Plan & spec
10,699 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
slalomboy/talking-head-video-suite/skills/short-video-operations-pack/skills/short-video-topic-planning Skill
0★ repoUse when short-video ideas need prioritization by audience relevance, attention, evidence, shootability, conversion distance, and risk.
aoli0919/visual-thinking-skills/skills/diagram-brief Skill
0★ repoWrite a brief for a diagram that explains a concept, system, or workflow.
Demand backward production planning
mahidalhan/openfactory/.agents/skills/demand-backward-production-planning Skill
0★ repoUse when orders, forecasts, ship dates, routings, lead times, WIP, and capacity must be converted into a feasible production plan or when an existing plan no longer matches shop-floor reality.
mahidalhan/openfactory/.agents/skills/material-availability-gate Skill
0★ repoUse when a production plan, customer promise, purchase decision, or stage release depends on material quantity, grade, specification, quality clearance, supplier timing, or an approved substitute.
ahtishamshahzad/agent_dev_flow/.ai/skills/devops/pnpm-workspaces Skill
0★ repoUse to plan a pnpm-workspaces monorepo — workspace layout, internal package linking (workspace protocol), dependency hoisting/isolation policy, versioning of shared packages, and lockfile/CI discipline. Configuration planning; does not scaffold apps.
ahtishamshahzad/agent_dev_flow/.ai/skills/devops/repository-strategy Skill
0★ repoUse to decide how a project's applications are organized into repositories — single repo, monorepo, or multiple repos — based on shared code, coupling, team boundaries, and release cadence. A decision, not a default; feeds monorepo-selection when a monorepo is chosen.
ahtishamshahzad/agent_dev_flow/.ai/skills/devops/rollback-planning Skill
0★ repoUse to plan how to undo a bad deploy fast — previous-artifact redeploy, migration reversibility rulings (roll-forward vs down), feature-flag kill switches, data-safety on revert, clear triggers, and rehearsal. An untested rollback is a hope, not a plan.
ahtishamshahzad/agent_dev_flow/.ai/skills/feature-planning Skill
0★ repoUse to plan a feature work item — scoping new capability within existing (or planned) architecture, defining its phases, tasks, tests, and acceptance criteria without expanding scope. Delegates general phase/task mechanics to task-planning.
ahtishamshahzad/agent_dev_flow/.ai/skills/migration-planning Skill
0★ repoUse to plan a move from one state to another (framework/version/data/schema/infra) safely and incrementally, with a compatibility strategy, per-step verification, a rollback path, and an explicit cutover. Production migrations require approval.
ahtishamshahzad/agent_dev_flow/.ai/skills/mobile/mobile-native-modules Skill
0★ repoUse to plan native module usage or authoring — evaluating existing packages/config plugins first, and planning custom native modules (iOS/Android) only when needed. Prefer Expo config plugins/dev builds before ejecting.
ahtishamshahzad/agent_dev_flow/.ai/skills/refactor-planning Skill
0★ repoUse to plan a behavior-preserving structural improvement — audit the target, ensure test coverage exists, plan small reversible steps, and verify behavior is unchanged. Any intended behavior change is a feature, not a refactor.
ahtishamshahzad/agent_dev_flow/.ai/skills/release-planning Skill
0★ repoUse to validate release readiness and plan a release — tests green, docs and changelog updated, versioning handled, git workflow followed, and any publish/deploy explicitly approved. Enforces Gate 7; never ships on a failed gate.
ahtishamshahzad/agent_dev_flow/.ai/skills/task-planning Skill
0★ repoUse to generate dynamic phases and break them into concrete, verifiable tasks with inputs, outputs, acceptance criteria, and dependencies. Produces the implementation plan approved at Gate 4. Phases are derived from real work, never a fixed template.
ahtishamshahzad/agent_dev_flow/.ai/skills/testing-strategy Skill
0★ repoUse to choose testing levels and tools per application and change, proportional to risk, and to define what "tested" means for the work. Aligns with the approved stack; every bug fix gets a regression test. Honest about what was actually run.
lzx-Bill/Project-Factory-Core/.agents/skills/delivery-planning Skill
0★ repoUse when breaking work into tasks, planning milestones, mapping dependencies, sequencing implementation, or maintaining backlog and in-progress views. Trigger when user says "task breakdown", "milestone", "dependencies", "backlog", "sprint", "implementation plan", "delivery plan", or asks to "break this down into tasks". Coordinate with prompt-authoring for task-to-prompt mapping and with acceptance-design for task-to-acceptance mapping.
