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.
48.168 de skill-uri din 2.325 de depozite · actualizat acum 12 ore
6.204 skill-uri
- hyperpod-performance-debuggerawslabs/agent-pluginsDiagnose performance issues on Amazon SageMaker HyperPod clusters — uneven NCCL bandwidth across nodes and poor filesystem throughput. Read-only. Surfaces host-side signals (Xid, ECC, NVLink, EFA reachability, FSx saturation) and routes to the appropriate sibling skill (hyperpod-node-debugger, hyperpod-nccl, hyperpod-version-checker, hyperpod-issue-report) for any remediation. Triggers on uneven NCCL across nodes, straggler node, FSx slow, checkpoint slow, dataloader slow, filesystem bottleneck, FSx throughput, cross-AZ latency, topology mismatch.InginerieFără avertismente★ 932↓ —
- uganda-vatopenaccountants/openaccountantsUse this skill whenever asked to prepare, review, or classify transactions for a Uganda VAT return. Standard rate 18%. Withholding VAT 6% of taxable value. EAC customs union but no common VAT. ALWAYS read before handling Uganda VAT work.InginerieFără avertismente★ 468↓ —
- morocco-vatopenaccountants/openaccountantsUse this skill whenever asked to prepare, review, or classify transactions for a Morocco VAT (TVA) return. Two rates from 2026 -- 20%/10% (7% and 14% phased out). Critical distinction between exempt-with-deduction (Art. 92) and exempt-without-deduction (Art. 91). ALWAYS read before handling Morocco TVA work.InginerieFără avertismente★ 468↓ —
- senegal-vatopenaccountants/openaccountantsUse this skill whenever asked to prepare, review, or classify transactions for a Senegal VAT (TVA) return. Standard rate 18%, reduced 10% (tourism). WAEMU member. Precompte TVA mechanism. ALWAYS read before handling Senegal VAT work.InginerieFără avertismente★ 468↓ —
- tunisia-vatopenaccountants/openaccountantsUse this skill whenever asked to prepare, review, or classify transactions for a Tunisia VAT (TVA) return. Three rates -- 19%/13%/7%. Unique suspension regime (not zero-rating). Droit de consommation interaction. Withholding TVA 25%. ALWAYS read before handling Tunisia TVA work.InginerieFără avertismente★ 468↓ —
- policy-as-codeBagelHole/DevOps-Security-Agent-SkillsImplement policy as code with OPA, Sentinel, and Kyverno. Automate policy enforcement in CI/CD and infrastructure. Use when enforcing compliance through automation.InginerieFără avertismente★ 1,2 K↓ —
- code-reviewevanca/flutter-ai-rulesUse when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.InginerieFără avertismente★ 665↓ —
- cos-reviewsno-ai/sno-station-skillsReview PL self-approvals, estimates, board drift, and close quality after a declared night shift. Loaded ONLY by the cos core via its routing table; NEVER auto-load from context or invoke directly.InginerieFără avertismente★ 858↓ —
- python-codersno-ai/sno-station-skillsImplement and refactor production Python, FastAPI, Pydantic, async, and migrations.InginerieFără avertismente★ 858↓ —Apare și în 1 alt depozit
- systematic-debuggingcoco-research/cocoUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesInginerieFără avertismente★ 795↓ —
- find-skillscountbot-ai/CountBot基于腾讯 SkillHub 搜索、安装和管理技能。用户提到“找技能”“安装 skill”“扩展功能”“启用/禁用 skill”“删除 skill”“安装 SkillHub CLI”时优先使用。InginerieFără avertismente★ 783↓ —
- codemanArk0N/CodemanDrive Codeman, the session manager this agent is running inside, over its HTTP API, from any agent CLI (Claude Code, Codex, Gemini CLI, OpenCode, Antigravity, Grok Build, DeepSeek Harness, OMP): list sessions, start worker sessions in any installed CLI, send them prompts, block until they finish (wait / wait-output / send-and-wait), read their output, and clean up; where available, message claude workers directly (Claude Code cross-session messaging). Use when asked to orchestrate or parallelize work across Codeman sessions, get a second opinion from another CLI or model, watch another session, start and manage workers, or retrieve saved local Codex history by file/native ID or root and descendants with topic/date filters. Live API operations require a Codeman-managed session (CODEMAN_MUX=1). Offline history reads do not require a server or managed session.InginerieFără avertismente★ 825↓ —Apare și în 1 alt depozit
