-planner Skill
3★ repoDecomposes a goal into a work breakdown structure (WBS) with milestones, task dependencies, and effort estimates, then produces a schedule, critical path, and risk list. Use this skill when the user wants to plan a project, "break this down into tasks", build a work breakdown structure, create a project plan or roadmap, estimate effort/timeline, identify dependencies or the critical path, sequence work, or turn a goal/spec into an actionable, scheduled task list.
JayRHa/AgentSkills/study-plan-builder Skill
3★ repoBuilds a realistic, personalized learning roadmap for a skill or subject — with milestones, curated resource types, active practice, spaced review, and progress checkpoints — fit to the learner's deadline and weekly time budget. Use this skill when the user asks to "make a study plan", "create a learning roadmap", "help me learn X in N weeks", "plan how to study for an exam", "build a curriculum", or wants a structured path to master a topic. Grounded in learning-science principles (spacing, retrieval, interleaving).
JayRHa/AgentSkills/swot-analyzer Skill
3★ repoProduces a rigorous SWOT analysis (Strengths, Weaknesses, Opportunities, Threats) for a company, product, team, project, or personal decision, then converts the four quadrants into prioritized, concrete strategic actions using a TOWS cross-matrix. Use this skill when the user asks for a "SWOT analysis", "SWOT", "strengths and weaknesses", "competitive analysis", "strategic assessment", "situation analysis", "should we launch/enter/pivot", or wants help turning a SWOT into an action plan, strategy, or roadmap.
JayRHa/AgentSkills/trip-planner Skill
3★ repoBuilds realistic, day-by-day travel itineraries that balance logistics, budget, pacing, and local highlights, with hour-level day plans, transit links, cost estimates, and contingency buffers. Use this skill when a user asks to "plan a trip", "build an itinerary", "plan X days in <city/country>", "what should I do in <destination>", "make a travel schedule", "plan a road trip / honeymoon / family vacation", or wants help sequencing activities, allocating a travel budget, or pacing days to avoid burnout.
JayRHa/AgentSkills/user-story-writer Skill
3★ repoWrites high-quality agile user stories that satisfy the INVEST criteria, with clear role/goal/benefit phrasing and testable Gherkin (Given/When/Then) acceptance criteria, and splits epics into thin vertical slices. Use this skill when the user asks to "write a user story", "create acceptance criteria", "break this epic into stories", "turn this requirement into a backlog item", "write Gherkin scenarios", or is grooming/refining a product backlog.
JayRHa/AgentSkills/workout-planner Skill
3★ repoBuilds safe, progressive, personalized workout programs around a person's goal, experience level, available equipment, schedule, and constraints — with weekly splits, exercise selection, sets/reps, progression rules, and deload guidance. Use this skill when a user asks to "make me a workout plan", "build a training program", "gym routine for X days a week", "help me build muscle / lose fat / get stronger", "home workout with no equipment", or wants a push/pull/legs, upper/lower, or full-body split.
control-decks/think-it-through/plugins/think-it-through/skills/grill Skill
3★ repoStress-test a proposal, assumption, decision, design, or plan through a relentless multi-turn grill that follows its decision tree one question and recommendation at a time. Use only when the user invokes grill or asks for a demanding challenge; never begin silently.
control-decks/think-it-through/plugins/think-it-through/skills/to-brief Skill
3★ repoTurn the full available conversation or a result from the same combo into a neutral, reusable Thinking Brief. Use only when the user invokes to-brief or asks to preserve the thinking; never create or overwrite a durable artifact silently.
control-decks/think-it-through/plugins/think-it-through/skills/to-plan Skill
3★ repoTurn an accepted or explicitly provisional executable direction into an ordered, verifiable Execution Plan using the agent's native planning surface when available. Use only when the user invokes to-plan or asks for an operational plan; never plan or execute silently.
arsudsandesh97/Revoact/skills/prd-doc Skill
3★ repoGenerate comprehensive Product Requirements Documents (PRDs) for any software project, feature, or product initiative
arsudsandesh97/Revoact/skills/roadmap-doc Skill
3★ repoGenerate a complete ROADMAP.md (or PHASES.md) file for any project. Use whenever the user asks to create, write, generate, or draft a ROADMAP.md or PHASES.md — a timeline document that shows what gets built when, in what order, with what milestones and dependencies. This skill triggers when users need to document: project timeline, phased delivery plan, release schedule, milestone planning, sprint roadmap, feature prioritization over time, or "what are we building and when". Do NOT trigger for single-feature implementation plans (use Design.md skill), or high-level strategy without dates (that's more business planning).
