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
MAHDTech/agent-skills/skills/review/pr-create-test-plan Skill
0★ repoGenerate a manual test plan for a branch's changes — hands-on verification of real user flows and integration behaviour, not unit-test edge cases. Use when you want a copy-paste test plan a reviewer can run by hand before merging a PR.
MAHDTech/agent-skills/skills/review/rfc-review Skill
0★ repoReview an RFC or design doc for problem clarity (SCQA), compliance, security, and performance, and return the few most important issues. Use when reviewing someone's RFC or design proposal before it's approved.
lucaswychan/quant-paper-agent/.agents/skills/strategy-translate Skill
0★ repoTranslate a user-accepted quantitative replication into a framework-specific event-driven strategy and equivalence tests. Use only after a replication benchmark is complete and explicitly accepted, and when a schema-valid framework contract defines events, strategy callbacks, orders, fills, positions, contract metadata, risk limits, and clock semantics. Produces research or paper-trading code by default; live deployment requires separate operational review.
lucaswychan/quant-paper-agent/quant_paper_skills/skills/strategy-translate Skill
0★ repoTranslate a user-accepted quantitative replication into a framework-specific event-driven strategy and equivalence tests. Use only after a replication benchmark is complete and explicitly accepted, and when a schema-valid framework contract defines events, strategy callbacks, orders, fills, positions, contract metadata, risk limits, and clock semantics. Produces research or paper-trading code by default; live deployment requires separate operational review.
h3y6e/agent-skills/.vendor/skills/change-communication Skill
0★ repoProduce a communication package for a design system change — release notes, migration guide, and team announcement. This produces communication artefacts for changes that have already been decided, NOT the deprecation lifecycle itself. Trigger when someone says: communicate this change, breaking change announcement, how do I tell teams about this, release notes, change log, write the announcement, or anything about communicating an update, release, or breaking change to consuming teams. Do NOT trigger for planning or executing a deprecation — use deprecation-process for that, which includes its own communication plan as part of the full lifecycle.
h3y6e/agent-skills/.vendor/skills/design-to-code-check Skill
0★ repoCheck alignment between a specific design specification and its code implementation — a focused, single-component or single-screen comparison. Trigger when someone says: does this match the design, check implementation, design code alignment, what's different between the design and the build, spec check, implementation review, or anything about comparing a designed component or screen to its coded equivalent. Do NOT trigger for system-wide drift detection across multiple components or teams — use drift-detection for that.
h3y6e/agent-skills/.vendor/skills/interview-me Skill
0★ 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"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.
Mino architecture quality strategy
h3y6e/agent-skills/.vendor/skills/mino-architecture-quality-strategy Skill
0★ repo複数module・data ownership・system-wide trade-off・公開契約・target/transition architecture・migration/recoveryを、product valueと品質scenarioから設計するときに使う。局所class改善、流行architecture選定、単一契約抽出には使わない。
h3y6e/agent-skills/.vendor/skills/planning-and-task-breakdown Skill
0★ 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.
h3y6e/agent-skills/.vendor/skills/spec-driven-development Skill
0★ 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.
h3y6e/agent-skills/.vendor/skills/stakeholder-brief Skill
0★ repoWrite a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design system status to an audience that does not have a design systems background.
h3y6e/agent-skills/.vendor/skills/to-issues Skill
0★ repoBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
h3y6e/agent-skills/.vendor/skills/to-prd Skill
0★ repoTurn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
h3y6e/agent-skills/.vendor/skills/to-spec Skill
0★ 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.
h3y6e/agent-skills/.vendor/skills/to-tickets Skill
0★ 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.
