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
ntaffzii/Skill-Agents/skills/productivity/grill-with-docs Skill
4★ repoPlanning interview skill that asks sharp questions before execution and turns decisions into durable project docs, domain language, PRDs, or ADR notes. Use when the user has an idea, feature, plan, product change, or unclear request that needs alignment before implementation.
Adri3l-R3nan/cognify-skills/.github/skills/change-management-planner Skill
no license4★ repoPlans organizational change initiatives including technology rollouts, process redesigns, and team restructuring. Maps stakeholders, identifies resistance, designs communication plans, and builds adoption strategies with measurable milestones.
Adri3l-R3nan/cognify-skills/.github/skills/client-discovery-interview Skill
no license4★ repoConducts structured discovery interviews for consultants, agencies, and service providers. Guides conversation through problem identification, stakeholder mapping, success criteria definition, budget/timeline scoping, and produces a formatted discovery brief with next steps.
Adri3l-R3nan/cognify-skills/.github/skills/competitive-intelligence Skill
no license4★ repoConducts structured competitive analysis including market positioning, feature comparison, pricing intelligence, SWOT analysis, and strategic recommendations. Use when evaluating competitors, preparing for a sales battle card, planning market entry, differentiating a product, or building a competitive strategy.
Adri3l-R3nan/cognify-skills/.github/skills/operations-audit Skill
no license4★ repoConducts a comprehensive small business operations audit across 8 functional areas: sales, marketing, finance, HR, technology, customer service, supply chain, and leadership. Scores each area using 5 questions rated 1-5, identifies highest-leverage improvements using a prioritization matrix, and produces a 90-day action roadmap.
Adri3l-R3nan/cognify-skills/.github/skills/seo-strategy-analyzer Skill
no license4★ repoAnalyzes website SEO performance, identifies keyword opportunities, audits technical SEO issues, and generates a prioritized action plan with traffic projections. Use when a user wants to improve their search rankings, analyze competitors' SEO, build a content strategy, or audit their website for SEO issues.
Strategic planning facilitator
Adri3l-R3nan/cognify-skills/.github/skills/strategic-planning-facilitator Skill
no license4★ repoFacilitates strategic planning sessions for small to mid-size businesses. Guides through vision/mission refinement, SWOT analysis, goal setting with OKRs, strategic initiative prioritization, and execution roadmap creation.
Dragoon0x/dragoon-skills/skills/autoplan Skill
4★ repoRun /brief, /plan-eng, and /plan-design in one shot to bootstrap a complete sprint plan. All three documents land in .dragoon/plans/ pre-filled with codebase facts. Use when the user wants to spin up a full plan quickly. Defaults to dry-run; pass --apply to write all three files. Run as `node ~/.claude/skills/dragoon/skills/autoplan/scripts/autoplan.js "<idea>"`.
Dragoon0x/dragoon-skills/skills/brief Skill
4★ repoGenerate a structured product brief markdown from a one-line idea, pre-filled with codebase facts (stack, type system, palette, components count) from dragoon.json. Use when the user is starting a new feature, project, or initiative and wants to think through it before coding. Output goes to .dragoon/plans/brief-{slug}-{date}.md. Defaults to dry-run preview; pass --apply to write. Run as `node ~/.claude/skills/dragoon/skills/brief/scripts/brief.js "<idea>"`.
Dragoon0x/dragoon-skills/skills/plan-design Skill
4★ repoGenerate a structured design plan markdown that respects the constraints in dragoon.json (spacing grid, type ratio, palette, font families). Forces a screens-and-flows breakdown, accessibility plan, responsive plan, and design review checklist gated on /critique and /slop. Use after /brief or before any UI work. Output goes to .dragoon/plans/plan-design-{slug}-{date}.md. Defaults to dry-run; pass --apply to write. Run as `node ~/.claude/skills/dragoon/skills/plan-design/scripts/plan-design.js "<idea>"`.
