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
jpoindexter/product-management-skills/skills/product-prd Skill
0★ repoWrite or critique a lean product brief, PRD, or PR/FAQ that frames the customer, outcome, evidence, risks, constraints, measures, and open decisions before implementation detail. Use when requirements are solution-heavy, scope is unclear, or a team needs an executable product definition.
jpoindexter/product-management-skills/skills/product-prioritization Skill
0★ repoPrioritize product bets under strategic, capacity, evidence, dependency, and risk constraints. Use when a backlog is overloaded, stakeholders compete for priority, a team asks for RICE or scoring, resources must be allocated, or explicit trade-offs and sequencing are required.
jpoindexter/product-management-skills/skills/product-roadmap Skill
0★ repoOperational product-management skills and a /pm router for Codex and Claude.
jpoindexter/product-management-skills/skills/product-strategy Skill
0★ repoDevelop or critique a product strategy by diagnosing the central obstacle, choosing a guiding policy, and defining coherent actions and non-goals. Use when priorities compete, a roadmap lacks rationale, a team has goals but no choices, or a strategy reads like aspirations or a feature list.
hashirventhodi/taskforge-skills/taskforge-refine Skill
0★ repoThe universal entry point of the taskforge workflow - assess whether a task is executable and produce its Specification, or route it. Use whenever the user says to refine, spec, scope, groom, or prepare a taskforge task, asks "what's next for TASK-x", or wants to move a new task forward - and whenever a task's readiness is "refine" (including after escalations or invalidation cascades). Four modes - adopt a well-written task nearly verbatim, elaborate an underspecified one, generate blocking clarification prerequisites, or escalate to taskforge-explore for an architectural decision.
coconilu/token-plan-media-hub/adapters/codex/token-plan-media-hub/skills/token-plan-generate-video Skill
0★ repoSubmit and track an Alibaba Model Studio video-generation job through the local Token Plan Media Hub. Use for text-to-video requests and, only when reported by the Hub, image-to-video or reference-video requests. Do not use for deterministic editing, timeline composition, or an unsupported model capability.
coconilu/token-plan-media-hub/adapters/codex/token-plan-media-hub/skills/token-plan-synthesize-speech Skill
0★ repoSynthesize text into a local audio artifact through Token Plan Media Hub. Use for narration, voice previews, accessibility audio, and system or previously authorized cloned voices. Do not describe multi-line TTS assembly as speech-to-speech.
lubochka/xiigen-mvp-engine/.agents/skills/codex-planning-quality Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
Conversation intent and self reflection
lubochka/xiigen-mvp-engine/.agents/skills/conversation-intent-and-self-reflection Skill
0★ repoClassify the CURRENT message before acting. Prevents six soft failures that the existing Critique-Response Protocol in agent-constitution does NOT catch on its own: answering direct questions late, defensive freeze, defensive self-reflection, action-as-relief drift, attention-budget drift, and entropy tolerance. Extends — does not replace — agent-constitution (Critique-Response, Session Start/End) and authority-chain (binding authority). Use before architect planning, plan review, governance/protocol/skill repair, sub-agent orchestration, or any response to a "why / where / who allowed / why shallow / return to analysis" message.
lubochka/xiigen-mvp-engine/.agents/skills/how-to-prepare-a-plan-skill Skill
0★ repoMaster orchestration skill for preparing plans that Codex can actually execute. Includes 5 core sub-skills + SK-416-430 planning skills. 10 principles (P1-P10) must all be answered before any other planning work. SK-430 NamingConventionsEnforcer added as step 8 — runs before session files are produced. DECISIONS-LOCKED.md is the authoritative source for all architectural decisions.
lubochka/xiigen-mvp-engine/.agents/skills/how-to-prepare-a-plan Skill
0★ repoMaster orchestration skill for preparing plans that Codex can execute. 9-step pipeline. 11 principles (P1-P11). FC-1 through FC-21. D-STACK decisions govern stack coupling. SK-430/431/432 run as steps 8-9. Naming conventions enforced throughout. FLOW-00.1 and FLOW-00.2 are prerequisites for FLOW-01+.
lubochka/xiigen-mvp-engine/.agents/skills/plan-execution-feedback Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.agents/skills/plan-restructure Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.agents/skills/plan-review-skill Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.agents/skills/planning-quality-forward-test Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.agents/skills/planning-skill Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.agents/skills/session-output Skill
0★ repoThe procedure Claude Code follows at the end of every phase, after the gate passes. Produces three artifacts: EXECUTION-LOG (machine-readable), PHASE-COMPLETE (human-readable for Luba), and SESSION-BRIEF (structured for the next web planning session). Never runs if the gate failed. Supports two gate models: absolute (sequential flows) and delta (parallel wave flows). Gate model determined by parallel_wave field in STATE.json.
