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
kjuhwa/skills-hub/skills/design/game-design-doc-review Skill
0★ repoReviews a game design document for completeness, internal consistency, implementability, and adherence to project design standards. Run this before handing a design document to programmers.
kjuhwa/skills-hub/skills/design/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)
Plan to screen spec conversion
kjuhwa/skills-hub/skills/design/plan-to-screen-spec-conversion Skill
0★ repoPLAN 작업지시서를 rules/fe/02-screen-spec-template.md 형식의 화면 스펙 문서로 변환
Retry strategy visualization pattern
kjuhwa/skills-hub/skills/design/retry-strategy-visualization-pattern Skill
0★ repoVisualize retry attempts as timeline tracks with backoff intervals, jitter bands, and terminal outcome markers
Selfcontained nds design doc html
kjuhwa/skills-hub/skills/design/selfcontained-nds-design-doc-html Skill
0★ repo외부 CSS/JS 의존 없이 단일 .html로 완성되는 Lucida/NDS 톤 디자인 문서 템플릿. As-Is/To-Be, 페이지 맥락 목업, 다이얼로그, 인터랙션, API 테이블, MoSCoW Phase 카드 등 10개 섹션 카드로 구성. 메일/Slack/PR에 첨부해도 깨지지 않는 self-contained 아티팩트가 필요할 때 사용.
Gradle jacoco exclusion strategy
kjuhwa/skills-hub/skills/devops/gradle-jacoco-exclusion-strategy Skill
0★ repoCurated Jacoco/Sonar exclusion patterns for Spring Boot projects — skips config/DAO/entity/generated layers and Querydsl Q-classes
Arch spec static polymorphism for codegen
kjuhwa/skills-hub/skills/jit-compilation/arch-spec-static-polymorphism-for-codegen Skill
0★ repoUse a templated `get_best_config<ArchSpec>(desc)` where each architecture (SM90, SM100, etc.) is a plain struct full of `static` methods, so the compiler inlines the arch-specific heuristic with zero virtual-call overhead.
Plan based multi step task decomposition
kjuhwa/skills-hub/skills/llm-agents/plan-based-multi-step-task-decomposition Skill
0★ repoPlan mode for multi-step agent tasks — exploration via subagent, gated planning with user confirmation, strict execution loop, and adversarial verification.
Cycle estimation via bandwidth and wave efficiency
kjuhwa/skills-hub/skills/performance-modeling/cycle-estimation-via-bandwidth-and-wave-efficiency Skill
0★ repoScore kernel config candidates with a closed-form cost model combining L1/L2 bandwidth-limited cycles, compute cycles, and wave-efficiency loss from partial final waves.
kjuhwa/skills-hub/skills/production/milestone-review Skill
0★ repoGenerates a comprehensive milestone progress review including feature completeness, quality metrics, risk assessment, and go/no-go recommendation. Use at milestone checkpoints or when evaluating readiness for a milestone deadline.
kjuhwa/skills-hub/skills/production/sprint-plan Skill
0★ repoGenerates a new sprint plan or updates an existing one based on the current milestone, completed work, and available capacity. Pulls context from production documents and design backlogs.
kjuhwa/skills-hub/skills/production/team-live-ops Skill
0★ repoOrchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
kjuhwa/skills-hub/skills/qa/qa-plan Skill
0★ repoGenerate a QA test plan for a sprint or feature. Reads GDDs and story files, classifies stories by test type (Logic/Integration/Visual/UI), and produces a structured test plan covering automated tests required, manual test cases, smoke test scope, and playtest sign-off requirements. Run before sprint begins or when starting a major feature.
kjuhwa/skills-hub/skills/refactor/request-refactor-plan Skill
0★ repoCreate a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.