Ahoo-Wang/skills/plugins/ahoo-cosid-skills/skills/cosid-strategy-guide Skill
3★ repoChoose the right CosId ID generation strategy for Java distributed systems. Use when the user compares CosIdGenerator, SnowflakeId, SegmentId, or SegmentChainId; asks which generator to use; or evaluates ID type, ordering, throughput, clock sensitivity, machine ID allocation, JavaScript-safe IDs, coordination backends, or production tradeoffs.
The same file is in 1 other repository
Ahoo-Wang/skills/sources/CosId/skills/cosid-strategy-guide Skill
3★ repoChoose the right CosId ID generation strategy for Java distributed systems. Use when the user compares CosIdGenerator, SnowflakeId, SegmentId, or SegmentChainId; asks which generator to use; or evaluates ID type, ordering, throughput, clock sensitivity, machine ID allocation, JavaScript-safe IDs, coordination backends, or production tradeoffs.
The same file is in 1 other repository
Orfi/trackbed/claude/skills/trackbed-plan Skill
3★ repoCreate or update the persisted plan for a Trackbed phase. Writes the phase's plan file in the tracked planning layer so a phase is never executed planless. Default simple mode drafts from the roadmap's scope/done; naming a tool in the prompt ("using superpowers") runs that tool's planning flow and adopts its output. User-invocable.
Orfi/trackbed/claude/skills/trackbed-sync Skill
3★ repoReconcile the Trackbed planning layer to the live roadmap — refresh the state file, roadmap, phase↔ticket mapping, and regenerate the viewer, then check every phase has a persisted plan and notify if one is missing. Read-reconcile only; never advances a phase, authors a plan, or writes Jira. Callable directly, and invoked by trackbed-orchestrate on any material change. User-invocable.
Orfi/trackbed/copilot/skills/trackbed-plan Skill
3★ repoCreate or update the persisted plan for a Trackbed phase. Writes the phase's plan file in the tracked planning layer so a phase is never executed planless. Default simple mode drafts from the roadmap's scope/done; naming a tool in the prompt ("using superpowers") runs that tool's planning flow and adopts its output. User-invocable.
Orfi/trackbed/copilot/skills/trackbed-sync Skill
3★ repoReconcile the Trackbed planning layer to the live roadmap — refresh the state file, roadmap, phase↔ticket mapping, and regenerate the viewer, then check every phase has a persisted plan and notify if one is missing. Read-reconcile only; never advances a phase, authors a plan, or writes Jira. Callable directly, and invoked by trackbed-orchestrate on any material change. User-invocable.
Nembie/claude-code-skills/skills/api-docs-generator Skill
3★ repoGenerate OpenAPI 3.1 specification from existing Next.js API routes. Use when asked to generate API docs, create OpenAPI spec, document endpoints, generate Swagger file, or create API documentation.
The same file is in 2 other repositories
myksyut/pev-harness/skills/pev-linear-sync Skill
3★ repoLinear MCP server 経由で plan.md / verify.json を Linear Issue と双方向 sync。inbound (Linear → spec 抽出)、issue-first (実装前に issue 作成 + branch checkout、v3.3.0+)、outbound success (Done + コメント)、outbound fail (failure summary コメント) の4方向。Linear MCP plugin (`@plugin_linear_linear`) が install済みで認証済みであることが前提
myksyut/pev-harness/skills/pev-spec-template Skill
3★ repoタスク開始時の初回プロンプト雛形を提示。Goal/Constraints/Acceptance Criteria の3要素を強制し、Opus 4.8のliteral instruction-followingに最適化された入力を作る
GhostlyGawd/recursive-harness/skills/roadmap Skill
3★ repoTurn one big goal into a dated, sequenced, measurable ROADMAP.md you stick to. Trigger when the user wants to roadmap / scope out / plan / sequence a multi-feature goal, says "turn this idea into a plan", or keeps iterating with no deadline or win condition. A commitment device vs exploration-loop drift: frame -> decompose -> map deps/risks -> sequence into time-boxed milestones -> hand each feature to build-loop. Each milestone gets a deadline, done-criteria, and a hypothesis you score. Skipping it = endless iteration, no ship date. Single feature -> use build-loop.
hollandkevint/data-product-operator/skills/stakeholder-alignment Skill
3★ repoTranslates between technical data teams and business stakeholders. Use when preparing stakeholder updates, translating technical data work for executives, shaping vague business requests into buildable specs, navigating competing priorities across data consumers, or when someone asks "how do I explain this to my VP?" or "the business team wants X but that's not how data works."
NatsuFox/A-Stockit/skills/astockit/market-brief Skill
3★ repoGenerate the default one-symbol A-share brief. Use when user wants a fast, single-pass synthesis combining current market state, conditional decision framing, and conditional execution planning in one persisted run.