lzx-Bill/Project-Factory-Core/.agents/skills/express-incubate Skill
0★ repoUse when the user explicitly wants a fast, one-pass project incubation, such as "快速孵化", "快速出计划", "express plan", "帮我规划一下这个项目". This skill orchestrates the existing Project Factory skills with bounded multi-agent batches, dependency gates, document reviews, execution logging, a final project audit, and one implementation-kit handoff. Do not trigger it for ordinary single-stage planning or when the user requests gradual confirmation at every stage.
lzx-Bill/Project-Factory-Core/.agents/skills/operations-planning Skill
0★ repoUse when documenting deployment, environment layout, monitoring, alerting, rollback, runtime constraints, or operational dependencies. Trigger when user says "deployment", "operations", "monitoring", "rollback", "runtime", "environment", "infrastructure", "SLA", or when preparing for production launch. Coordinate with architecture-decisions for deployment topology and with delivery-planning for operational tasks.
lzx-Bill/Project-Factory-Core/.agents/skills/requirements-spec Skill
0★ repoUse when writing formal functional requirements, non-functional requirements, MVP scope, user stories, constraints, or priorities. Trigger when user says "requirements", "user story", "MVP", "constraints", "priorities", "feature list", "functional specs", or asks to "organize features into backlogs or phases". Coordinate with assumptions-tracking if requirements depend on unconfirmed assumptions.
lzx-Bill/Project-Factory-Core/.agents/skills/test-strategy Skill
0★ repoUse when designing testing strategy for a project — "test strategy", "unit testing", "integration testing", "e2e testing", "test coverage", "mock strategy", "测试策略", "单元测试", "集成测试", "端到端测试". This skill defines the overall testing approach, coverage targets, test pyramid, and specific test cases for critical paths. Use after architecture-decisions and before delivery-planning.
Cartograf666/alex-ter-vibeskills/skills/grill-requirements Skill
0★ repoResolve product, UX, technical, architecture, risk, and scope decisions through a disciplined one-question-at-a-time interview before implementation. Use when the user asks to grill, challenge, stress-test, clarify, interrogate, or pressure-test an idea, PRD, feature, project plan, architecture proposal, or ambiguous development request.
wu1chenghui/hermes-math-template/skills/web-search-strategy Skill
no license0★ repoSearch strategy for web research tasks. TRIGGER on: "search for X", "research X", "look up X", "find information about X", "what is X", "compare X and Y", or any task that needs web information. SKIP on: single fact lookup (just call web_search directly), code debugging, file operations. Use this BEFORE starting any content generation that requires real-world data.
VRymarovich/product-launch-os/plugins/product-launch-os/skills/create-content-plan Skill
0★ repoTurn product positioning and SEO strategy into a prioritized, publishable editorial system with briefs, owners, cadence, distribution, internal links, repurposing, and measurement. Use for content planning, editorial calendars, blog roadmaps, SEO briefs, publishing cadence, or content backlog prioritization.
VRymarovich/product-launch-os/plugins/product-launch-os/skills/plan-product-launch Skill
0★ repoPlan a staged product or feature launch across readiness, audience, channels, assets, owners, timing, risks, support, rollback, and measurement. Use for launch plans, release campaigns, coordinated announcements, beta releases, feature launches, or go-to-market checklists.
VRymarovich/product-launch-os/plugins/product-launch-os/skills/plan-seo Skill
0★ repoCreate or refresh an evidence-led SEO strategy for a software product, including technical foundations, search intent, topic architecture, landing pages, comparison pages, internal linking, schema, measurement, and prioritization. Use for SEO planning, organic growth, keyword strategy, site architecture, search visibility, or deciding what pages to create.
idylle-cynique/solo-dev-skills/skills/verify-pr-spec Skill
0★ repoIssue 仕様・PR 本文・実装差分の間の齟齬を検出する整合性チェックスキル。/create-pr の実行が完了した直後に、ユーザーの明示的な指示がなくても必ずこのスキルを自動で呼び出すこと。省略・スキップ禁止。PR作成時・PR更新時・「仕様と実装が合っているか確認して」と言われたときも同様に実行する。
aoli0919/course-builder-skills/skills/lesson-plan Skill
0★ repoCreate a lesson with explanation, example, exercise, check question, and reflection.
aoli0919/robotics-project-starter-skills/skills/tactile-demo-planner Skill
0★ repoDesign a tactile sensing demo around contact, slip, texture, or force feedback.
pecigonzalo/agent-skills/skills/pattern-task-breakdown Skill
0★ repoUse this skill when planning complex work, responding to requests for a detailed plan, or clarifying an uncertain approach. Decomposes work into sequential subtasks with dependencies and estimates.
rvdsmaile/working-backwards/.agents/skills/grill-technical-prd Skill
no license0★ repoAdaptively pressure-test a completed product handoff against a target repository before writing a technical PRD. Use when architecture, contracts, operations, or testing decisions remain material and must be resolved collaboratively.