Translate programming language
h3y6e/agent-skills/.vendor/skills/translate-programming-language Skill
0★ repoPlan and execute language-to-language server or application migrations with behavior parity. Use when porting modules, services, APIs, or runtimes between programming languages; generating source-runtime oracles and fixtures; generating migrated parity tests; detecting runtime, standard-library, serialization, numeric, encoding, time, regex, or protocol differences; building temporary compatibility layers; accumulating migration knowledge; benchmarking; shadow testing; canarying; or planning cutover and rollback.
cristianorj22/arthus-harness/core/.claude/skills/spec-keeper Skill
0★ repoAuto-fire when editing files that look like public surfaces (API endpoints, edge functions, migrations, exported clients). Reads Docs/SPEC.md and reminds whether the change needs a SPEC §2 update. Companion to the SDD method documented in Docs/sdd-guide.md.
cristianorj22/arthus-harness/tests/snapshots/full-stack/.claude/skills/spec-keeper Skill
0★ repoAuto-fire when editing files that look like public surfaces (API endpoints, edge functions, migrations, exported clients). Reads Docs/SPEC.md and reminds whether the change needs a SPEC §2 update. Companion to the SDD method documented in Docs/sdd-guide.md.
cristianorj22/arthus-harness/tests/snapshots/minimal/.claude/skills/spec-keeper Skill
0★ repoAuto-fire when editing files that look like public surfaces (API endpoints, edge functions, migrations, exported clients). Reads Docs/SPEC.md and reminds whether the change needs a SPEC §2 update. Companion to the SDD method documented in Docs/sdd-guide.md.
cristianorj22/arthus-harness/tests/snapshots/web-supabase/.claude/skills/spec-keeper Skill
0★ repoAuto-fire when editing files that look like public surfaces (API endpoints, edge functions, migrations, exported clients). Reads Docs/SPEC.md and reminds whether the change needs a SPEC §2 update. Companion to the SDD method documented in Docs/sdd-guide.md.
atkntepe/skillbox/skills/write-codex-goal Skill
0★ repoUse when the user wants to draft or revise a Codex `/goal` prompt, goal instruction Markdown file, durable long-running objective, stopping condition, validation loop, checkpoint plan, progress contract, or background-task brief. Apply when work should persist across many turns with measurable completion; do not use for one-off prompts, loose backlogs, or tasks whose next step depends on frequent unresolved product decisions.
Autter-dev/agentic-sales-skills/01-preparation/pricing/skills/pricing-strategy Skill
0★ repoValue-based pricing analysis with Van Westendorp sensitivity, tier design, competitive positioning, and pricing page recommendations.
Autter-dev/agentic-sales-skills/04-proposals-and-close/skills/proposal-generator Skill
0★ repoGenerates tailored SOW and proposal documents from discovery notes, with pricing options and ROI projections
ultimatile/development-skills/skills/codex-plan-review Skill
no license0★ repoReview an implementation plan with OpenAI Codex before coding, getting a second opinion on assumptions and approach.
xiongxianzhu/xskills/skills/prd-creator Skill
0★ repo根据用户提问生成专业规范的产品需求文档(PRD)。在用户要求创建 PRD、撰写需求文档、起草产品需求或记录项目需求时使用。
tRollNhard/1st/custom-skills/clarifying-questions Skill
no license0★ repoAlways-active skill. Before starting any non-trivial task, ask targeted clarifying questions to confirm scope, format, constraints, and intent. Prevents wasted work from wrong assumptions.
sonhaicoder/haiclaudeskill/skills/code-review Skill
0★ repoCode review skill — find bugs, security issues, anti-patterns BEFORE merge. AUTO-TRIGGER khi: user nói "review/check code/audit/PR review", file vừa changed (git diff), Claude Code spawn reviewer/qa-reviewer agent, hoặc trước khi commit/push. Force apply 6 audit lenses: (1) Security (SQLi/XSS/secrets/auth bypass), (2) Multi-tenant leak (shop_id missing), (3) Money precision (float vs Decimal), (4) Race conditions (read-then-write), (5) State machine violations (order/payment status jumps), (6) API↔frontend boundary mismatch. Plus 27 anti-patterns + 5-dim severity scoring + grep recipes ready-to-run. Distilled từ Commerce Platform 100 commits production patterns. KHÔNG dùng cho: writing new code (use feature skill), planning/architecture (use planner).