Dragoon0x/dragoon-skills/skills/plan-eng Skill
4★ repoGenerate a structured engineering plan markdown for an idea, pre-filled with codebase facts (stack, dependencies, current critique score) from dragoon.json. Forces a test matrix, edge cases, migration plan, and review checklist. Use after /brief or before any non-trivial feature implementation. Output goes to .dragoon/plans/plan-eng-{slug}-{date}.md. Defaults to dry-run; pass --apply to write. Run as `node ~/.claude/skills/dragoon/skills/plan-eng/scripts/plan-eng.js "<idea>"`.
wicttor/pwrl/pwrl-plan-design Skill
no license4★ repoCreate technical design and implementation unit decomposition for planning workflow.
wicttor/pwrl/pwrl-plan-generate Skill
no license4★ repoChoose tier, render plan from templates, embed learnings, and save to docs/plans/.
wicttor/pwrl/pwrl-plan-research Skill
no license4★ repoPerform local and external research to inform technical design decisions during planning.
wicttor/pwrl/pwrl-plan-scope Skill
no license4★ repoGather context, check learnings, validate domain, and bootstrap requirements for planning workflow.
wicttor/pwrl/pwrl-plan Skill
no license4★ repoCreate structured implementation plans with three tiers (Fast/Standard/Deep). Pure skill pipeline orchestrator—no agent routing.
ThanhNguyxnOrg/blendops/skills/acceptance-criteria-builder Skill
4★ repoTurn a locked 3D brief plus chosen recipe into a measurable acceptance checklist with evidence hooks.
ThanhNguyxnOrg/blendops/skills/asset-fallback-strategy Skill
4★ repoProvide a fallback strategy when an asset is unavailable, over-budget, license-blocked, or style-incompatible — without halting the recipe.
Asset library organization planner
ThanhNguyxnOrg/blendops/skills/asset-library-organization-planner Skill
4★ repoPlan an internal asset library structure (folders, naming, metadata, license tracking, version control) so future recipes find and reuse assets reliably.
Blender asset discovery planner
ThanhNguyxnOrg/blendops/skills/blender-asset-discovery-planner Skill
4★ repoPlan the asset acquisition strategy (procedural, library, generative, photogrammetry) for a Blender scene without installing or executing. Use after the brief, before scene planning.
Blender composition camera planner
ThanhNguyxnOrg/blendops/skills/blender-composition-camera-planner Skill
4★ repoProvide detailed composition and camera planning for product hero outputs.
Blender lighting material planner
ThanhNguyxnOrg/blendops/skills/blender-lighting-material-planner Skill
4★ repoBuild detailed lighting and material direction with portability and caveat handling for Blender/web-3D outputs.
Character portrait scene planner
ThanhNguyxnOrg/blendops/skills/character-portrait-scene-planner Skill
4★ repoPlan a character-portrait scene (subject, pose, expression, wardrobe, framing, lighting, background) before any modeling or render attempt.
Environment establishing shot planner
ThanhNguyxnOrg/blendops/skills/environment-establishing-shot-planner Skill
4★ repoPlan a wide environment / establishing-shot scene (locale, time of day, weather, focal subject, depth, atmosphere) before any modeling or render attempt.
ThanhNguyxnOrg/blendops/skills/intent-to-3d-brief-writer Skill
4★ repoConvert a non-Blender-user's natural-language request into a structured 3D brief (subject, mood, deliverables, constraints, evidence expectations). Use as first step before any planner.
Interior architectural scene planner
ThanhNguyxnOrg/blendops/skills/interior-architectural-scene-planner Skill
4★ repoPlan an interior architectural visualization scene (room layout, furniture, materials, natural + artificial lighting) before any modeling or render attempt.
ThanhNguyxnOrg/blendops/skills/product-grid-scene-planner Skill
4★ repoPlan a multi-product grid scene (e-commerce, catalog, comparison) before any modeling or render attempt; consistent lighting, camera, and grid spacing.
ThanhNguyxnOrg/blendops/skills/product-hero-scene-planner Skill
4★ repoGenerate a complete product-hero scene plan from non-Blender-user intent with explicit assumptions and gates.
Three fiber component shape planner
ThanhNguyxnOrg/blendops/skills/three-fiber-component-shape-planner Skill
4★ repoPlan the React Three Fiber component shape (props, refs, Suspense, useGLTF cache, animation hooks) before delivering a GLB to a web team.
tbc-servicos/dataagile-agent-kit/fluig/skills/plan Skill
4★ repoEscreve plano de implementação para artefatos Fluig. Mapeia arquivos, define tasks com TDD, e salva em docs/fluig/plans/. Acione após /fluig:brainstorm aprovar o design. Próximo passo obrigatório: /fluig:implement.