- wallet-analysissendaifun/skillsAnalyze Solana wallets and multichain portfolios with Zerion API. Use for Solana portfolio value, token positions, transaction history, wallet charts, and PnL. Prefer direct REST API integration, with hosted MCP and x402 on Solana as no-key alternatives for agent workflows.InginerieFără avertismente★ 130↓ —
- code-review-advancedjaktestowac/awesome-copilot-for-testersPerforms evidence-driven code review for pull requests, legacy modules, and quality-critical changes. Use when reviewing complex or multi-file changes, test automation suites, architectural refactors, or hot paths that need analysis of correctness, maintainability, security, performance, test quality, and operability risks. Provides structured feedback with severity-ranked findings, actionable recommendations, and clear rationale. For a fast sanity check of a small diff or single file, use the code-review skill instead.InginerieFără avertismente★ 118↓ —Apare și în 1 alt depozit
- trace-claude-codeparcadei/Continuous-Claude-v3Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.InginerieFără avertismente★ 3,9 K↓ —
- ts-codersno-ai/sno-station-skillsImplement and refactor production TypeScript/TSX, strict types, APIs, and migrations.InginerieFără avertismente★ 858↓ —Apare și în 1 alt depozit
- rotate-agentsno-ai/sno-station-skillsQuota-triggered failover from Claude Code, Codex, Cursor, Hermes or OpenClaw. When armed, it reads the sender quota and tries other-vendor models in place, then receiving agents in the configured order. Use when a long run must finish even if one vendor's quota runs out. Not a monitor for anything else.InginerieFără avertismente★ 858↓ —
- session-handoff-promptdongshuyan/compass-skillsCreate a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries, task-forest maintenance, durable user-profile updates, automatic session creation, code execution, or external publishing.InginerieFără avertismente★ 763↓ —
- cozempic-doctorRuya-AI/cozempicRun health checks on Claude Code configuration and sessions. Use when troubleshooting Claude Code issues. (cozempic — does not shadow Claude Code's built-in /doctor)InginerieFără avertismente★ 427↓ —
- israel-vatopenaccountants/openaccountantsUse this skill whenever asked to prepare, review, or classify transactions for an Israel VAT (Ma'am — מע"מ) return or advise on Israeli VAT registration, filing, and reporting. Trigger on phrases like "prepare Ma'am return", "Israeli VAT", "מע"מ", "doch maam", or any Israel VAT request. ALWAYS read this skill before touching any Israel Ma'am-related work.InginerieFără avertismente★ 468↓ —
- static-code-analysis-typescriptjaktestowac/awesome-copilot-for-testersCreates, reviews, and modernizes static code analysis setups for Node.js and TypeScript repositories, covering ESLint flat config, typescript-eslint, tsconfig, Prettier, import sorting, Husky, lint-staged, package.json quality scripts, and CI quality gates. Use when setting up or auditing linting, formatting, type-checking, commit hooks, or GitHub Actions quality checks in a TypeScript project.InginerieFără avertismente★ 118↓ —Apare și în 1 alt depozit
- github-repo-health-stingerlegioncodeinc/vibe-coding-toolsAudit GitHub repository hygiene. Use for branch protection, CI checks, CODEOWNERS, templates, README coverage, or commit history. Read README.md for the guide map.InginerieFără avertismente★ 94↓ —
- pr-reviewMiniMax-AI/skillsReview pull requests for the MiniMax Skills repository. Use when reviewing PRs, validating new skill submissions, or checking existing skills for compliance. Run the validation script first for hard checks, then apply quality guidelines for content review. Triggers: PR review, pull request, validate skill, check skill.OficialInginerieFără avertismente★ 13,7 K↓ —
- embeddings-runtime-stingerlegioncodeinc/vibe-coding-toolsPicks and runs embedding models: hosted (OpenAI, Cohere, Voyage) vs self-hosted, cost tradeoffs, batching, caching. Use when choosing, swapping, or debugging an embedding model.InginerieFără avertismente★ 94↓ —