sonhaicoder/haiclaudeskill/skills/web-taste Skill
0★ repoAnti-slop web frontend skill — AUTO-TRIGGER mọi web UI task. Force ship Kimi/Lovable-tier quality bằng 3 luật cứng: (1) Turn 1 emit Discovery Form lock brief TRƯỚC khi gen pixel (cho task lớn) hoặc apply quality bar (cho tweak nhỏ), (2) Turn 2 pick 1 trong 5 visual directions deterministic (OKLch palette + font + posture) hoặc extract brand-spec — KHÔNG freestyle, (3) Turn 3+ TodoWrite plan → live updates → 27 anti-pattern checklist + 5-dim critique + quality tier scoring → ship single artifact. AUTO-TRIGGER khi: chạm file .tsx/.jsx/.ts/.vue/.svelte/.astro/.html/.css/.scss/.tailwind, hoặc user nói "build/sửa/render/design/tạo/refactor" + "page/landing/UI/component/storefront/admin/site/web/trang/giao diện/style/theme", hoặc "design như Kimi/Lovable/Linear/Stripe/Apple/Monocle/Vercel/Notion". Bao gồm: 9 references (directions/discovery-form/anti-slop/critique/design-md-format/quality-tiers/hero-patterns/section-blueprints/motion-recipes), 8 starter design systems (Kimi, Lovable, Linear, Stripe, Apple, Monocle, Brutalist, Datadog). Distilled từ open-design (24K stars), taste-skill, impeccable.style, getdesign.md, kimi.com, lovable.dev, huashu-design, guizang-ppt. KHÔNG dùng cho: mobile (Flutter/iOS/Android/RN — dùng mobile-design), backend (API/DB), config/infra (CI/env/docker).
rerelurelu/skillbox/skills/decomposition Skill
0★ repoDecomposes complex tasks into detailed, actionable todos with rich descriptions executable from the description alone. Use when the user has a large task that needs breaking down, asks for a task breakdown, plan, or checklist, or wants to start a new feature with clear milestones.
rysk-tanaka/skills/skills/design-doc-yaml Skill
0★ repo設計内容をYAMLに集約し診断レビューを経て肥大化しないMarkdown設計書を作成 (user)
sanjeevafk/agent-skills/skills/interview-style-doc-building Skill
0★ repoUse when the user wants to build a structured strategic document by answering questions (life priorities, goals docs, framework files, ranked lists, principles, reviews). Interview one question at a time, patch the file after each answer, then re-ask. Not for day planning (use day-plan).
mj-deving/pai-skills/skills/Beads/TopologyPlanner Skill
no license0★ repoChoose the right Beads collaboration topology. USE WHEN deciding between embedded single-clone, shared-remote clones, per-clone remotes, or server mode for concurrent writers.
mj-deving/pai-skills/skills/Frontend/Impeccable/shape Skill
no license0★ repoPlan the UX and UI for a feature before writing code. Runs a structured discovery interview, then produces a design brief that guides implementation. Use during the planning phase to establish design direction, constraints, and strategy before any code is written.
mj-deving/pai-skills/skills/Thinking/ContextEngineering Skill
no license0★ repoStrategic context management for AI agents — 5-level hierarchy, starvation/flooding diagnosis, brain dump structuring, confusion surfacing. USE WHEN context management, context strategy, too much context, too little context, context window, context budget, brain dump, session context, what context to load, context starvation, context flooding, agent context, prompt engineering context.
mj-deving/pai-skills/skills/Thinking/PlanSynthesis Skill
no license0★ repoSynthesize multi-agent outputs into a single templated execution spec. Consumes any combination of Thinking sub-skill and Research outputs. USE WHEN synthesize plan, plan synthesis, merge findings, execution spec, combine analysis, synthesize outputs, make a plan from.