tbc-servicos/dataagile-agent-kit/protheus/skills/advpl-tlpp-sdd Skill
4★ repoPlan and implement Protheus projects/features with 4 adaptive phases — Specify, Design, Tasks, Execute. Auto-sizes depth based on complexity. Creates atomic tasks with verification criteria, atomic commits, requirement traceability, and persistent memory across sessions. Specific to AdvPL/TLPP + Protheus. Use when: (1) Starting new Protheus projects, (2) Working on existing codebases (map modules, architecture, conventions), (3) Planning features (requirements, design, task breakdown), (4) Implementing with verification and atomic commits, (5) Quick tasks (bug fixes, entry points, config), (6) Tracking decisions/blockers/ideas across sessions, (7) Pausing/resuming work. Triggers on: 'initialize project', 'map codebase', 'specify feature', 'discuss feature', 'design', 'tasks', 'implement', 'validate', 'verify work', 'quick fix', 'pause work', 'resume work'.
tbc-servicos/dataagile-agent-kit/protheus/skills/create-implementation-plan Skill
4★ repoCreate machine-readable implementation plan files for features, refactoring, upgrades, design, architecture, or infrastructure. Use when a user says "create implementation plan", "plan this upgrade", "plan this refactor", or needs a structured, phased plan with requirements, constraints, tasks, and validation criteria saved to the /plan/ directory.
tbc-servicos/dataagile-agent-kit/protheus/skills/implement Skill
4★ repoOrquestra Agent Team para executar o plano ADVPL/TLPP — protheus-implementer (haiku) implementa em worktree isolado, protheus-spec-reviewer (sonnet) verifica spec, protheus-reviewer (sonnet) revisa qualidade. Comunicação bidirecional entre teammates. Gate de compilação via lint. Use após /protheus:plan. Próximo passo: /protheus:deploy.
tbc-servicos/dataagile-agent-kit/protheus/skills/plan Skill
4★ repoDecompõe o design aprovado do brainstorm em tasks concretas para teammates ADVPL. Gera plano tipado com artefatos R[MOD][TYPE][SEQ].prw/.tlpp, gates de lint e testes E2E Playwright (test-web). Use após /protheus:brainstorm.
stephenrogan/augmented-csm/skills/pillar-2-lifecycle-orchestration/lo-milestone-tracker Skill
4★ repoTracks customer progress against defined adoption and lifecycle milestones, flags blockers, and reports on time-to-milestone metrics. Use when asked to track customer milestones, monitor adoption progress, measure time-to-value, build success plans with measurable checkpoints, identify stalled accounts, report on adoption velocity, or when any workflow needs to know whether a customer is on track against their plan. Also triggers for questions about success planning, goal tracking, outcome measurement, or adoption milestones.
stephenrogan/augmented-csm/skills/pillar-3-communication-content/cc-internal-brief-writer Skill
4★ repoCreates internal account briefs, escalation write-ups, and executive summaries for internal audiences. Compiles cross-system data into standardised formats for leadership reviews, cross-functional meetings, and escalation documentation. Adapts content and detail level to the specific audience. Use when asked to write an escalation brief, prepare an internal account summary, create a leadership report on an account, or document an escalation. Also triggers for questions about internal documentation, escalation reports, account status summaries for managers, or cross-functional context documents.
Ra stakeholder change detector
stephenrogan/augmented-csm/skills/pillar-7-relationship-architecture/ra-stakeholder-change-detector Skill
4★ repoMonitors for stakeholder changes at customer accounts including champion departures, new executive hires, reorganisations, and role changes. Detects changes from CRM updates, LinkedIn signals, and engagement pattern shifts. Use when asked to track contact changes, monitor for champion departure, detect reorgs at customer accounts, set up stakeholder change alerts, or when any workflow needs early warning of relationship disruption. Also triggers for questions about contact monitoring, org change detection, stakeholder continuity, or relationship risk from personnel changes.
stephenrogan/augmented-csm/skills/pillar-7-relationship-architecture/ra-stakeholder-mapper Skill
4★ repoTracks customer org charts, contact roles, engagement frequency, and relationship coverage across accounts. Maintains a structured stakeholder map that identifies champions, economic buyers, influencers, and coverage gaps. Use when asked to map stakeholders, track customer contacts, build an org chart, identify relationship gaps, assess stakeholder coverage, or when any workflow needs to know who matters at an account and how recently they have been engaged. Also triggers for questions about contact mapping, multi-threading assessment, stakeholder analysis, single-thread risk, or relationship breadth.
