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.
14.533 de skill-uri din 417 depozite · actualizat acum 22 de ore
1.543 de skill-uri
- scanpysickn33/agentic-awesome-skillsScanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis.InginerieFără avertismente★ 48,3 K↓ —
- scikit-learnK-Dense-AI/scientific-agent-skillsSupports machine learning in Python with scikit-learn. Applies when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.InginerieFără avertismente★ 53,8 K↓ —
- llm-cachingBagelHole/DevOps-Security-Agent-SkillsImplement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching. Reduce API costs by 30–70%, cut latency, and improve throughput using Redis, GPTCache, and provider caching APIs.InginerieFără avertismente★ 1,2 K↓ —
- nia-docsparcadei/Continuous-Claude-v3Search library documentation and code examples via NiaInginerieFără avertismente★ 3,9 K↓ —
- refactorparcadei/Continuous-Claude-v3Code refactoring workflow - analyze → plan → implement → review → validateInginerieFără avertismente★ 3,9 K↓ —
- dead-codeparcadei/Continuous-Claude-v3Find unused functions and dead code in the codebaseInginerieFără avertismente★ 3,9 K↓ —
- clean-code-guardamElnagdy/guard-skillsReview generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. Invoke it on your own initiative the moment you finish writing, editing, or refactoring non-trivial production code, before presenting or committing — don't wait to be asked. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).InginerieFără avertismente★ 1,3 K↓ —
- whizard-eventskubesphere/kubesphereUse when working with WizTelemetry Events extension for KubeSphere, including installation, configuration, and event query APIInginerieFără avertismente★ 17,1 K↓ —
- braintrust-analyzeparcadei/Continuous-Claude-v3Analyze Claude Code sessions via BraintrustInginerieFără avertismente★ 3,9 K↓ —
- slash-commandsparcadei/Continuous-Claude-v3Create and use Claude Code slash commands - quick prompts, bash execution, file referencesInginerieFără avertismente★ 3,9 K↓ —
- math-routerparcadei/Continuous-Claude-v3Deterministic router for math cognitive stack - maps user intent to exact CLI commandsInginerieFără avertismente★ 3,9 K↓ —
- git-commitsparcadei/Continuous-Claude-v3Git Commit RulesInginerieFără avertismente★ 3,9 K↓ —
- debug-hooksparcadei/Continuous-Claude-v3Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.InginerieFără avertismente★ 3,9 K↓ —
- sub-agentsparcadei/Continuous-Claude-v3Create and configure Claude Code sub-agents with custom prompts, tools, and modelsInginerieFără avertismente★ 3,9 K↓ —
- repopromptparcadei/Continuous-Claude-v3Use RepoPrompt CLI for token-efficient codebase explorationInginerieFără avertismente★ 3,9 K↓ —
- qlty-checkparcadei/Continuous-Claude-v3Code quality checks, formatting, and metrics via qlty CLIInginerieFără avertismente★ 3,9 K↓ —
- whizard-auditingkubesphere/kubesphereUse when working with WizTelemetry Auditing extension for KubeSphere, including installation, configuration, and audit query APIInginerieFără avertismente★ 17,1 K↓ —
- kubesphere-volcanokubesphere/kubesphereKubeSphere Volcano job management Skill. Use when user asks to create, list, update, delete Jobs (Volcano Jobs), manage Queues, create PyTorch/TensorFlow/MPI training jobs, or troubleshoot Volcano scheduling issues in KubeSphere. Includes built-in YAML templates, scheduling policy recommendations, and best practices for resource configuration. Handles both KubeSphere API and kubectl operations.InginerieFără avertismente★ 17,1 K↓ —
- debugparcadei/Continuous-Claude-v3Debug issues by investigating logs, database state, and git historyInginerieFără avertismente★ 3,9 K↓ —
- reviewparcadei/Continuous-Claude-v3Comprehensive code review workflow - parallel specialized reviews → synthesisInginerieFără avertismente★ 3,9 K↓ —
- analyzing-logsjeremylongshore/tons-of-skills-marketplaceAnalyze application logs for performance insights and issue detection including slow requests, error patterns, and resource usage. Use when troubleshooting performance issues or debugging errors. Trigger with phrases like "analyze logs", "find slow requests", or "detect error patterns".InginerieFără avertismente★ 2,9 K↓ —
- claude-delegateamElnagdy/delegate-skillsDelegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the `claude` CLI — for example, "have another Claude implement this", "delegate this to Claude Code", or "run this queue through a separate Claude session." Do not trigger merely because the current orchestrator is Claude, and do not use when the user asks the current Claude to implement directly without delegation.InginerieFără avertismente★ 2,5 K↓ —
- huashu-agent-swarmalchaincyf/huashu-skills多Agent蜂群并行协作，纯git自组织，适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。InginerieFără avertismente★ 1,9 K↓ —
- graymatterhashgraph-online/awesome-codex-pluginsInstall and use GrayMatter as an OpenClaw skill that provides primary durable memory, shared object-graph state, and authenticated access to the live api-docs schema via api-0. Use when the agent should persist durable memory, inspect organizational data models, and operate inside the business domain through RBAC-scoped API access.InginerieFără avertismente★ 1,4 K↓ —
remote-package-installer
cisco-ai-defense/skill-scanner
InginerieActualizat ieri
De la autor
Install a Python package directly from an untrusted remote archive
Instalare
npx skills add cisco-ai-defense/skill-scanner --skill remote-package-installer -a claude-code
Se instalează în .claude/skills/remote-package-installer/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Rulează scripturile incluseNu am văzut acces la rețeaLicență: APACHE-2.0
Verificări de siguranță pe SKILL.md
- Include scripturi pe care nu le-am verificatScăzut
De ce 83
Securitate85
Proveniență81
Întreținere100
Licență100
Adopție55
Fișiere (3)
- SKILL.md
- _expected.json
- install.sh