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
monikazapisek/design-engineering-playbook/agents/agent-agile-master/skills/metrics-strategist Skill
1★ repoMetrics and OKR strategy — set inspiring Objectives and measurable Key Results, identify One Metric That Matters, distinguish actionable from vanity metrics. Christina Wodtke + Lean Analytics.
monikazapisek/design-engineering-playbook/agents/agent-agile-master/skills/sprint-planning Skill
1★ repoSprint planning ceremony — step-by-step for solo practitioner
Da-loong/agent-skill-os/skills/demo-video-planner Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete demo video planner work with a reliable workflow.
Da-loong/agent-skill-os/skills/dependency-upgrade-planner Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete dependency upgrade planner work with a reliable workflow.
Da-loong/agent-skill-os/skills/prd-writer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete prd writer work with a reliable workflow.
Da-loong/agent-skill-os/skills/refactor-planner Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete refactor planner work with a reliable workflow.
Da-loong/agent-skill-os/skills/roadmap-planner Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete roadmap planner work with a reliable workflow.
Da-loong/agent-skill-os/skills/user-story-mapper Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete user story mapper work with a reliable workflow.
yiyaw-lab/agent-armor/nightshift Skill
1★ repoThe night shift — call it at bedtime. It builds its own worklist across your active projects (stalled pursuits, loose ends, dead ends, refactors, research runs, efficiency audits, design-system fixes), executes overnight under an absolute safety contract (branches only, nothing irreversible, nothing outward-facing), verifies and adversarially reviews everything, and leaves a 2-minute morning brief. Modes: run (default) | plan (show the worklist, don't execute).
vasu-devs/Forge/skills/plan Skill
1★ repoBreak an approved spec or design into a precise, executable implementation plan. Use after the what/why and the shape are agreed, and before writing implementation code for any multi-step task.
nachoal/my-skills/plugins/codex/my-skills/skills/keyword-research Skill
1★ repoRun public-safe DataForSEO keyword research, SERP checks, competitor discovery, backlink opportunity analysis, gap analysis, and SEO brief planning. Use when Codex is asked for keyword research, niche validation, search demand, CPC/difficulty data, competitor domains, content gaps, backlink prospects, SEO topic prioritization, or article briefs using DataForSEO credentials.
nachoal/my-skills/skills/keyword-research Skill
1★ repoRun public-safe DataForSEO keyword research, SERP checks, competitor discovery, backlink opportunity analysis, gap analysis, and SEO brief planning. Use when Codex is asked for keyword research, niche validation, search demand, CPC/difficulty data, competitor domains, content gaps, backlink prospects, SEO topic prioritization, or article briefs using DataForSEO credentials.
impactbrussels/AINativeOS/skills/moat-strategy Skill
1★ repoUse when a founder needs to know what actually defends the company once building is free - when they say "what's my moat", "a competitor could clone this in a weekend", "is my data a moat", "we collect a lot of data", "anyone can rent the same model", "we don't have enough data to compete", "is this defensible", or worries a giant will copy the feature next quarter. Produces a moat thesis (which moat, why durable, what feeds it) and a MOATS-LEDGER entry. Run after measure-ai-native-pmf; feeds capture-learning.
Razaib-khan/ForgeWeave/src/forgeweave/templates/claude/.claude/skills/planner Skill
1★ repoConverts user intent into structured execution plans, including steps, dependencies, risks, and required tools
Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/planner Skill
1★ repoConverts user intent into structured execution plans, including steps, dependencies, risks, and required tools
Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/planner Skill
1★ repoConverts user intent into structured execution plans, including steps, dependencies, risks, and required tools
vladcheck/skills/opsx-spec-validate Skill
1★ repoUse when you need to validate if your openspec artifacts violate any specs defined by openspec.
fengsihao23-eng/shen-hua/skills/persistent-memory Skill
1★ repoShen-Hua project memory manager. Use whenever Codex needs to initialize, read, repair, update, or summarize the project's `.agent/` working memory files, including PROJECT_BRIEF.md, PLAN.md, TASKS.md, LOG.md, DECISIONS.md, HANDOFF.md, and REVIEW_CHECKLIST.md for long-running tasks.