pax-k/build-right/skills/build-right-feature-planning Skill
4★ repoAgent-agnostic skills that turn a fuzzy app idea into evidence-backed AI execution.
fabienjuif/agentic-skills/plugins/fabien-skills/skills/make-plan Skill
3★ repoProduce a plan for a non-trivial task as a self-contained docs/plans/<name>/ directory (CLAUDE.md, README.md, ROADMAP.md, PROMPT.md, changelogs/) so a fresh agent session AND a human can pick it up later. Use whenever asked to "create a plan", "plan this out", or before implementing anything multi-step or architectural.
BytesFromToby/plumbline/skills/foreman Skill
3★ repoReads the spec and produces the blueprint — a step-by-step execution plan for the builder, with a committed test planned for every automated Done-when item. Run after architect, before builder.
BytesFromToby/plumbline/skills/homeowner Skill
3★ repoAutonomous build orchestrator — takes a written brief to verified code without a human gate, sequencing scaffold, architect, foreman, builder, and inspector. Halts and surfaces when a spec has Open Questions, a builder gets stuck, or an inspection fails. The build-mode counterpart to walkthrough (maintain mode).
QBall-Inc/clear/skills/cf-plan Skill
3★ repoManage and view the development plan — status, progress, blockers, phases, and next steps. Use when the user asks about plan status, needs next-step recommendations, wants to create or modify the plan, or asks about phases and milestones.
QBall-Inc/clear/skills/plan-management Skill
3★ repoUse when creating a new development plan from a topic or brief, importing an existing plan YAML, checking plan status, identifying blockers, or getting next-step recommendations.
lantisprime/claude-sdlc/skills/build Skill
3★ repoUse this skill during Phase 4 implementation whenever Claude is about to write or modify code. Validates the work item (requirement ID for new builds, issue ticket for fixes, signed CR for change requests), enforces surgical-edit discipline against the plan's in-scope list, validates code against the tech spec and architecture, validates frontend output against UX specs, and generates unit tests ONLY for functions actually modified in the diff. Coordinates with the surgical-edit, minimal-code, and security-review skills. Triggered by any Edit/Write tool call when a plan file exists.
lantisprime/claude-sdlc/skills/plan Skill
3★ repoUse this skill at the START of every coding task — new builds, bug fixes, and change requests. Classifies the work item, validates it against project scope, produces a high-level estimate, proposes a technology stack, and checks stack compatibility. Writes a plan artifact to .claude/sdlc/plans/ that every downstream phase and hook depends on. Must run before any Edit, Write, or code-generation tool call. Trigger this skill whenever the user says "implement", "fix", "add", "change", "build", "refactor", or references a ticket/requirement ID — even if the request seems small.
lantisprime/claude-sdlc/skills/scoping Skill
3★ repoUse this skill whenever a request is ambiguous, vague, or missing critical information — e.g. "fix the login bug" (which one?), "make this faster" (how fast? measured how?), "add caching" (where? invalidation strategy?). Forces clarification BEFORE planning or coding begins, and writes the clarified scope into the plan artifact. Trigger proactively when a task lacks: a clear trigger condition, an expected behavior, an actual behavior (for bugs), a specific user flow, an environment, or measurable acceptance criteria.
GrayMa77er/tiny-spec/tiny-spec-create Skill
3★ repoStart or update a spec — capture intent and requirements into .spec/<slug>/SPEC.md, optionally bound to a ticket (or ad-hoc). On first run, scaffolds .spec/ and seeds the shared constitution (constitution.md) from a short interview. If a BREAKDOWN.md (from tiny-spec-breakdown) is present, seeds the spec from a chosen story instead of a full interview. Re-run to update an existing spec in place.
GrayMa77er/tiny-spec/tiny-spec-plan Skill
3★ repoTurn the active ticket's SPEC.md into a technical design — produce PLAN.md and harden the shared constitution.md (the constitution). Re-run in update mode to reconcile after a SPEC change.
GrayMa77er/tiny-spec/tiny-spec-prd Skill
3★ repoOptional planning on-ramp — turn a rough product idea into a short PRD through a brief interview, written to PRD.md at the project root. The one skill that works from a blank page. Does not scaffold .spec/, touch the constitution, or carve stories — tiny-spec-breakdown reads PRD.md and decomposes it into Features → Stories. The suite works without it.