NatsuFox/A-Stockit/skills/astockit/strategy-chat Skill
3★ repoRun a multi-turn strategy Q&A workflow over a stock. Use when user wants iterative discussion anchored to an explicit symbol, artifact, or prior run instead of a one-shot report.
NatsuFox/A-Stockit/skills/astockit/strategy-design Skill
3★ repoDesign an execution plan for one A-share symbol. Use when user wants the execution-planning stage of the workflow: strategy family selection, entry and exit structure, hold horizon, monitoring rules, and execution-realism notes after the investment view is already accepted.
unix2dos/skills/strategic-product-advisor Skill
3★ repoOnly invoke when explicitly requested via "产品方向"、"怎么赚钱"、"竞品分析"、"@strategic-product-advisor". Do NOT auto-trigger.
jesse-black/execplan-skills/skills/planner-execplan Skill
3★ repoCreate, update, revise, reopen, or rescope a plan or ExecPlan using `PLANS.md`. Use when an agent needs to create a plan, plan a change, update the plan with new requirements, or rewrite an active ExecPlan.
lianxhcn/PXa2026a/skills/core/04-data-cleaning-planner Skill
no license3★ repoUse this skill when planning or reviewing data cleaning for empirical research. Given a variable list and data dictionary, it drafts a cleaning plan; checks whether a merge/join is sound (1:1 vs m:1, key name/case/type/leading-zero consistency, expected match rate); explains the differences among missing-value handling, outliers, winsorizing, trimming, log transform and standardization; recommends exploratory plots given variable types; explores each table's observation unit, grain, primary key and shape (long/wide) into a review checklist; and plans text-variable extraction without hand-writing regex. Emphasizes judgment and human review; never fabricates data, codebooks, or results.
intelliscale/alphameta-skills/skills/alphameta-options-strategy Skill
3★ repoOptions strategy recommendation via AlphaMeta (IBKR) — selects and explains covered calls, protective puts, straddles, strangles, bull/bear spreads, iron condors, and butterflies based on market view (bullish/bearish/neutral) and IV environment (rich/cheap). Fetches live option chain, IV, Greeks, and max pain to recommend the right strategy with specific legs. Triggers: "期权策略", "备兑开仓", "保护性看跌", "跨式策略", "宽跨式", "牛市价差", "熊市价差", "铁鹰", "蝶式", "期权组合", "买入期权", "卖出期权", "看涨期权", "看跌期权", "options strategy", "covered call", "protective put", "straddle", "strangle", "bull spread", "bear spread", "iron condor", "butterfly", "option strategy", "what option should I", "how to play", "options recommendation".
Eipi-Tong/agentic-coding-starter-kit/.claude/skills/milestone Skill
no license3★ repoClose a feature group as a milestone. Writes docs, proposes E2E tests, and runs a go/no-go gate. Use when the user says "/milestone", "this group is done", or the agent detects all items in a group are complete.
testfree2023/airein/skills/new-plan Skill
3★ repoCreate a new plan directory (P{NNN}-{slug}/) through an interactive, approval-gated document pipeline. Use when starting a new feature, bugfix effort, or architectural change — any work that needs structured tracking across multiple sessions.
testfree2023/airein/skills/tdd Skill
3★ repoSpec-bound TDD for AI agents — bind acceptance tests, implement in vertical slices, prove GREEN, and maintain the plan tests ledger. Use when implementing features, fixing bugs, or refactoring.
EvezArt/evez-skills/skills/tax-strategy-optimizer Skill
no license3★ repoPre-tax vs Roth analysis, charitable giving optimization, capital gains timing, deduction maximization. Not a substitute for CPA.
The same file is in 5 other repositories
m-binimran/creator-pack/skills/engagement-strategy Skill
3★ repoBuild a growth/engagement strategy for Instagram + Facebook - format mix, posting rhythm, hooks, saves/shares optimization, and community tactics - without bait or buying followers. Use for channel growth planning.