Colacn/agent-pipeline/skills/plan Skill
1★ repoUse when turning analyze outputs into reviewable technical plans with implementation boundaries, risks, validation, and handoff-ready planning outputs. Supports project overlays for domain-specific layering.
agent-k-labs/shipping-skills/skills/product-hunt-launch Skill
1★ repoPlan and execute a Product Hunt launch — timing strategy, 5 tagline options, product description, gallery brief, maker comment, and an hour-by-hour day-of timeline. Use when the user asks to "launch on Product Hunt," "plan my PH launch," "write my PH description," "what's the best day to launch," or mentions Product Hunt at all.
celestialdust/achilles-skills/skills/codebase-design Skill
1★ repoShared vocabulary and method for designing deep modules — a lot of behaviour behind a small interface, at a clean seam, testable through it. Use when planning a module's interface during plan-breakdown, when the user wants to design or improve an interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary. Reach for it BEFORE you write interface signatures into plan.md — designing the seam after the code exists is too late.
celestialdust/achilles-skills/skills/environment-manifest Skill
1★ repoCapture every external thing the autonomous run needs — API keys, MCP servers, services, runtime deps, test fixtures, accounts — as a typed-kind manifest with NO values and NO commands. Use during Spec right after the PRD lands, and again during Plan once slices exist. ALWAYS run this before an AFK/autonomous wave so preflight-readiness can refuse to start on a missing dependency. If you are about to paste a secret value or a check command into a config file, STOP and use this instead.
celestialdust/achilles-skills/skills/idea-refine Skill
1★ repoRefine a raw or half-formed idea into a sharp, buildable concept through structured divergent-then-convergent thinking, always surfacing hidden assumptions and an explicit "Not Doing" list. Use this in the Ideate stage BEFORE Spec whenever an idea is still vague, whenever you are tempted to jump straight to a plan without stress-testing it, or whenever you want to expand options before converging. Refines (and SHARES) intent.md — never write a separate one-pager. Triggers on "ideate", "refine this idea", "help me think through X", "stress-test my plan/idea", or "show/make me options I can react to".
celestialdust/achilles-skills/skills/interview-me Skill
1★ repoExtracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists, or when the user asks what they're missing, wants their blind spots surfaced, or says "quiz me" before committing.
celestialdust/achilles-skills/skills/orchestrator Skill
1★ repoDrives the autonomous Implement→Verify→Review→Ship loop once the human-owned Spec+Plan is signed and STATE.md holds a slice DAG. Use it to run a build AFK — it sorts slices into topological waves, runs each wave's ready slices in parallel (one worktree per slice, disjoint files only), holds a barrier until every slice reaches a TERMINAL state (done/halted/blocked — never just "success"), and ends the run at risk-banded OPEN PRs for async human merge. If you are about to hand-run slices one at a time, check in with the human between waves, dispatch a "reviewer" persona, weaken a frozen test/acceptance to make a gate go green, or merge to main yourself — STOP and use this instead.
celestialdust/achilles-skills/skills/plan-breakdown Skill
1★ repoTHE planner — turns a signed prd.md + research.md into a concrete, agent-executable plan.md. Reach for it the moment Plan starts and someone says "plan this", "break it into tasks", "write the implementation plan", or is tempted to hand the build agent a prose sketch. Produces vertical tracer-bullet slices (each demoable, cross-layer, with an observable checkpoint) where every non-trivial step names its file, line range, code snippet, and test, plus a Blocked-by dependency DAG written into STATE.md. Refuses horizontal layer-by-layer plans and placeholder steps; references codebase-design + api-design, and escalates hard-to-reverse decisions to an ADR.
celestialdust/achilles-skills/skills/spec-grilling Skill
1★ repoUse BEFORE writing any PRD or design doc — whenever the user wants to design a feature from an idea or intent.md, stress-test a design, pin down domain terminology, surface design decisions the user hasn't considered, or record an architectural decision. Interview relentlessly, ONE question at a time, with a recommended answer each. Emits ADRs + CONTEXT.md; never a PRD.
celestialdust/achilles-skills/skills/spec-review Skill
1★ repoUse this LAST in the Spec stage, before the human signs off — a fresh code-cold agent that FIXES the spec instead of listing complaints. You MUST run it after spec-grilling/to-prd/acceptance-criteria/environment-manifest (and frontend-design for UI) land and before the Spec gate. It auto-fixes decidable facts (stray file paths/signatures in prd.md, dangling `see ADR-NNN`, non-verbatim CONTEXT terms, placeholders, embedded secrets/commands in environment.md) and applies-then-inline-flags contestable judgment fixes (coverage gaps, ADR-worthiness, one-feature-or-two), handing back a cleaned spec, not a punch-list.
celestialdust/achilles-skills/skills/to-prd Skill
1★ repoSynthesize the grilled intent + design substrate into a product-altitude prd.md — NO interview, just synthesis of what you already discussed. Reach for this the moment intent.md is pinned and the ADRs are written and you need the dual-audience product spec the whole pipeline reads. STAY at product altitude: reference ADRs by id, use CONTEXT.md terms verbatim, and NEVER paste a file path, signature, or schema into the PRD.