GrayMa77er/tiny-spec/tiny-spec-tasks Skill
3★ repoSlice the active ticket's PLAN.md into tasks.md — a flat, ordered checklist of small tasks, each with an acceptance outcome. Executed sequentially by tiny-spec-build. Re-run in update mode to reconcile after a plan change.
raphaelDkhn/worldbuilder/demo Skill
no license3★ repoPlan bottom-up artifacts that test the core hypothesis — landing pages, painted-door tests, click-through prototypes, product screenshots, spec docs, copy. Not production code. Refuses to proceed without a live hypothesis.md. Defines the engagement metric that would confirm or refute the hypothesis. Separates coding from validation signal. Use when asked to "build a demo", "landing page", "prototype this", "painted door test", "MVP spec", "demo my idea", "how do I test this". Proactively invoke this skill (do NOT answer directly) when the user has a hypothesis and wants to run a bottom-up test. Use after /hypothesis. For actual production code, redirect to gstack. (worldbuilder)
raphaelDkhn/worldbuilder/north-star Skill
no license3★ repoFind and refine your guiding domain for the -1 to 0 phase. Interactive expertise × passion × market mapping. Runs napkin $1B market math as an integrated HARD GATE — you cannot proceed to ideation until your chosen domain can plausibly support a venture-scale company. Use when asked to "find my north star", "what should I work on", "I need a direction", "I don't know what to build", "I'm thinking about leaving my job", "help me pick a domain", or "where should I focus". Proactively invoke this skill (do NOT answer directly) when the user describes being lost, in between things, between jobs, exploring, or says they "don't know what to build next". Use before /founder-fit, /idea-shotgun, /hypothesis. (worldbuilder)
aneja5/forge-skills/skills/gtm-strategy Skill
3★ repoUse when user says "go to market", "GTM", "how do we sell this", "find customers", when planning a launch, when defining the ideal customer profile, when designing a pilot program before broad launch, or when a structured sales motion needs to be documented.
aneja5/forge-skills/skills/parallel-execution-strategy Skill
3★ repoUse when 3+ independent tasks are ready in .forge/tasks.yaml and multiple agents will work concurrently, when assessing file-conflict risk before dispatching parallel work, when planning branch and merge sequencing for a sprint, or when prior parallel runs have caused merge nightmares.
aneja5/forge-skills/skills/planning-and-task-breakdown Skill
3★ repoUse when .forge/prd.md and .forge/architecture.md exist and the work needs to be decomposed before implementation, when sizing tasks for a sprint, when mapping dependencies between modules, or when a critical path needs to be identified before parallel work begins.
aneja5/forge-skills/skills/spec-driven-development Skill
3★ repoUse when user wants to write a spec, create a PRD, or plan a new feature before implementation begins, when .forge/idea-brief.md exists and is ready to formalize, when requirements need to be captured before architecture or planning, or when a feature's scope and acceptance criteria need to be documented.
aneja5/forge-skills/skills/testing-strategy Skill
3★ repoUse when defining a project's test approach, when choosing what gets tested at unit vs integration vs e2e level, when setting per-component coverage targets, when reviewing test quality, or when CI is slow / flaky and tests need a strategy reset.
ProjAnvil/MindForge/skills/en/product-management Skill
3★ repoExpertise in product management lifecycle, from ideation to launch. Covers requirements gathering, user story creation, prioritization, and product strategy. Use this skill for product planning, writing PRDs, defining MVPs, or competitive analysis.
The same file is in 1 other repository
mryll/skills/skills/codex-review Skill
3★ repoIterative code review and planning discussion between the local agent and Codex CLI. Orchestrates an automatic back-and-forth debate where both agents discuss findings, architecture decisions, or implementation plans until reaching consensus. Codex CLI runs READ-ONLY and never modifies files; model and reasoning effort come from the user's local Codex config. Supports plan mode: when the local agent has a plan ready, Codex evaluates and iterates on it before implementation, producing an updated consensus plan. Use when the user asks to review with codex, analyze with codex, discuss code with codex, iterate with codex, consult codex, ask codex, review the plan with codex, validate plan with codex, or any Codex CLI request for code review, architecture review, plan review, or implementation strategy. Does NOT trigger on non-code topics like diet, fitness, writing, life decisions, or general strategy; use codex-discuss for those.