Plan & spec
10,724 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
darbin/claudecraft/plugins/rem-dev-core/skills/rem-review-plan Skill
1★ repoValidate an implementation plan BEFORE code is written. Checks Prior Art claims, plan-contract conformance, breakage and bug-introduction risk, convention compliance, premise-wrong exit. Dispatches domain specialists in parallel, iterates up to 3 rounds, and writes Status back to the plan file so rem-execute knows the state. Distinct from rem-plan (writes the plan) and rem-review-code (reviews the implementation). Use for "review this plan", "check my plan", "validate the plan", "is this plan ready", "pre-execute review", "plan review", or after /rem-plan produces a draft.
goldenprofile/llm-skills/git-commit-planner Skill
1★ repoАнализирует изменения в git и строит план логических атомарных коммитов, чтобы избежать одного монолитного коммита. Используй когда пользователь собирается закоммитить много изменений, просит «разбить на логические коммиты», «атомарные коммиты», «организовать коммиты», или когда в репозитории большое число staged/unstaged/untracked файлов.
goldenprofile/llm-skills/spec-writer Skill
1★ repoПишет проектные документы как Markdown-файлы в трёх режимах: spec (техспецификация — проблема, цели, архитектура, ADR-решения, риски), plan (план реализации — фазы, оценки, зависимости) и brief (записка для CEO без кода и терминов). Заточен под solo-разработчика. Используй когда пользователь просит «напиши спеку», «tech spec», «design doc», «RFC», «запроектируй фичу», «план разработки», «разбей на фазы», «аналитическая записка», «executive summary». Только документ — ничего не исполняет; для документации по коду (README/docstrings/ADR) — см. docs-generator.
goldenprofile/llm-skills/task-decomposer Skill
1★ repoДекомпозиция крупной задачи или фичи на атомарные «агентские» куски: каждый кусок — один заход Claude Code с проверяемым результатом и зелёным (коммитабельным) состоянием в конце. Строит план с целями, DoD, порядком, зависимостями и точками контроля пользователя; разведку отделяет от изменений. Используй когда пользователь говорит «разбей задачу», «декомпозируй», «разбей на подзадачи/этапы», «слишком большая задача», «с чего начать фичу», приносит крупную размытую фичу, или прошлый заход агента забуксовал из-за размера куска. Превратить ОДИН кусок в чистый промт — clarify-prompt; полноценный документ-план с оценками — spec-writer (plan); автономное исполнение фаз через /goal — goal-pipeline.
horizon-foundry/foundry/skills/phase-plan Skill
1★ repoUse when a unit of work is finishing (a PR is about to merge, a phase is complete) and the next unit needs a plan, or when writing any plan file. Writes the next unit's plan while context is warm and indexes it so the next session can resume from it; when there is genuinely no next unit, indexes an honest terminal entry (decision required, awaiting evidence, or no next work selected) instead of a vacuous plan. Not for whole-product master planning or mid-execution task tracking; it writes the handoff at a close.
Asm3r96/wave-driven-dev/skills/wave-planner-claude Skill
1★ repoPlan and execute large multi-step, multi-stack changes with contract-first waves, parallel worker ownership, user approval gates, ordered integration, and final verification/docs updates using Claude Code Agent subagents. Use only when the task spans multiple areas (for example frontend, backend, tests, errors, docs) or has dependency-heavy sequencing.
Asm3r96/wave-driven-dev/skills/wave-planner Skill
1★ repoPlan and execute large multi-step, multi-stack changes with contract-first waves, parallel worker ownership, user approval gates, ordered integration, and final verification/docs updates. Use only when the task spans multiple areas (for example frontend, backend, tests, errors, docs) or has dependency-heavy sequencing.
guntherb7/helm/business/.claude/skills/new-proposal Skill
1★ repoGuided proposal generation. Asks discovery questions, references past pricing, generates document in your voice using writer agent.
guntherb7/helm/business/.claude/skills/weekly-plan Skill
1★ repoMonday strategic planning. Sets 3-5 weekly objectives. Loads retro, project statuses, financial calendar, personal goals.
croftspan/gigo/skills/blueprint Skill
1★ repoBrainstorm and produce approved design briefs. Use when the user has an idea, feature, or task that needs planning — from vague intent to approved design. Hands off to gigo:spec for formal spec and plan writing. Use gigo:blueprint.
croftspan/gigo/skills/spec Skill
1★ repoFormalize an approved design brief into a spec and implementation plan. Self-reviews both, runs Challenger for large tasks. Use after gigo:blueprint produces an approved brief, or when you have your own design brief to formalize. Use gigo:spec.