Lucida work order to paired spec
kjuhwa/skills-hub/skills/workflow/lucida-work-order-to-paired-spec Skill
0★ repo한 개의 작업지시서(.md)에서 specs/{domain}/planning/*.md 기획서와 specs/{domain}/design/*.html 디자인 목업을 함께 생성하는 워크플로우. 기존 specs/kcm/planning 등의 헤더·메타 관례를 먼저 스캔해 일관성을 맞춘다.
kjuhwa/skills-hub/skills/workflow/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/workflow/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/workflow/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".
kjuhwa/skills-hub/skills/workflow/prd-to-issues Skill
0★ repoBreak a PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Use when user wants to convert a PRD to issues, create implementation tickets, or break down a PRD into work items.
kjuhwa/skills-hub/skills/workflow/prd-to-plan Skill
0★ repoTurn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".
Retry strategy data simulation
kjuhwa/skills-hub/skills/workflow/retry-strategy-data-simulation Skill
0★ repoGenerate synthetic failure streams and retry attempts to stress-test backoff, jitter, and budget policies
Swagger spec baseline from git
kjuhwa/skills-hub/skills/workflow/swagger-spec-baseline-from-git Skill
0★ repoRe-run spec-based optimization workflow on a clean branch without running the Spring Boot app — restore prior baseline artifacts (swagger-before.json + scripts) via `git show <sha>:<path>` from the commit on another branch that already captured them.
kjuhwa/skills-hub/skills/workflow/write-a-prd Skill
0★ repoCreate a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
launchdarkly/experimental-agent-skills/skills/onboardingV2/sdk-install/plan Skill
no license0★ repoGenerate a minimal LaunchDarkly SDK integration plan from detected stack: choose SDK type(s), dual-SDK server+client when required, files to change, env conventions. Nested under sdk-install; follows detect, precedes apply.
The same file is in 1 other repository
floccose-burner9185/wow-harness/reference/towow-snapshot/.claude/skills/plan-lock Skill
0★ repo计划锁定器。把修复计划、实现方案和 WP 规格锻造成 decision-complete 的可执行上游文档:真相先验、决策关死、接口对齐、测试层级一致、时序稳定。在 lead 的 Gate 1 与 Gate 2 之间,以及 task-arch 拆 WP 之前必须使用。
rarexlabs/p11-public/claude-code/skills/share Skill
0★ repoCreate or update shareable, commentable p11 documents. Use when Claude Code should author a polished proposal, brief, report, spec, plan, memo, or review draft and publish it with p11.
The same file is in 2 other repositories
rarexlabs/p11-public/plugins/p11/skills/share Skill
0★ repoCreate or update shareable, commentable p11 documents. Use when Codex should author a polished proposal, brief, report, spec, plan, memo, or review draft and publish it with p11.
LuchoC-Dev/agent-kits/skills/sdd-flow Skill
no license0★ repoSpec-Driven Development workflow for Engram. Trigger: When user requests SDD or multi-phase implementation planning.
LuchoC-Dev/agent-kits/skills/sdd-spec Skill
no license0★ repoWrite specifications with requirements and scenarios (delta specs for changes). Trigger: When the orchestrator launches you to write or update specs for a change.
LuchoC-Dev/agent-kits/skills/sdd-tasks Skill
no license0★ repoBreak down a change into an implementation task checklist. Trigger: When the orchestrator launches you to create or update the task breakdown for a change.
LuchoC-Dev/agent-kits/skills/testing-strategy Skill
no license0★ repoDefine la estrategia de testing — capas de test (unit, integration, e2e), contract testing entre servicios, estrategia de test data y targets de cobertura. Es estrategia, no metodología test-first (eso vive en el pack implementation). Trigger cuando el usuario quiera "estrategia de testing", "qué probar", "tests de integración", "contract testing", "test data", "cobertura" o necesite cerrar cómo se prueba el backend antes de implementar.
oceanfsdfsvfdsvs/practical-agent-skills/workslop-review Skill
0★ repoReview AI-generated workplace drafts before they create downstream rework. Use when a user asks whether an AI-written email, report, brief, PRD, proposal, meeting summary, slide outline, analysis, or handoff is ready to send, needs repair, lacks evidence, contains hallucinated claims, or feels like "workslop".
rbr7/MedClawMini/skills/adhd-daily-planner Skill
0★ repoTime-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.
