Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
18.069 de skill-uri din 635 de depozite · actualizat acum 2 minute
3.489 de skill-uri
- thinking-probabilistictjboudreaux/cc-thinking-skillsUse when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into order-of-magnitude bounds.AlteleFără avertismente★ 1,7 K↓ —
- thinking-reversibilitytjboudreaux/cc-thinking-skillsBefore heavy deliberation, classify the decision as cheap or costly to undo; decide two-way doors fast and stage one-way doors to preserve options.AlteleFără avertismente★ 1,7 K↓ —
- thinking-steel-manningtjboudreaux/cc-thinking-skillsBefore rejecting a proposal or reflexively agreeing, build the strongest faithful opposing case, state agreement conditions, then update or reaffirm.AlteleFără avertismente★ 1,7 K↓ —
- thinking-five-whys-plustjboudreaux/cc-thinking-skillsWhen a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.AlteleFără avertismente★ 1,7 K↓ —
- thinking-jobs-to-be-donetjboudreaux/cc-thinking-skillsDeciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing workarounds.AlteleFără avertismente★ 1,7 K↓ —
- thinking-margin-of-safetytjboudreaux/cc-thinking-skillsWhen provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.AlteleFără avertismente★ 1,7 K↓ —
- thinking-opportunity-costtjboudreaux/cc-thinking-skillsBefore committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.AlteleFără avertismente★ 1,7 K↓ —
- thinking-model-combinationtjboudreaux/cc-thinking-skillsWhen one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.AlteleFără avertismente★ 1,7 K↓ —
- thinking-theory-of-constraintstjboudreaux/cc-thinking-skillsWhen throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.AlteleFără avertismente★ 1,7 K↓ —
- agentsop-prompt-compilationagentsope/SkillAlchemyThe compile-readiness gate for prompt auto-optimization. Decide whether you have earned the right to run an optimizer (DSPy MIPROv2 / GEPA / BootstrapFewShot) before spending compute. Two preconditions only — a real metric, and enough examples for the optimizer you picked. Garbage metric in, garbage prompt out. Pick the optimizer by data scale; GEPA inverts the scale assumption (~10 examples + textual feedback).AlteleFără avertismente★ 445↓ —
- agentsop-framework-selectionagentsope/SkillAlchemyNeutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, not competitors — a real project usually combines DSPy (compile) + LlamaIndex (retrieve) + LangGraph (orchestrate) + vLLM (serve), and you choose ONE per layer, not one to rule all. Use when starting any LLM/agent/RAG project, or whenever the "which framework?" question is asked. Deliberately neutral — unlike vendor docs and the LangChain-biased `framework-selection` on skill.sh, this skill has no horse in the race.AlteleFără avertismente★ 445↓ —
- agentsop-llm-engine-selectionagentsope/SkillAlchemyCross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not "which is fastest". Activates whenever a coder-agent must choose, defend, or migrate a serving runtime.AlteleFără avertismente★ 445↓ —
- matchmakinga5c-ai/babysitterMatchmaking skill for ELO/MMR and skill-based matching.AlteleFără avertismente★ 1,9 K↓ —
- Prismic AutomationComposioHQ/awesome-claude-skillsAutomate headless CMS operations in Prismic -- query documents, search content, retrieve custom types, and manage repository refs through the Composio Prismic integration.AlteleFără avertismente★ 77,7 K↓ —
- director-aia5c-ai/babysitterAI Director skill for pacing control and dynamic difficulty.AlteleFără avertismente★ 1,9 K↓ —
- dialogue-aia5c-ai/babysitterDialogue system skill for branching conversations and response generation.AlteleFără avertismente★ 1,9 K↓ —
- destructiona5c-ai/babysitterDestructible environment skill for fracturing and debris systems.AlteleFără avertismente★ 1,9 K↓ —
- rlhf-systemsa5c-ai/babysitterHuman-feedback-driven model optimization — preference data collection, reward modeling, policy updates, and alignment evaluation.AlteleFără avertismente★ 1,9 K↓ —
- voice-chata5c-ai/babysitterVoice chat skill for echo cancellation and codec optimization.AlteleFără avertismente★ 1,9 K↓ —
- utility-aia5c-ai/babysitterUtility AI skill for scoring functions and decision making.AlteleFără avertismente★ 1,9 K↓ —
- new-albumbitwize-music-studio/claude-ai-music-skillsCreates a new album with the correct directory structure and templates. Use IMMEDIATELY when the user says 'make a new album' or similar, before any discussion.AlteleFără avertismente★ 580↓ —
- Gumroad AutomationComposioHQ/awesome-claude-skillsAutomate Gumroad product management, sales tracking, license verification, and webhook subscriptions using natural language through the Composio MCP integration.AlteleFără avertismente★ 77,7 K↓ —Apare și în 1 alt depozit
- remotion-docsremotion-dev/skillsSearch Remotion documentationOficialAlteleFără avertismente★ 5,6 K↓ —
- tiktok-shop-pricingnexscope-ai/eCommerce-SkillsPricing strategy for TikTok — competitive pricing, commission impact, bundling, discount psychologyAlteleFără avertismente★ 1,2 K↓ —
Apollo Automation
ComposioHQ/awesome-claude-skills
AlteleActualizat 18 sept. 2026
De la autor
Automate Apollo.io lead generation -- search organizations, discover contacts, enrich prospect data, manage contact stages, and build targeted outreach lists -- using natural language through the Composio MCP integration.
Instalare
npx skills add ComposioHQ/awesome-claude-skills --skill 'Apollo Automation' -a claude-code
Se instalează în .claude/skills/Apollo-Automation/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Fără descărcare: licența acestui skill (Fără licență) nu ne permite să-i redistribuim fișierele. Comenzile de instalare le iau direct de pe GitHub.
La ce are acces
Doar instrucțiuniNu am văzut acces la rețeaLicență: fără licență
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 86
Securitate100
Proveniență95
Întreținere85
Licență25
Adopție75
Fișiere (1)
- SKILL.md