madnpc/skills/skills/planning-with-files-zh Skill
no license3★ repo适用于需要跨会话持久追踪的复杂任务、研究或多阶段实施。Use when work needs durable planning, coordination, or progress tracking across multiple steps or sessions. Do not use for small edits, simple explanations, copy changes, styling tweaks, or single-file fixes. 中文关键词:复杂任务、跨会话、任务规划、项目计划、分解任务、多步骤规划、复杂实现、实施计划、进度跟踪、文件规划、拆解项目。
ligyDt/ai-ide-init-template/codebuddy/.codebuddy/skills/experience-specification Skill
3★ repo形成用户流程、信息结构、界面状态、视觉方向、响应式与可访问性验收规格。用于体验设计任务。
ligyDt/ai-ide-init-template/codex/.agents/skills/experience-specification Skill
3★ repo将产品目标转化为可实现和可测试的用户体验规格。用于创建或审查用户流程、信息架构、页面布局、交互状态、视觉方向、响应式行为、可访问性要求及体验验收标准时。
ligyDt/ai-ide-init-template/cursor/.cursor/skills/experience-specification Skill
3★ repo形成用户流程、页面结构、视觉方向、交互状态、响应式和可访问性规格。用于 UI、UX 或视觉交付前。
ligyDt/ai-ide-init-template/trae/.agents/skills/experience-specification Skill
3★ repo定义用户流程、页面结构、视觉方向、交互状态、响应式和可访问性要求。用于体验设计或前端实现之前。
ligyDt/ai-ide-init-template/trae/.trae/skills/trae-project-workflow Skill
3★ repo在 TRAE 项目中编排 Rules、Commands、.agents Skills 以及 SOLO Spec/Plan 工作流。用于需要判断应使用项目规则、斜杠命令、/spec、/plan 或通用研发 Skills 的任务。
tmusser/ai-engineering-skills/skills/checklist-mini Skill
3★ repoValidate a mini-spec before planning.
tmusser/ai-engineering-skills/skills/mini-spec Skill
3★ repoCreate a compact, reference-first SPEC.md that defines the task-specific delta, non-goals, likely failure modes, spec ceiling, and verification target without paraphrasing richer authoritative sources.
tmusser/ai-engineering-skills/skills/thin-plan Skill
3★ repoConvert a mini-spec into 3-7 vertical implementation slices.
rshade/agent-skills/skills/roadmap Skill
3★ repoStrategic roadmap management for GitHub repositories. Syncs ROADMAP.md with GitHub Issues and labels, bootstraps roadmap files from scratch, runs brainstorming sessions with boundary checking, and provides quick status summaries. Use when managing project planning, syncing roadmap state, or exploring feature ideas.
The same file is in 2 other repositories
rshade/agent-skills/skills/tech-debt Skill
3★ repoSystematic technical debt analysis across architecture, testing, documentation, and infrastructure. Investigates the codebase, scores findings by impact and effort, and generates a prioritized TECH_DEBT.md remediation plan. Delegates to specialized skills for code quality (scout) and linting (lint-fix). Use when assessing overall project health, planning cleanup sprints, or onboarding to an unfamiliar codebase.
The same file is in 2 other repositories
jposluns/grc_library/dev-security/claude-rules/skills/pr-retrospective Skill
2★ repoPost-merge retrospective on each successful PR. Surfaces what went well, what caused friction, recurring patterns, and proposed improvements. Output is one entry per PR in the improvement-log register; recurring patterns become candidates for pack-rule updates, worker-brief template additions, or new audit gates. Invoke after `/validate-pr` returns and before the next-PR planning step.
exchanet/method_enterprise_builder_planning/agents/antigravity/.agent/skills/plan-enterprise Skill
2★ repoComplete 8-phase enterprise software planning cycle for mission-critical systems
Method enterprise builder planning
exchanet/method_enterprise_builder_planning/agents/cursor/.cursor/skills/method-enterprise-builder-planning Skill
2★ repo🏗️ Universal 8-phase methodology for planning and building enterprise-grade, mission-critical software with AI coding agents. Supports Cursor AI, Claude Code, Kimi Code, Windsurf & Google Antigravity. Includes ADR validator, microtask linter & CI/CD templates. ≥99% test coverage. MIT.
halflength-ampleness75/claude-code-recipes/skills/testing-strategy Skill
2★ repoProvide ready-to-use Claude Code commands, subagents, hooks, skills, and configs to simplify setup and speed up development.
qte77/claude-code-plugins/plugins/cc-meta/skills/distilling-plan-learnings Skill
2★ repoExtracts decisions, rejected alternatives, and patterns from recent plans into a persistent learnings document. Use after completing a plan or sprint.
qte77/claude-code-plugins/plugins/docs-generator/skills/generating-tech-spec Skill
2★ repoGenerates structured technical specifications including ADR (MADR), RFC, design documents, and proposals. Use when writing a spec, creating an ADR, drafting an RFC, or creating a design document.
The same file is in 1 other repository
qte77/claude-code-plugins/plugins/market-research/skills/developing-gtm-strategy Skill
2★ repoDevelop customer segmentation, channel selection, and a 90-day launch plan from Phase 2 PMF assessment. Run after `validating-product-market-fit` (Phase 3).
Generating prd json from prd md
qte77/claude-code-plugins/plugins/ralph/skills/generating-prd-json-from-prd-md Skill
2★ repoGenerates prd.json task tracking file from PRD.md requirements document. Use when initializing Ralph loop or when the user asks to convert PRD to JSON format for autonomous execution.