rbr7/MedClawMini/skills/drug-target-validation Skill
0★ repoComprehensive computational validation of drug targets for early-stage drug discovery. Evaluates targets across 10 dimensions (disambiguation, disease association, druggability, chemical matter, clinical precedent, safety, pathway context, validation evidence, structural insights, validation roadmap) using 60+ MedToolkit tools. Produces a quantitative Target Validation Score (0-100) with GO/NO-GO recommendation. Use when users ask about target validation, druggability assessment, target prioritization, or "is X a good drug target for Y?"
rbr7/MedClawMini/skills/mesh-generation Skill
0★ repoPlan and evaluate mesh generation for numerical simulations. Use when choosing grid resolution, checking aspect ratios/skewness, estimating mesh quality constraints, or planning adaptive mesh refinement for PDE discretization.
The same file is in 3 other repositories
rbr7/MedClawMini/skills/time-stepping Skill
0★ repoPlan and control time-step policies for simulations. Use when coupling CFL/physics limits with adaptive stepping, ramping initial transients, scheduling outputs/checkpoints, or planning restart strategies for long runs.
The same file is in 3 other repositories
SID-SURANGE/cursor-team-ops/skills/community/spec-driven-development Skill
0★ repoWrite a structured specification before touching any code. Use when starting a new feature, facing ambiguous requirements, or when the change touches more than one file. Triggered by "write a spec", "spec this out", "spec-driven", "what should I build", "define this first".
jboczek/skills/skills/to-prd Skill
0★ repoTurn rough feature ideas into concise PRDs for `docs/features/` with lightweight frontmatter, consistent sections, and right-sized scope. Use when creating or revising PRDs, feature specs, or product requirement documents.
mohammaddaoudfarooqi/agent-engineering-skills/skills/spec-driven-tdd Skill
0★ repoSpec-driven test-driven development for AI coding agents. Transforms ambiguous requests into verified implementations through structured specs, derived tests, and strict TDD. Verifies on two axes: coverage and realism (smoke tier, mock-parity, boundary inventory, phase-end demo). Handles greenfield, brownfield, refactors, and complex bug fixes. Use when the user requests a new feature, module, refactor, API, CLI tool, or system with multiple requirements, edge cases, or unclear specs, or for complex bug fixes needing root cause analysis. Triggers on phrases like "add a feature", "implement", "refactor", "fix this bug", "write tests for", "TDD", "test-first", "spec this out", or "mock parity", and when modifying code with adjacent test files or test config. Also triggers on mentions of edge cases, invariants, acceptance criteria, or EARS. Do NOT use for one-line fixes, cosmetic changes, formatting, renames, dependency bumps, or tasks already fully specified with tests provided.
fengluisobel/ask-dongfeng-hermes/skills/software-development/ask-dongfeng Skill
0★ repoFramework workflow skill for replacing or wrapping spec, planning, superpowers-style writing-plans, spike, and review-gate workflows. Use when a user wants to turn an ambiguous goal, product idea, workflow, project, research spike, or implementation plan into a DongFeng Packet: selected operating mode, reviewable control artifact, execution contract, sensors, comparators, controllers, feedback cadence, human gates, and next prompts/actions.
fengluisobel/ask-dongfeng-hermes/skills/software-development/plan Skill
0★ repoPlan mode: write markdown plan to .hermes/plans/, no exec.
ujffdi/specpowers-flow/skills/specpowers-build Skill
0★ repoUse as stages 6-7 of specpowers-flow — execute the approved plan test-first (subagent-driven per task recommended, inline single-context supported) with no silent scope expansion, then verify the implementation complies with the hardened spec via independent adversarial review.
ujffdi/specpowers-flow/skills/specpowers-plan Skill
0★ repoUse as stages 4-5 of specpowers-flow — write the implementation plan into tasks.md from the hardened spec, then build and check the requirement coverage matrix before any code is written.