lubochka/xiigen-mvp-engine/.agents/skills/xiigen-flow-builder Skill
0★ repoSkill for extending XIIGen with new flows (FLOW-32+). Use when: the user wants to add a new flow, define new task types, register new factory interfaces, create flow DAG templates, run BFA cross-flow validation, or plan a new engine extension. Triggers: "new flow", "FLOW-32", "FLOW-33", "add flow", "extend engine", "new task type", "T516", "F1339", "factory interface", "flow template", "flow DAG", "cross-flow", "BFA validation", "backward compatibility", "new family", "engine extension", "fabric resolution", "register factory", "flow specification", "flow design". ALWAYS use this skill when the user references adding capabilities to the engine that involve new flows, task types, or factory families. If the user says "build X feature", this skill teaches how to make the ENGINE generate X — not how to implement X directly.
lubochka/xiigen-mvp-engine/.claude/skills/universal/authority-requirement-binding Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
Conversation intent and self reflection
lubochka/xiigen-mvp-engine/.claude/skills/universal/conversation-intent-and-self-reflection Skill
0★ repoClassify the CURRENT message before acting. Prevents six soft failures that the existing Critique-Response Protocol in agent-constitution does NOT catch on its own: answering direct questions late, defensive freeze, defensive self-reflection, action-as-relief drift, attention-budget drift, and entropy tolerance. Extends — does not replace — agent-constitution (Critique-Response, Session Start/End) and authority-chain (binding authority). Use before architect planning, plan review, governance/protocol/skill repair, sub-agent orchestration, or any response to a "why / where / who allowed / why shallow / return to analysis" message.
lubochka/xiigen-mvp-engine/.claude/skills/universal/phase-planning Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.claude/skills/universal/plan-review Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.claude/skills/universal/plan-self-validation Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
lubochka/xiigen-mvp-engine/.claude/skills/universal/planning-session-startup Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
sairam0424/MindForge/.agent/skills/mindforge-add-phase Skill
0★ repoAdd phase to end of current milestone in roadmap
sairam0424/MindForge/.agent/skills/mindforge-audit-milestone Skill
0★ repoAudit milestone completion against original intent before archiving
sairam0424/MindForge/.agent/skills/mindforge-complete-milestone Skill
0★ repoArchive completed milestone and prepare for next version
sairam0424/MindForge/.agent/skills/mindforge-milestone-summary Skill
0★ repoGenerate a comprehensive project summary from milestone artifacts for team onboarding and review
sairam0424/MindForge/.agent/skills/mindforge-new-milestone Skill
0★ repoStart a new milestone cycle — update PROJECT.md and route to requirements
sairam0424/MindForge/.agent/skills/mindforge-plan-milestone-gaps Skill
0★ repoCreate phases to close all gaps identified by milestone audit
sairam0424/MindForge/.agent/skills/mindforge-plan-phase Skill
0★ repoCreate detailed phase plan (PLAN.md) with verification loop
sairam0424/MindForge/.agent/skills/mindforge-plan-phase_extended Skill
0★ repoUse when you have a spec or requirements for a multi-step task, before touching code
sairam0424/MindForge/.agent/skills/mindforge-system-architecture Skill
0★ repoDesign systems with appropriate complexity - no more, no less. Use when the user asks to architect applications, design system boundaries, plan service decomposition, evaluate monolith vs microservices, make scaling decisions, or review structural trade-offs. Applies to new system design, refactoring, and migration planning.
sairam0424/MindForge/.agent/skills/plan Skill
0★ repoPlan mode: write an actionable markdown plan to .planning/plans/, no execution. Bite-sized tasks, exact paths, complete code.
sairam0424/MindForge/.mindforge/skills/capacity-planning Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/cost-estimation Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/estimation-techniques Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/plan Skill
0★ repoPlan mode: write an actionable markdown plan to .planning/plans/, no execution. Bite-sized tasks, exact paths, complete code.