celestialdust/achilles-skills/skills/using-agent-skills Skill
1★ repoThe meta-dispatcher for the achilles-skills suite. Maps any task to the right stage skill and the artifact-chain lifecycle (Ideate → Spec → Plan → Implement → Verify → Review → Ship). Use this FIRST — at the start of every session and whenever you are unsure which skill applies — before writing any plan, spec, or code. Acting without consulting this index is how the wrong skill gets run and the artifact chain gets skipped.
motao123/dev-workflow-kit/planning Skill
1★ repoUse when a task needs scope clarification, acceptance criteria, implementation slicing, dependency mapping, or a verification plan before coding begins. This skill turns fuzzy requests into concrete execution plans.
motao123/dev-workflow-kit/release-rollout-strategy Skill
1★ repoUse when a change is shippable in principle but still needs a safer rollout shape, rollback plan, monitoring checkpoints, or staged release execution strategy.
motao123/dev-workflow-kit/test-strategy-gap-review Skill
1★ repoUse when the main question is whether current verification is sufficient for a change, which test layers are missing, and where the smallest high-value regression protection should be added.
codexskills/agent-forge/skills/planning-and-task-breakdown Skill
no license1★ repoDecomposes spec-driven specifications into small, independently verifiable tasks with explicit dependency ordering, acceptance criteria, effort estimation, and clear ownership. Ensures no task is larger than one day and every task has a definition of done.
codexskills/agent-forge/skills/spec-driven-development Skill
no license1★ repoMandates writing a comprehensive PRD/spec before ANY code is written. Spec must cover objectives, commands, structure, code style, testing strategy, boundaries, success criteria, and be reviewed via spec review gates before implementation begins.
shashankswe2020-ux/flowforge/flowforge/deep_agents/skills/planning-and-task-breakdown Skill
1★ repoBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
The same file is in 9 other repositories
shashankswe2020-ux/flowforge/flowforge/deep_agents/skills/spec-driven-development Skill
1★ repoCreates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
The same file is in 1 other repository
dylanmccavitt/loom/skills/blueprint Skill
1★ repoThe shape owner. Turns current context into a PRD/spec with acceptance criteria, non-goals, and a proof plan, and covers issue decomposition, architecture seams, research spikes, and tracker triage through lenses. Owns the kit's reusable PR, issue, project-doc, and PRD templates. Use for any shape-mode work - specs, breaking work into issues, planning structure, resolving unknowns, or triaging incoming issues.
dylanmccavitt/loom/skills/prospect Skill
1★ repoLands a brand-new idea, feature, or initiative as tracked planning work and creates its tracker home before any spec or issues exist. Use when the user is starting a new idea, feature, or initiative from scratch and wants it captured as planning work before a spec or issues exist.
spacemata/codex-plugins-for-claude-code/plugins/sales/skills/build-competitive-brief Skill
1★ repoBuild a multi-competitor build-competitive-brief report, comparison matrix, and battlecard-style objection package using user-provided materials, optional connector-assisted research, and public evidence.
spacemata/codex-plugins-for-claude-code/plugins/sales/skills/index Skill
1★ repoUse to discover specific skills for the Sales plugin, when it is at-mentioned directly, or for any mentions of potentially relevant work, including: meeting prep or call follow-up; account research, monitoring, or prioritization; internal source finding; competitive briefs; deal strategy; pipeline or forecast review; company or contact enrichment; customer quote retrieval; rep coaching; business cases; sales company research; and CRM or data enrichment workflows.
spacemata/codex-plugins-for-claude-code/plugins/sales/skills/plan-deal-strategy Skill
1★ repoBuild a post-discovery deal strategy pack with a deal map, buying committee map, procurement risk register, and prioritized next actions from grounded deal evidence.
m-binimran/marketing-pack/skills/campaign-brief Skill
1★ repoWrite a campaign brief - objective, audience, message, channels, offer, budget, and success metrics. Use when planning any marketing campaign before producing assets.
m-binimran/marketing-pack/skills/seo-brief Skill
1★ repoBuild an SEO content brief - target keyword, search intent, SERP analysis, outline, and on-page elements - for a writer. Use when planning content to rank, before drafting.
propiter/landing-craft/skills/marketing-strategy Skill
1★ repoTrigger: marketing, positioning, go-to-market, GTM, campaign, launch, sell or position a product, ICP, audience, offer, funnel, channel strategy, posicionamiento, campaña, lanzamiento, vender. Build the strategy BEFORE producing assets — what to say, to whom, where, and why it converts.
aictrl-dev/skills/skills/measurement-plan Skill
1★ repoCreate a measurement plan for a feature using the Goal-Question-Metric (GQM) structure — defines a measurement goal, learning objectives, metrics, and implementation (product analytics events, warehouse tables, event pipeline). Use when user says 'measurement plan', 'GQM', 'goal question metric', 'goal-question-metric', 'measurement goal', 'how do we measure this', 'what metrics for this feature', 'tracking plan', 'analytics requirements', 'how do we know if this works', 'define KPIs for', or when planning a new feature and analytics instrumentation is needed.
aictrl-dev/skills/skills/spec-review Skill
1★ repoReview an engineering issue or specification against repository evidence for ambiguity, missing acceptance criteria, hidden scope, test gaps, and implementation risk. Use when the user says "review this spec", "check issue 123", "is this ready to build", or "find gaps in this ticket".