Handling strategic insults and mockery
EdLuxAI/trumps-ten-commandments-skills/handling-strategic-insults-and-mockery Skill
0★ repoUse when you, your group, or someone you advise is being attacked with calculated personal insult, mockery, nickname-branding, or ridicule — not as a loss of temper by the attacker, but as a calibrated political or media tactic. Helps the user recognize the insult playbook and respond in a way that doesn't legitimize it, mirror it, or walk into its trap. Triggers on phrases like "they've given me a nickname that keeps sticking", "I'm being mocked publicly and I don't know how to respond", "the attacks are cruel but also effective", "my allies keep saying 'just ignore it' but it's working on the audience", "they made a joke at my expense and now it's a meme", "how do I fight mockery without looking humorless". Do not use for: legitimate policy critique expressed sharply, comedy at the user's expense without a strategic frame, or ordinary workplace rudeness without public stakes.
Civic-Skills-Lab/civil-resistance-skills/plugins/civil-resistance-communication/skills/4004-marches Skill
no license0★ repoThis skill guides planning for a march as a civil-resistance communication tactic. Consult when a user asks to "plan a march route", "prepare a march with marshals and documentation", "assess march logistics", "build a march planning package", "compare marches against vigils or rallies", or reduce legal, safety, accessibility, narrative, and crowd-control risk around a lawful public procession.
Civic-Skills-Lab/civil-resistance-skills/skills-catalog/4004-marches Skill
no license0★ repoThis skill guides planning for a march as a civil-resistance communication tactic. Consult when a user asks to "plan a march route", "prepare a march with marshals and documentation", "assess march logistics", "build a march planning package", "compare marches against vigils or rallies", or reduce legal, safety, accessibility, narrative, and crowd-control risk around a lawful public procession.
OnestarQQ/Samantha/skills/morning-brief Skill
0★ repo私人订制早报系统。根据用户偏好自动采集相关资讯,每天早上定时发送个性化早报。支持AI资讯、全球新闻、赚钱机会等多维度定制。
antonioshaman/aura-companion/.agents/skills/council-plan Skill
0★ repoArchitect a feature with the Carmack Council before writing code. Use when explicitly asked to plan a feature, do a "council plan", "carmack plan", or invoke /council-plan. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Telegram UX Expert, Backend/Python Expert, Brandur Leach (PostgreSQL/Alembic), systemd/VPS Deploy Expert, Simon Willison (LLM pipeline), Karri Saarinen (UI quality), Vitaly Friedman (UX quality). Interactive feature discovery followed by parallel subagent dispatch. Produces a sequenced, attributed implementation plan with no code. Stack: Python 3.11+ / aiogram 3.x / SQLAlchemy sync / PostgreSQL + Alembic / OpenAI SDK via ProxyAPI.
antonioshaman/aura-companion/.agents/skills/spec-writer Skill
0★ repoGenerate structured software specifications for features, bug fixes, and products. Use when the user wants to create a spec, PRD, feature brief, requirements document, or when starting any new implementation that needs a specification first. Invoke via /spec-writer or when the user says "write a spec", "spec this out", "create a spec", "I need a spec for...", or describes a feature they want to build. Produces adaptive-complexity specs with Job Stories, Gherkin acceptance criteria, and three-tier boundaries. Output is a markdown file ready for agent execution or human review.
hansonkim/agent-skills/skills/requirements-interview Skill
0★ repoSocratic requirements interview for turning vague product, work, operational, or personal task requests into explicit requirements before execution. Use when the user wants to clarify requirements, define a PRD or work brief, explore scope and success criteria, perform an interview before planning, or avoid premature implementation. Produces an editable Interview Ledger plus PRD, ADR candidates, and handoff contract in the user's working language; does not implement, plan execution phases, create final ADRs, or run follow-up work.
dzhokhov/markdown-agent-vault/skills/project-creator Skill
0★ repoCreates a new vault project and the full starter documentation set: plan.md, tasks.md, context.md, log.md, README.md, plus index updates. The agent writes the plan itself using the autonomous LLM-agent planning methodology: Intent Lock, Owner Interaction Policy, milestones with acceptance conditions, Quality Criteria, and Drift Guard. Use when the owner says: "create a project", "start a project", "turn this into a project", "capture this as a project", "set up a project for X", or equivalent wording. Works in two scenarios: the project is extracted from the current conversation, or the owner asks for a new project from scratch. Do not use for meeting processing, parking/resume flows, or ordinary continuation of an existing project.