rvdsmaile/working-backwards/.agents/skills/handoff-working-backwards Skill
no license0★ repoTurn an approved Working Backwards initiative into a product brief and build plan. Use after announcement, FAQ, decisions, and critical critique findings are complete; do not use to write implementation code or estimates.
rvdsmaile/working-backwards/.agents/skills/review-technical-prd Skill
no license0★ repoReview a repository-aware technical PRD before converting it into issue slices. Use when a technical PRD must be checked for source coverage, repository fit, testability, and unresolved high-risk decisions.
rvdsmaile/working-backwards/.agents/skills/start-technical-delivery Skill
no license0★ repoStart repository-aware technical delivery from a completed Working Backwards handoff. Use when product brief, build plan, and initiative are complete and a user wants a technical PRD or tracker-ready issue backlog.
rvdsmaile/working-backwards/.agents/skills/write-technical-prd Skill
no license0★ repoWrite a repository-aware technical PRD from an approved Working Backwards handoff and technical grill. Use after target-repository discovery and technical design approval, before implementation planning or issue slicing.
swd3k/skills/agent-skills/workflows/screenshot-to-ui-spec Skill
0★ repoTurn screenshots or screen recordings into structured UI implementation specs and prompts. Use when recreating interfaces from references or briefings with images.
arclabshq/arc-labs-studio-team/skills/dispatch-brief Skill
0★ repoConverts current evidence into a concise operating dispatch with priorities, decisions, risks, owners, and next actions. Use for daily or weekly briefs, project updates, leadership summaries, or a focused start-of-session plan.
arclabshq/arc-labs-studio-team/skills/tech-lead Skill
0★ repoGrounds technical decisions in the current codebase, constraints, risks, implementation plan, and verification evidence. Use for architecture, implementation planning, technical review, debugging direction, or delivery readiness.
cleudice/kiro-ai-team/skills/review-spec Skill
0★ repo(Somente reviewer-spec, sessão limpa) Compara o diff do PBI com requirements.md critério a critério — pega requisito esquecido e scope creep. Use quando pedirem 'revisão de requisitos', 'o diff cobre a spec?', 'conferência de conformidade', antes do merge-gate. Também no modo DRAFT (G0): 'revise a spec antes de implementar', 'a spec está pronta pra congelar?' — revisão adversarial de requirements+design ANTES das tasks.
cleudice/kiro-ai-team/skills/write-requirements Skill
0★ repoGera .kiro/specs/<slug>/requirements.md — user stories com critérios EARS testáveis — a partir do brief, perguntando TODAS as ambiguidades antes de congelar. Use ao iniciar o trilho feature, ou quando pedirem 'requisitos', 'spec', 'user stories', 'critérios de aceitação', 'especifique a feature'.
cleudice/kiro-ai-team/skills/write-tasks Skill
0★ repoGera .kiro/specs/<slug>/tasks.md — checklist executável com os gates G1–G5 embutidos no final. Trilho feature (do design) ou manutenção (mínimo, direto do brief). Use quando pedirem 'tasks', 'plano de implementação', 'quebre em tarefas', ou ao fechar a spec.
lhbsaa/apex-discovery/skills/apex-spec Skill
0★ repoSpec-driven development workflow. Propose features with specs, design docs, and tasks before writing code. Triggers on: /apex:spec, propose, write spec, design feature.
lhbsaa/apex-discovery/skills/plan-orchestrate Skill
0★ repoRead a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit ready-to-paste /orchestrate custom prompts. Generative only — never invokes /orchestrate itself. Use when the user has a multi-step plan and wants to drive it through orchestrate without composing chains by hand.
lhbsaa/apex-discovery/skills/prd Skill
0★ repoGenerate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
kimsanguine/signal-to-growth/skills/plan-customer-reach Skill
0★ repoPlan consent-aware customer research recruitment and draft-only outreach without sending messages. Use when defining interview segments, recruiting participants, selecting channels, or preparing 고객 인터뷰 대상자·모집·컨택 초안.
menot-you/n-soul/skills/plan Skill
0★ repoConvert a ratified result into an execution-ready dependency graph whose units a zero-context executor can land without inventing a decision.
