Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
9,277 skills from 267 repositories · updated 14 minutes ago
617 skills
- stakeholder-identificationdeanpeters/Product-Manager-SkillsMap every stakeholder before engaging anyone. Use when launching an initiative, scoping discovery, or building an engagement plan from scratch.PlanningNo warnings★ 7.6K↓ —
- executive-onboarding-playbookdeanpeters/Product-Manager-SkillsPlan a VP or CPO 30-60-90 day diagnostic onboarding path. Use when entering a new executive product role and avoiding premature change.PlanningNo warnings★ 7.6K↓ —
- product-sense-interview-answerdeanpeters/Product-Manager-SkillsStructure a spoken PM product-sense answer with assumptions, segmentation, pain-point prioritization, and MVP tradeoffs. Use when practicing design, improve, or build-next interview questions.PlanningNo warnings★ 7.6K↓ —
- stakeholder-engagement-advisordeanpeters/Product-Manager-SkillsPlan engagement for a specific stakeholder. Use when preparing an outreach, navigating resistance, or aligning a critical relationship before a key milestone.PlanningNo warnings★ 7.6K↓ —
- reflyrefly-ai/reflyBase skill for Refly ecosystem: creates, discovers, and runs domain-specific skills bound to workflows. Routes user intent to matching domain skills via symlinks, delegates execution to Refly backend. Use when user asks to: create skills, run workflows, automate multi-step tasks, or manage pipelines. Triggers: refly, skill, workflow, run skill, create skill, automation, pipeline. Requires: @refly/cli installed and authenticated.PlanningNo warnings★ 7.5K↓ —
- process-analyzera5c-ai/babysitterAnalyze processes, identify workflows, define boundaries and scope, and map process requirements for specialization creation.PlanningNo warnings★ 1.9K↓ —
- finishing-worka5c-ai/babysitterFinal completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.PlanningNo warnings★ 1.9K↓ —
- gsd-toolsa5c-ai/babysitterCentral utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules (commands, config, core, init).PlanningNo warnings★ 1.9K↓ —
- anti-drifta5c-ai/babysitterHierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.PlanningNo warnings★ 1.9K↓ —
- prd-creationa5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationPlanningNo warnings★ 1.9K↓ —
- brainstorminga5c-ai/babysitterClarify vague requirements through exploratory questioning and option generation before committing to research or implementation.PlanningNo warnings★ 1.9K↓ —
- roadmap-managementa5c-ai/babysitterRoadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert (decimal), remove, complete, and requirements coverage analysis.PlanningNo warnings★ 1.9K↓ —
- verification-suitea5c-ai/babysitterPlan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.PlanningNo warnings★ 1.9K↓ —
- planning-patternsa5c-ai/babysitterStructured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.PlanningNo warnings★ 1.9K↓ —
- spec-creationa5c-ai/babysitterFeature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.PlanningNo warnings★ 1.9K↓ —
- self-optimizationa5c-ai/babysitterSONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.PlanningNo warnings★ 1.9K↓ —
- goapa5c-ai/babysitterGoal-Oriented Action Planning skill for world state and action costs.PlanningNo warnings★ 1.9K↓ —
- prd-creationa5c-ai/babysitterBabysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestrationPlanningNo warnings★ 1.9K↓ —
- spec-executiona5c-ai/babysitter6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.PlanningNo warnings★ 1.9K↓ —
- nestjsa5c-ai/babysitterNestJS architecture including modules, dependency injection, guards, interceptors, and microservices patterns.PlanningNo warnings★ 1.9K↓ —
- brainstorminga5c-ai/babysitterUse when starting any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.PlanningNo warnings★ 1.9K↓ —
- openapia5c-ai/babysitterOpenAPI/Swagger specification, code generation, documentation, and validation.PlanningNo warnings★ 1.9K↓ —
- plan-review-gatea5c-ai/babysitterAdversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.PlanningNo warnings★ 1.9K↓ —
- plan-implementationa5c-ai/babysitterDisciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.PlanningNo warnings★ 1.9K↓ —