sairam0424/MindForge/.mindforge/skills/rfc-pipeline Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/stakeholder-communication Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/plugins/mindforge/skills/mindforge-add-phase Skill
0★ repoAdd phase to end of current milestone in roadmap
sairam0424/MindForge/plugins/mindforge/skills/mindforge-audit-milestone Skill
0★ repoAudit milestone completion against original intent before archiving
sairam0424/MindForge/plugins/mindforge/skills/mindforge-complete-milestone Skill
0★ repoArchive completed milestone and prepare for next version
sairam0424/MindForge/plugins/mindforge/skills/mindforge-milestone-summary Skill
0★ repoGenerate a comprehensive project summary from milestone artifacts for team onboarding and review
sairam0424/MindForge/plugins/mindforge/skills/mindforge-new-milestone Skill
0★ repoStart a new milestone cycle — update PROJECT.md and route to requirements
sairam0424/MindForge/plugins/mindforge/skills/mindforge-plan-milestone-gaps Skill
0★ repoCreate phases to close all gaps identified by milestone audit
sairam0424/MindForge/plugins/mindforge/skills/mindforge-plan-phase Skill
0★ repoCreate detailed phase plan (PLAN.md) with verification loop
sairam0424/MindForge/plugins/mindforge/skills/mindforge-plan-phase_extended Skill
0★ repoUse when you have a spec or requirements for a multi-step task, before touching code
sairam0424/MindForge/plugins/mindforge/skills/mindforge-system-architecture Skill
0★ repoDesign systems with appropriate complexity - no more, no less. Use when the user asks to architect applications, design system boundaries, plan service decomposition, evaluate monolith vs microservices, make scaling decisions, or review structural trade-offs. Applies to new system design, refactoring, and migration planning.
nchaugen/tabletest-claude-plugin/skills/spec-by-example Skill
0★ repoClaude Code plugin to help write TableTest-style JUnit tests in Java and Kotlin
rdzehtsiar/agent-skill-auditor/fixtures/compatibility/valid/spec-basic Skill
0★ repoPortable compatibility fixture.
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/representative-corpus/.claude/skills/planning Skill
0★ repoClaude path representative skill.
wamalalawrence/agent-skills/skills/domain-modeler Skill
no license0★ repoDomain modeling workflow that maintains a living glossary of canonical terms (CONTEXT.md) and generates Architecture Decision Records (ADRs) sparingly when a decision is hard to reverse, surprising without context, and the result of a real trade-off. Use when: stress-testing a plan against the project's domain language, sharpening fuzzy terminology, recording architectural decisions, cross-referencing stated behaviour against code, or resolving ambiguous terms before implementation. Collaborates with product-owner for product terminology and scope, software-engineer for technical architecture decisions, and delivery-planner for documenting phase-level architectural choices.
vikynofebriputra-creator/Orkas-Awesome-AgentSkills/education/skills/study-planner Skill
0★ repoAccess a curated library of high-quality agents and modular skills for Orkas and other agent frameworks to accelerate task automation and development.
The same file is in 1 other repository
vikynofebriputra-creator/Orkas-Awesome-AgentSkills/product/skills/marketing-skills/references/free-tool-strategy Skill
0★ repoWhen the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," or "free resource." This skill bridges engineering and marketing — useful for founders and technical marketers.
The same file is in 5 other repositories
vikynofebriputra-creator/Orkas-Awesome-AgentSkills/product/skills/marketing-skills/references/launch-strategy Skill
0★ repoWhen the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' or 'product update.' This skill covers phased launches, channel strategy, and ongoing launch momentum.
The same file is in 5 other repositories
vikynofebriputra-creator/Orkas-Awesome-AgentSkills/product/skills/marketing-skills/references/pricing-strategy Skill
0★ repoWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' or 'monetization.' This skill covers pricing research, tier structure, and packaging strategy.
The same file is in 6 other repositories
vikynofebriputra-creator/Orkas-Awesome-AgentSkills/product/skills/product-prd Skill
0★ repoUse to write or refine a PRD after product demand is reasonably understood and before acceptance criteria, design handoff, engineering breakdown, or implementation planning. Use when the user asks for a PRD, product requirements document, scope definition, engineering-ready requirements, requirements handoff, goals and success metrics, functional requirements, non-functional needs, dependencies, risks, milestones, or open questions.
The same file is in 1 other repository
vikynofebriputra-creator/Orkas-Awesome-AgentSkills/product/skills/product-test Skill
0★ repoUse to turn a PRD section, user story, feature slice, or behavior description into product test scenarios and pass/fail conditions. Use when the user asks for product testing, acceptance criteria, Given/When/Then scenarios, QA-ready scenarios, pass/fail checks, edge cases, error states, non-functional acceptance checks, or story-level verification.
The same file is in 1 other repository
khash89/pbl-builder/.claude/skills/pbl-plan-reviewer Skill
no license0★ repoReview an existing Project Based Learning project plan and return prioritized, specific revisions. Works on PBL Builder plans and on plans written anywhere else — a Word doc, a Google Doc, a pasted outline, a plan from another curriculum. Use when someone asks for feedback on a project plan, wants to know whether a project is 'real PBL', or asks what's weak about a unit they've designed. Trigger phrases: 'review my project plan', 'is this good PBL?', 'what's wrong with this unit', 'critique this project', 'will this work?'. Output: ranked findings, each with the specific fix.