NewbieCheng/company-skills-marketplace/plugins/social-media-hotspot-brief/skills/hotspot-brief-public Skill
0★ repoResearch current public web and social-media trends, preserve traceable sources and public metrics, and produce Markdown and structured JSON briefs with content ideas. Use for daily or weekly hotspot reports, keyword trend research, public-source monitoring, content planning, and evidence-based topic selection when private services are unavailable or unnecessary.
pooyagolchian/specforge/plugins/specforge/skills/clarify Skill
0★ repoResolve the open questions and [NEEDS CLARIFICATION] markers in a feature spec before planning. Use when a spec has unresolved unknowns, the user wants to answer clarifying questions, or asks to clarify requirements. Writes a reviewable questions file and folds answers back into spec.md.
pooyagolchian/specforge/plugins/specforge/skills/implement Skill
0★ repoExecute the approved task list to build the feature — the guarded build phase. Use when the user explicitly wants to implement, build, or write the code for a feature whose spec and plan are approved. Code edits are blocked by the SpecForge gate until spec + plan are approved; this skill runs the tasks in order and keeps state in sync.
pooyagolchian/specforge/plugins/specforge/skills/loop Skill
0★ repoAutonomously work through an approved feature's task list one task at a time until done or blocked — SpecForge's governed "Ralph loop". Use when the user wants to auto-run the implementation, loop through remaining tasks, run SpecForge autonomously, or asks for a Ralph loop. Gate-safe: only runs after the spec and plan are approved, and stops (never guesses) on a blocker.
pooyagolchian/specforge/plugins/specforge/skills/plan Skill
0★ repoProduce the technical implementation plan (the HOW) for an approved feature spec. Use when the user wants to plan a feature, design the architecture, decide the tech approach, or move from spec to implementation design. Writes plan.md plus research.md, data-model.md, contracts/, and quickstart.md, and checks the plan against the constitution.
pooyagolchian/specforge/plugins/specforge/skills/quick Skill
0★ repoFast-track a trivial change past the spec-and-plan gate (typo, tiny fix, config tweak, small refactor). Use when the user wants to skip the full lifecycle for a small change, bypass the gate once, or asks to quick-fix something. Turns on fast-track in specforge/state.md so code edits are allowed, and logs it — an audited escape hatch.
pooyagolchian/specforge/plugins/specforge/skills/specify Skill
0★ repoWrite a feature specification (the WHAT and WHY, never the HOW) for a new feature. Use when the user wants to specify a feature, capture requirements, write a spec, define user stories, or start a new feature in SpecForge. Creates specforge/specs/NNN-slug/spec.md, sets it active, and marks unknowns with [NEEDS CLARIFICATION].
pooyagolchian/specforge/plugins/specforge/skills/tasks Skill
0★ repoBreak an approved plan into a concrete, ordered, verifiable task list. Use when the user wants to generate tasks, create a task breakdown, turn the plan into a to-do list, or prepare for implementation. Writes tasks.md with parallel-safe [P] tags and requirement traceability.
blakebauman/skillist-validator/skills/skill-validation Skill
0★ repoValidate agent skills against the Agent Skills specification (agentskills.io) — SKILL.md frontmatter, name and description rules, character limits, directory layout, bundled file references, and progressive disclosure. Use when the user asks to validate, lint, check, or verify a skill or a directory of skills; when they ask whether a SKILL.md is spec-compliant or why a skill fails to load; before publishing or packaging skills; or when they are debugging a skill that an agent will not pick up. Applies to skills for any client — Claude Code, Cursor, Codex CLI, Gemini CLI — not just Claude.
Iu1ky/paper-digger/plugins/paper-digger/skills/paper-digger-plan Skill
0★ repoUse when converting a confirmed idea and venue into falsifiable hypotheses, an experiment matrix, dependencies, and one kill-early test. Triggers on 研究计划, 实验矩阵, experiment plan, 最小验证.
Jorgut/context-quality-suite/skills/strategic-compact Skill
0★ repoSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
ridermw/my-skills/skills/plan-exit-review Skill
0★ repoPortable, self-contained agent skills for Copilot CLI / Claude Code / Cursor. First skill: project-room.
ridermw/my-skills/skills/plan-mega-review Skill
0★ repoPortable, self-contained agent skills for Copilot CLI / Claude Code / Cursor. First skill: project-room.
VJDiPaola/skill-forge/behavior-spec-canvas Skill
0★ repoDefine the behavioral contract for an AI component using a Behavior Spec Canvas covering guardrails, tone, confidence thresholds, and edge cases. Trigger on "how should this behave," "what are the guardrails," "spec out this AI feature," "what should this AI always/never do," or when an eval framework exists and the behavioral rules come next. Based on the "No Vibes, Just Evals" methodology by Shankha Dey.
VJDiPaola/skill-forge/testing-strategy Skill
0★ repoDecide what to test, at which level, and how much. Use when the user asks what tests to write for a feature, whether coverage is adequate, why the test suite is slow or flaky, how to test something hard (time, randomness, external APIs), or to review an existing suite. Trigger on test strategy, what should I test, unit vs integration, flaky test, mocking, coverage, or TDD.
stella-dust/autoxeo-marketplace/skills/autoxeo-content-brief Skill
0★ repoGEO content brief generator — generates structured content briefs optimized for AI citation across Chinese and global AI platforms.