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.
45.604 skill-uri din 2.205 depozite · actualizat acum 9 ore
9.755 de skill-uri
- hidden-agendasitseffi/agentic-osIdentify potential hidden agendas of stakeholders. Use before high-stakes meetings with complex motivations.AlteleFără avertismente★ 117↓ —
- ost-target-selectionitseffi/agentic-osSelect one target opportunity from an OST using evidence-based weighted scoring and tie-breakers.AlteleFără avertismente★ 117↓ —
- delivery-probe-libraryzby/commonplaceIndex of the delivery-probe library. Use when the user asks to follow, run, or look up a delivery-probe procedure, instruction, or type by name (for example "retire a widget" or "calibrate the gadget").AlteleFără avertismente★ 91↓ —
- analyzing-mempooljeremylongshore/tons-of-skills-marketplaceMonitor blockchain mempools for pending transactions, gas analysis, and MEV opportunities. Use when analyzing pending transactions, optimizing gas prices, or researching MEV. Trigger with phrases like "check mempool", "scan pending txs", "find MEV", "gas price analysis", or "pending swaps".AlteleFără avertismente★ 2,9 K↓ —
- cp-skill-validatezby/commonplaceRun deterministic validation on KB artifacts, collections, collection landings, and the published redirect map, including schemas, links, required sections, and batch signals.AlteleFără avertismente★ 91↓ —
- ReasoningBank Intelligencespencermarx/open-code-reviewImplement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.AlteleFără avertismente★ 380↓ —
- problem-structuringitseffi/agentic-osBreak down complex problems into actionable recommendations using deductive and inductive analysis.AlteleFără avertismente★ 117↓ —
- podium-authjeremylongshore/tons-of-skills-marketplaceAuthenticate production Podium integrations and survive the auth-side failures — OAuth2 access-token expiry storms, refresh-token decay after 90 days of non-use, scope drift on re-grant, secret rotation without downtime, multi-tenant token routing, leakage in commits. Use when hardening token caching, building a refresh-token decay monitor, rotating Podium client credentials, or recovering from 401/403 auth cascades. Trigger with "podium auth", "podium oauth", "podium token refresh", "podium scope drift", "podium credential rotation", "podium multi-location auth".AlteleFără avertismente★ 2,9 K↓ —
- no-manifestalvin-reyes/better-agentic-ideBetter Agentic Development EnvironmentAlteleFără avertismente★ 85↓ —
- nopus-configureVistyy/nopusConfigure nopus complexity sensitivity, extra-simple rewrites, rewrite evidence, and Pi response hiding for this user.AlteleFără avertismente★ 299↓ —
- bmad-old-thingalvin-reyes/better-agentic-ideBetter Agentic Development EnvironmentAlteleFără avertismente★ 85↓ —
- assumption-mappingitseffi/agentic-osSurface and categorize assumptions underlying product strategy. Use early in development to document what you're betting on.AlteleFără avertismente★ 117↓ —
- otel-telemetry-emissionsollygarden/opentelemetry-agent-skillsVersion-pinned inventory of the telemetry (spans, metrics, logs, attributes) emitted by OpenTelemetry collector components and SDK instrumentation packages. Use when working with a covered component — what it emits at a given version, or how emission changed across versions — and when upgrading a component or SDK version, to see the telemetry after the change.AlteleFără avertismente★ 116↓ —
- simpo-losscxcscmu/SkillLearnBench[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.AlteleFără avertismente★ 91↓ —
- stream-chainspencermarx/open-code-reviewStream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflowsAlteleFără avertismente★ 380↓ —
- AgentDB Learning Pluginsspencermarx/open-code-reviewCreate and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.AlteleFără avertismente★ 380↓ —
- V3 MCP Optimizationspencermarx/open-code-reviewMCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring for sub-100ms response times.AlteleFără avertismente★ 380↓ —
- continuityparcadei/Continuous-Claude-v3Problem-solving strategies for continuity in real analysisAlteleFără avertismente★ 3,9 K↓ —
- root-cause-analysisitseffi/agentic-osUncover root causes through recursive Why questioning and consequence exploration. Use before acting on problems.AlteleFără avertismente★ 117↓ —
- decision-journalitseffi/agentic-osCreate structured records of decisions with expected outcomes, probabilities, and quit conditions. Use for important decisions.AlteleFără avertismente★ 117↓ —
- mece-analysisitseffi/agentic-osStructure thinking using Mutually Exclusive, Collectively Exhaustive categories. Use when breaking down problems or ensuring complete coverage.AlteleFără avertismente★ 117↓ —
- crux-diagnosisitseffi/agentic-osIdentify the pivotal obstacle between current state and desired future. Use when developing strategy.AlteleFără avertismente★ 117↓ —
- limit-based-strategyitseffi/agentic-osDevelop a limit-based product strategy with convergence milestones, acceleration levers, assumptions, and phased execution.AlteleFără avertismente★ 117↓ —
- influence-strategiesitseffi/agentic-osGenerate influence strategies using Cialdini's seven principles. Use when you need to influence toward an outcome.AlteleFără avertismente★ 117↓ —