donatassimkus/claude-ai-skills/skills/brief Skill
1★ repoProduce a short, scannable morning brief for one or more work/life contexts. Delegates email to whichever skill or tool owns the inbox (triage + send-ready drafts) and reads chat, notes/tasks, CRM, calendar, web + search analytics, then synthesizes what happened since the last brief, what needs a decision, what is time-sensitive today, what to watch out for, and 1-3 suggested focus items. Takes a context (fuzzy-matched) and a window (day/week/month). Never sends or deletes; the email stage delegates to the inbox owner (drafts only, reversible archive) or reads the inbox read-only where no such owner exists. Use when the user says /brief, "morning brief", "brief me on <context>", "what do I need to know for <context> today", "catch me up on <context>", "what should I focus on in <context>", or names a context plus a timeframe.
donatassimkus/claude-ai-skills/skills/content-plan Skill
1★ repoPlan a blog content program for a registered site. Turn a broad keyword, or one or more skills, into a validated pillar-and-cluster map and a seeded keyword queue that the blog batch writes from. Each row carries volume, difficulty, search intent, a content format, secondary keywords, People Also Ask questions, SERP features, competitor entities, internal-link targets, and a priority score. Researches demand and SERP intelligence with your keyword and SERP tools, gates against cannibalization and competitor coverage gaps, and ranks by demand x winnability so a low-authority site builds the winnable posts first. Use when the user says /content-plan, "plan blog content for <site>", "build a content map", "turn this skill into blog posts", "what should we write for <site>", "seed the keyword queue", or wants a content or keyword plan before batching. Plans only: it never writes, publishes, or builds engine adapters. Writing a single post, running the batch that writes many, general SEO frameworks, and market research are each a separate step or skill, not this one.
donatassimkus/claude-ai-skills/skills/growth Skill
1★ repoGrowth strategy through marketing channels: funnel analysis, channel prioritization, offer design, MRR planning, weekly planning, acquisition strategy, the Marketing Machine (customer-generated ad system), and objection-to-content mapping. Use when asked for a growth plan, channel strategy, weekly priorities, or why a specific marketing channel is underperforming.
donatassimkus/claude-ai-skills/skills/partnerships Skill
1★ repoStrategic business development, tech partnerships (SaaS integrations), channel partners, co-marketing, resellers, referral partner programme design at scale, co-selling, integration partnerships, affiliate networks at structural level, channel sales, BD strategy. Use when asked about building a partner programme, partner types, how to structure co-sell motions, how to run a reseller channel, or how to design a referral network beyond simple one-off referrals.
donatassimkus/claude-ai-skills/skills/product Skill
1★ repoProduct management, roadmap prioritization, user research, feature scoping, PMF measurement, product metrics, PRDs, and build vs buy decisions. Use when asked about what to build, backlog prioritization, user research, MVPs, or product-market fit. Distinct from pricing and packaging, which decide how the product is sold rather than what gets built, and from market research, which is a separate discipline.
LukeJMadden/Veltrix-skills/skills/business/product Skill
1★ repoProduct management skill — feature prioritisation, roadmap tracking, user feedback synthesis, release notes. Use when tasks involve features, roadmaps, sprints, user feedback, or product decisions.
LukeJMadden/Veltrix-skills/skills/business/strategy Skill
1★ repoStrategic analyst skill — competitor analysis, market positioning, competitive monitoring, opportunity identification. Use when tasks involve competitors, market positioning, strategic decisions, or competitive intelligence.
lennney/gate-all-skills/skills/product/acceptance-criteria Skill
no license1★ repoWrite testable acceptance criteria and acceptance tests for requirements using Given/When/Then, checklist, and rule-based formats. Use when defining the conditions that prove a requirement is correctly implemented.
lennney/gate-all-skills/skills/product/prd-development Skill
no license1★ repoBuild a structured PRD that connects problem, users, solution, and success criteria. Use when turning discovery notes into an engineering-ready document for a major initiative.
lennney/gate-all-skills/skills/product/user-story Skill
no license1★ repoCreate user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions.
YuAICode/ai-skills/skills/slack-to-spec Skill
1★ repo把某个 Slack 频道一段时间内的讨论收敛成一份"可落地需求"spec 文档。用户以 `/slack-to-spec <频道> <时间范围>` 调用时触发。读频道+决策密集的 thread+关联 canvas doc,抽取「需求点 / 决策(含撤销轨迹) / 待定问题」,按固定模板产出结构化、可追溯、能直接喂开发的 markdown。Use when the user wants to turn Slack discussion into a landable requirement/spec.