ujffdi/specpowers-flow/skills/specpowers-spec Skill
0★ repoUse as stages 2-3 of specpowers-flow — generate OpenSpec artifacts from the approved proposal, then harden them via validation and independent adversarial review.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/Boom5426__Nature-Paper-Skills/skills/core/figure-planner Skill
no license0★ repoUse when designing, restructuring, or auditing manuscript figures and you need to define one main claim per figure, assign panel roles, align legends with the text, or decide what belongs in main figures versus supplement.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/andrehuang__research-companion/codex-skills/research-companion Skill
no license0★ repoStrategic research companion for Codex. Use when the user wants to brainstorm research directions, evaluate ideas, assess project strategy, or run a structured ideation session from vague topic to pursue/park/kill decision.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/flonat__claude-research/skills/strategic-revision Skill
no license0★ repoUse when you receive referee comments for a paper (R&R, revise-and-resubmit) and need a DAG-validated revision master plan — atomic task extraction, dependency mapping, computational critical-path analysis, execution blocks, venue strategy. Merges /parse-reviews ingestion with Sihvonen's strategic-revision architecture.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/jkitchin__skillz/skills/productivity/planning Skill
no license0★ repoStructured planning and project breakdown using proven methodologies for goals, projects, and strategic initiatives. Use when users need to create plans, break down complex projects, set milestones, estimate timelines, identify dependencies, or develop action plans. Triggers include 'help me plan,' 'create a roadmap for,' 'break down this project,' 'what are the steps to,' or 'how should I approach.'
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/lingzhi227__agent-research-skills/skills/atomic-decomposition Skill
no license0★ repoDecompose research ideas into atomic, self-contained concepts with bidirectional math-code mapping. For each concept, extract the math formula from papers and find code implementations. Use for complex system papers requiring formal grounding.
The same file is in 1 other repository
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/lingzhi227__agent-research-skills/skills/experiment-design Skill
no license0★ repoDesign experiment plans with progressive stages — initial implementation, baseline tuning, creative research, and ablation studies. Plan baselines, datasets, hyperparameter sweeps, and evaluation metrics. Use when planning experiments for a research paper.
The same file is in 1 other repository
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/lingzhi227__agent-research-skills/skills/research-planning Skill
no license0★ repoDesign research plans and paper architectures. Given a research topic or idea, generate structured plans with methodology outlines, paper structure, dependency-ordered task lists, UML diagrams, and experiment designs. Use when starting a new research project or paper.
The same file is in 1 other repository
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/luwill__research-skills/research-proposal Skill
no license0★ repoGenerate academic research proposals for PhD applications. Use when user asks to "write a research proposal", "create PhD proposal", "generate research plan", "撰写研究计划", "写博士申请", "doctoral proposal", or mentions specific research topics for PhD application. Supports STEM, humanities, and social sciences with field-specific adaptations. Follows Nature Reviews-style academic writing conventions. Supports both English and Chinese output based on user preference.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/pur3v4d3r__pur3-pkb-codebase/.claude/skills/chunking-strategy Skill
no license0★ repoImplement optimal chunking strategies in RAG systems and document processing pipelines. Use when building retrieval-augmented generation systems, vector databases, or processing large documents that require breaking into semantically meaningful segments for embeddings and search.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/rand__cc-polymath/skills/discover-product Skill
no license0★ repoAutomatically discover product management skills when working with product management, roadmap, user stories, prioritization, metrics, or product strategy. Activates for product development tasks.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/ablation-planner Skill
no license0★ repoUse when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission. Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements.
The same file is in 2 other repositories
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/experiment-plan Skill
no license0★ repoTurn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.
The same file is in 1 other repository
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/figure-spec Skill
no license0★ repoGenerate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.
The same file is in 1 other repository
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/grant-proposal Skill
no license0★ repoDraft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/paper-plan Skill
no license0★ repoGenerate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/paper-writing Skill
no license0★ repoWorkflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → figure-spec/paper-illustration/mermaid-diagram → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished PDF. At `— effort: max | beast` (or explicit `— assurance: submission`), Phase 6 gates the Final Report on `tools/verify_paper_audits.sh`; the PDF is labelled `submission-ready` only when the external verifier is green. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.