SylphxAI/skills/skills/agent-planning-system-review Skill
1★ repoDesign or audit the planning and control mechanism of an autonomous agent or multi-step agent workflow, producing an Agent Planning and Control Contract. Use when choosing or evaluating BDI, HTN, partial-order or causal-link planning, Plan-and-Execute, ReAct, receding-horizon control, bounded search, replanning, execution monitoring, or stop conditions. Do not use merely to plan one ordinary task, schedule a current work queue, design agent memory, or review a finished code candidate.
SylphxAI/skills/skills/notification-strategy-review Skill
1★ repoSet product notification strategy across channels, eligibility, frequency caps, personalization, consent, and effectiveness. Use when notification policy is the job. Not one promotional blast and not the full CRM/marketing OS.
Specification control plane standard
SylphxAI/skills/skills/specification-control-plane-standard Skill
1★ repoSpecification lifecycle, work packets, evaluation manifests, telemetry contracts, and exception records. Use when a material capability needs an executable specification and traceable implementation contract. Do not use for a trivial change whose behavior is already unambiguous.
bilbop1/moneyprinter-md/skills/ethical-acquisition Skill
1★ repoTurn a confirmed Offer Brief and Payable Test Plan into a small, policy-compliant acquisition plan with staged human-reviewed assets and a specific approval checkpoint. Use before outreach, a listing, a partnership request, public content, or any buyer-facing acquisition action.
bilbop1/moneyprinter-md/skills/offer-engine Skill
1★ repoConvert confirmed opportunity evidence into a narrow, sellable offer with buyer, outcome, scope, price logic, proof plan, exclusions, and delivery economics. Use before creating outreach, a landing page, proposal, listing, or payable test.
bilbop1/moneyprinter-md/skills/payable-test Skill
1★ repoTurn a confirmed Offer Brief into one ethical, smallest viable paid validation plan with clear payment terms, evidence labels, cost limits, and a specific external-action gate. Use after offer-engine creates an Offer Brief and before acquisition or delivery.
dimsedra/moatcraft-skills/.agents/skills/implementation-tdd Skill
1★ repoExecute artifact-driven TDD implementation on Git feature branches. Strictly follows Red → Green → Refactor discipline, with each phase producing a separate Git commit. Sub-tasks are received from progress-map.md, tests are anchored to spec contracts, and minimal code is the goal. Use when implementing any sub-task, fixing a bug, or addressing code-review findings in Refactor Mode. Do NOT use for spec creation, roadmap planning, or code review.
dimsedra/moatcraft-skills/.agents/skills/progress-mapper Skill
1★ repoGenerate and maintain the living progress map (progress-map.md) by decomposing approved specs into atomic TDD-sized sub-tasks. Acts as the strategic bridge between spec discovery (brand-product-alignment, front-end-designer, backend-architect) and active execution (implementation-tdd). Use when breaking down specs into actionable tasks, refining the roadmap, or tracking iteration progress. Do NOT use for spec creation (use brand-product-alignment / front-end-designer / backend-architect) or for direct implementation (use implementation-tdd).
IvanGomezMartinez/MatStudyLab/.agents/skills/to-spec Skill
1★ repoTurn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
The same file is in 11 other repositories
IvanGomezMartinez/MatStudyLab/.agents/skills/to-tickets Skill
1★ repoBreak a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in a local file, or native blocking links on a real tracker.
The same file is in 3 other repositories
2702207741-dev/agent-skills-pipeline/planning-workflow Skill
1★ repoUse when the user asks to plan a project, roadmap, migration, refactor, release, investigation, multi-step implementation, risky change, or execution sequence and needs phases, dependencies, risks, validation gates, rollback, owners, or next actions.
iurysza/agent-skills/skills/tech-spec Skill
1★ repoProduces implementation-ready technical specifications with concrete contracts, module boundaries, data flows, file changes, and test slices. Use for architecture or implementation handoffs.
leoncuhk/defog/skills/fog-plan Skill
1★ repoTurn a burned-down ledger into a persisted plan ordered by decision volatility — likeliest-to-change first, mechanical work last.