YuAICode/ai-skills/skills/source-to-spec Skill
1★ repo把 PDF / 飞书文档 / 会议纪要 / 长文本收敛成"可落地需求"spec(与 slack-to-spec 同一套模板)。当用户说"把这份文档/纪要/PDF 整理成需求 / 出个 spec"时触发。抽取需求点、决策(含被推翻方案)、待定问题,产出结构化、可追溯、能直接喂开发的 markdown。
sichengchen/esper/skills/esper-go Skill
1★ repoAdvance the current work stage. If in spec mode, derives an increment plan. If in increment mode, begins implementation.
sichengchen/esper/skills/esper-spec Skill
1★ repoCreate, review, or revise spec files. Opens a spec editing loop that continues until the user advances with `esper:go`.
entpnomad/bootstrapper-toolkit/.claude/skills/content-strategy Skill
no license1★ repoContent and distribution strategy generator for bootstrapped founders. Produces content pillars, 15 specific content ideas with titles, 20 SEO keywords, a 90-day content calendar, channel-specific tactics, and a distribution checklist. Use when user runs `/content-strategy`, asks about "content strategy", "what should I write about", "blog topics", "SEO keywords", "content calendar", "content marketing plan", or needs a concrete content and distribution plan for their product.
entpnomad/bootstrapper-toolkit/.claude/skills/gtm-strategy Skill
no license1★ repoGo-to-market strategy for bootstrapped founders — beachhead selection, GTM motion, channel strategy, message-market fit, funnel design, distribution economics, and concrete launch plan. Use when user runs `/gtm-strategy`, asks about "go to market", "how to reach customers", "distribution strategy", "first customers", "launch plan", "GTM", "channels", "message-market fit", or needs a distribution strategy for a bootstrapped product.
entpnomad/bootstrapper-toolkit/.claude/skills/launch-plan Skill
no license1★ repo30/60/90-day execution roadmap for bootstrapped founders. Synthesizes all prior analysis into a chronological plan with weekly action items, deliverables, decision gates, kill criteria, tools/budget, and phase exit criteria. Best after running dimension skills. Use when user runs `/launch-plan`, asks about "launch plan", "execution roadmap", "what do I do first", "90-day plan", "action plan", "next steps", "how to launch", or needs a concrete step-by-step execution plan.
entpnomad/bootstrapper-toolkit/.claude/skills/venture-sensei Skill
no license1★ repoBrutal, bullshit-free business strategist and mentor for founders. Use when user runs `/venture-sensei`, asks to "critique my startup", "review my business idea", "give me startup advice", "what customer acquisition strategy", "help me create an offer", "validate this idea", or needs strategic business mentorship. Created by the founders of RevenueHunt.com.
ambystechcom/AmbyKit/.agents/skills/amby-plan Skill
1★ repoProduce the technical implementation plan (the HOW) from an approved spec and UI.
ambystechcom/AmbyKit/.agents/skills/amby-specify Skill
1★ repoTurn a feature idea into a spec — user stories, EARS requirements, acceptance criteria.
jp-solumhealth/jpstack/product-insights Skill
1★ repoProduct intelligence for sprint planning, engineering roadmap, and execution priorities. Aggregates feature requests, bug reports, and usage patterns from customer calls (Fireflies), CRM notes (HubSpot), support interactions, and onboarding friction to produce a prioritized backlog and sprint recommendations. Use this skill when the user says "product insights", "sprint planning", "what should we build", "roadmap review", "backlog prioritization", "product roadmap", "engineering priorities", "what are customers asking for", "product sprint", "feature priorities", "bug triage", or any variation of wanting data-driven input for product decisions and engineering execution.
im-shashanks/claude-plugins/shaktra/skills/shaktra-tpm Skill
no license1★ repoTechnical Program Manager workflow — orchestrates design doc creation, user story generation, quality review loops, RICE prioritization, and sprint planning. Entry point for all planning work.
Chrike/coding-agent-skills/skills/plan-work Skill
no license1★ repoLightweight Claude Code skills for daily AI-assisted development workflows.
Chrike/coding-agent-skills/skills/test-strategy Skill
no license1★ repoUse when the primary problem is test design, explicit TDD, test-first or red-green-refactor work, test seams, regression coverage, mocks, assertions, fixtures, or timing and wait strategy, or when a requested change needs a non-obvious test level, seam, regression signal, or acceptance proof. Do not use for generic testing explanations, ordinary implementation, unresolved root-cause diagnosis, unresolved architecture or ownership/interface/dependency-boundary decisions, explicit review or feedback handling, or completed-work readiness review.