Llm empty plan controller fallback
kjuhwa/skills-hub/skills/agent-sdk/llm-empty-plan-controller-fallback Skill
0★ repoWhen a planning LLM returns an empty action list, force a deterministic verification action from a priority-ordered fallback list so the agent never spins on "no actions chosen".
kjuhwa/skills-hub/skills/agent-sdk/plan-audit-entry-per-step Skill
0★ repoEmit a structured audit dict on every planning iteration (loop count, tool budget, planned action count, rerouted flag, rerouted reason) and stash it in state so post-mortem analysis can replay every planner decision.
Tool params extract and availability pattern
kjuhwa/skills-hub/skills/agent-sdk/tool-params-extract-and-availability-pattern Skill
0★ repoTools implement is_available(sources) and extract_params(sources) so the agent can decide at plan time whether to include the tool AND automatically bind its inputs from the detected source dict — no per-tool glue code in the planner.
kjuhwa/skills-hub/skills/arch/adaptive-strategy-hot-swap Skill
0★ repoPeriodically re-evaluate candidate strategies/policies against recent data, swap the active one only when a weighted composite score beats the incumbent by a hysteresis threshold — prevents flapping while staying adaptive.
kjuhwa/skills-hub/skills/architecture/uuid-v7-rfc-9562-generation Skill
0★ repoGenerate RFC 9562 compliant UUIDv7 with millisecond timestamp prefix for sortability
Strategy spi list to map autoinject
kjuhwa/skills-hub/skills/backend/strategy-spi-list-to-map-autoinject Skill
0★ repoSpring이 자동 주입하는 List<T>를 생성자에서 Map<Key,T>로 변환해 Strategy를 enum 키로 O(1) 디스패치하는 패턴
kjuhwa/skills-hub/skills/cli/gstack/design-html Skill
0★ 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".
kjuhwa/skills-hub/skills/cli/gstack/plan-ceo-review Skill
0★ 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)
kjuhwa/skills-hub/skills/cli/gstack/plan-design-review Skill
0★ 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)
kjuhwa/skills-hub/skills/cli/gstack/plan-devex-review Skill
0★ 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".
kjuhwa/skills-hub/skills/cli/gstack/plan-eng-review Skill
0★ 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".
Audio codec selection strategy
kjuhwa/skills-hub/skills/codecs/audio-codec-selection-strategy Skill
0★ repoAudio codec selection (Opus) with Dasp/Rubato/SampleRate resampling backends chosen by feature flag.
Hardware codec fallback strategy
kjuhwa/skills-hub/skills/codecs/hardware-codec-fallback-strategy Skill
0★ repoGraceful fallback from hwcodec (NVENC/QSV) to software codecs (VP9/AOM) gated by feature flags + runtime probe.
kjuhwa/skills-hub/skills/configuration/env-driven-strategy-preset Skill
0★ repoExpose one env var that selects a named preset, where each preset is a tuple of behavior weights (innovate / optimize / repair). Default preset is "balanced"; operators swap presets for incident response without touching code.
kjuhwa/skills-hub/skills/configuration/strategy-preset-weight-table Skill
0★ repoWhen an autonomous loop has to pick between multiple intent classes each iteration (innovate / optimize / repair / …), expose them as a small set of named presets with explicit percentage weights, let one env var flip between presets, and document the use-case-per-preset in the same table operators read.
kjuhwa/skills-hub/skills/design/asset-spec Skill
0★ repoGenerate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.
kjuhwa/skills-hub/skills/design/design-html Skill
0★ 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".