KonH/ClaudeTools/plugins/k/skills/plan-review Skill
1★ repoReview a dated plan under docs/specs/ for missing steps, wrong assumptions, or guideline violations before implementation begins.
KonH/ClaudeTools/plugins/k/skills/plan Skill
1★ repoCreate an implementation plan and save it to docs/specs/<YY_MM_DD_HH>_<name>/plan.md, gated by a required constitution check.
KonH/ClaudeTools/plugins/k/skills/specify Skill
1★ repoCapture feature intent and acceptance criteria before planning begins, writing docs/specs/<YY_MM_DD_HH>_<name>/spec.md. Stops for user approval before the plan skill runs.
Yesterday-AI/ytstack/skills/plan-ceo-review Skill
1★ repoChallenge premise, scope, and ambition via four modes: SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, SCOPE REDUCTION. Auto-detects mode: concept-mode reviews a pitch (OFFICE-HOURS.md) before any scaffolding exists; milestone-mode reviews a committed milestone (M###-CONTEXT.md + M###-ROADMAP.md) before slicing. Use concept-mode right after office-hours to stress-test the pitch; use milestone-mode after plan-milestone and before slice-milestone. Thin ytstack wrapper around the vendored gstack plan-ceo-review procedure.
Yesterday-AI/ytstack/skills/plan-eng-review Skill
1★ repoReview execution approach for feasibility, architecture, data flow, edge cases, test coverage, performance, and security risks. Auto-detects mode: concept-mode reviews a pitch (OFFICE-HOURS.md) for technical feasibility before any scaffolding; milestone-mode reviews slice-plans (M###-S##-PLAN.md) before plan-task. Use concept-mode optionally after plan-ceo-review to sanity-check the pitched approach; use milestone-mode after slice-milestone to lock architecture before implementation. Thin ytstack wrapper around the vendored gstack plan-eng-review procedure.
Yesterday-AI/ytstack/skills/plan-milestone Skill
1★ repoPlan the next milestone: goal, exit criteria, rough size. Creates M###-CONTEXT.md and M###-ROADMAP.md. Run after init-project has scaffolded `.ytstack/`, before slice-milestone. Draws the goal from a validated pitch when available (OFFICE-HOURS.md or prior milestones); if no pitch exists yet in greenfield, prefer office-hours first so the milestone is grounded in real demand. Updates STATE.md with the new current_milestone.
Yesterday-AI/ytstack/skills/plan-task Skill
1★ repoFlesh out a single task within the current slice. Reads M###-S##-PLAN.md, picks the next unplanned task, writes M###-S##-T##-PLAN.md with exact file paths + verification steps. Enforces fits-one-context-window rule. Run after slice-milestone, before executing the task.
Yesterday-AI/ytstack/skills/reassess-roadmap Skill
1★ repoAfter a slice completes, review whether the milestone roadmap still fits reality. Reads recent summaries, surfaces deviations, prompts for roadmap changes (add/split/reorder/remove slices). Run at slice boundaries, not mid-slice.
Yesterday-AI/ytstack/skills/slice-milestone Skill
1★ repoBreak the current milestone into slices. Reads M###-ROADMAP.md, asks for slice content until all slices are filled. Creates M###-S##-PLAN.md per slice. Enforces 1-7 tasks per slice (iron rule). Run after plan-milestone, before plan-task.
Yesterday-AI/ytstack/skills/spawn-milestone-team Skill
1★ repoDispatch the current milestone's slices to a Claude Code Agent Team. Each teammate works on a slice in parallel with its own 200k context (replaces GSD's fresh-subprocess-per-task pattern). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and v2.1.32+. Run after slice-milestone + plan-eng-review.
Yesterday-AI/ytstack/vendor/gstack/design-html Skill
1★ repoDesign finalization: generates production-quality Pretext-native HTML/CSS. Works with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review, design review context from /plan-design-review, or from scratch with a user description. Text actually reflows, heights are computed, layouts are dynamic. 30KB overhead, zero deps. Smart API routing: picks the right Pretext patterns for each design type. Use when: "finalize this design", "turn this into HTML", "build me a page", "implement this design", or after any planning skill. Proactively suggest when user has approved a design or has a plan ready. (gstack) Voice triggers (speech-to-text aliases): "build the design", "code the mockup", "make it real".
Yesterday-AI/ytstack/vendor/gstack/openclaw/skills/gstack-openclaw-ceo-review Skill
1★ repoUse when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.
The same file is in 1 other repository
Yesterday-AI/ytstack/vendor/gstack/plan-ceo-review Skill
1★ repoCEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when asked to "think bigger", "expand scope", "strategy review", "rethink this", or "is this ambitious enough". Proactively suggest when the user is questioning scope or ambition of a plan, or when the plan feels like it could be thinking bigger. (gstack)
Yesterday-AI/ytstack/vendor/gstack/plan-design-review Skill
1★ repoDesigner's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Works in plan mode. For live site visual audits, use /design-review. Use when asked to "review the design plan" or "design critique". Proactively suggest when the user has a plan with UI/UX components that should be reviewed before implementation. (gstack)
Yesterday-AI/ytstack/vendor/gstack/plan-devex-review Skill
1★ repoInteractive developer experience plan review. Explores developer personas, benchmarks against competitors, designs magical moments, and traces friction points before scoring. Three modes: DX EXPANSION (competitive advantage), DX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only). Use when asked to "DX review", "developer experience audit", "devex review", or "API design review". Proactively suggest when the user has a plan for developer-facing products (APIs, CLIs, SDKs, libraries, platforms, docs). (gstack) Voice triggers (speech-to-text aliases): "dx review", "developer experience review", "devex review", "devex audit", "API design review", "onboarding review".
Yesterday-AI/ytstack/vendor/gstack/plan-eng-review Skill
1★ repoEng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation. (gstack) Voice triggers (speech-to-text aliases): "tech review", "technical review", "plan engineering review".
Yesterday-AI/ytstack/vendor/gstack/plan-tune Skill
1★ repoSelf-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required. Use when asked to "tune questions", "stop asking me that", "too many questions", "show my profile", "what questions have I been asked", "show my vibe", "developer profile", or "turn off question tuning". (gstack) Proactively suggest when the user says the same gstack question has come up before, or when they explicitly override a recommendation for the Nth time.
yokeloop/yoke/deprecated/plan Skill
1★ repoBuilds an implementation plan from a task file. Triggered when the user writes "build a plan", "make a plan", "plan", "plan the implementation", "prepare a plan", or passes a path to a task file and asks to plan execution.
yokeloop/yoke/skills/issues Skill
1★ repoBreaks a plan, spec, or PRD into independently-grabbable GitHub issues using vertical slices (tracer bullets), publishes them in dependency order, and saves a local index in .yoke/ai. Activates when the user writes "issues", "break into issues", "create tickets", "split into tasks", "decompose into issues", "make implementation tickets", "tracer bullets".
yokeloop/yoke/skills/prd Skill
1★ repoTurns the current conversation and codebase understanding into a PRD, publishes it as a GitHub issue, and saves a local copy in .yoke/ai. Does not interview — synthesizes what is already known. Activates when the user writes "prd", "create a prd", "write a prd", "turn this into a prd", "product requirements doc", "draft requirements".
Ludovic33Fr/product-ai-toolbox/skills/multi-stakeholder-comm Skill
1★ repoUtiliser avant chaque communication transverse importante pour décliner un même sujet en versions calibrées par stakeholder. Produit un encart d'une page par stakeholder, dans le format de prédilection identifié dans la matrice.
Ludovic33Fr/product-ai-toolbox/skills/roadmap-variants Skill
1★ repoUtiliser à chaque révision trimestrielle de roadmap pour simuler trois variantes selon des hypothèses de capacité et de risque. Produit une variante prudente, une variante agressive, une variante équilibrée, comparées ligne à ligne.
Ludovic33Fr/product-ai-toolbox/skills/spec-from-brief Skill
1★ repoUtiliser quand l'utilisateur fournit un brief flou de fonctionnalité et veut une spec testable et exhaustive. Produit une user story INVEST, un scénario nominal Given/When/Then, des scénarios annexes et la liste des questions business non tranchées.
claude-hangar/claude-hangar/core/skills/strategic-compact Skill
1★ repoSuggests optimal moments for /compact based on workflow state and context usage. Proactive context management to prevent quality degradation.
timdevai/proteus/skills/community/from-alireza/business-growth/skills/contract-and-proposal-writer Skill
1★ repoGenerate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, NDAs, and MSAs. Structured Markdown output with docx conversion instructions. Covers US (Delaware), EU (GDPR), UK, and DACH (German law) jurisdictions. Not a substitute for legal counsel — use as strong starting points. Use when drafting a freelance contract, preparing a client proposal, writing an SOW for a new engagement, or producing an NDA before sharing sensitive material.
The same file is in 3 other repositories