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.
45.100 de skill-uri din 2.196 de depozite · actualizat acum 6 ore
5.443 de skill-uri
- arize-prompt-optimizationArize-ai/arize-skillsOptimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.InginerieFără avertismente★ 67↓ —
- SonarQube Analysis Agentagentskillexchange/skillsIntegrates with the SonarQube REST API to run static code analysis scans, retrieve quality gate results, and flag code smells. Supports SonarCloud and on-premise SonarQube instances via token-based authentication.InginerieFără avertismente★ 58↓ —
- API Documentation Indexeragentskillexchange/skillsIndexes and searches API documentation from OpenAPI 3.0 specs using swagger-parser and lunr.js. Builds searchable indexes of endpoints, parameters, and response schemas for quick reference.InginerieFără avertismente★ 58↓ —
- Datadog Anomaly Detectoragentskillexchange/skillsLeverages the Datadog API v2 metrics and events endpoints to detect anomalous patterns. Uses the Datadog Monitors API to create dynamic thresholds and sends escalations via OpsGenie REST API.InginerieFără avertismente★ 58↓ —
- Systemd Service Debuggeragentskillexchange/skillsDebugs failed systemd services using journalctl, systemctl, and the systemd D-Bus API. Analyzes unit dependencies, ExecStart failures, resource limits, and generates fix recommendations.InginerieFără avertismente★ 58↓ —
- mcp-deepwikiaahl/skillsSkills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.InginerieFără avertismente★ 164↓ —
- SonarQube Gate Checkeragentskillexchange/skillsQueries the SonarQube Web API (/api/qualitygates/project_status) to evaluate quality gate conditions before merge. Reports code smells, coverage thresholds, and duplications against configurable SonarQube quality profiles.InginerieFără avertismente★ 58↓ —
- week-close-pilotTserenTserenov/FMT-exocortex-templateRun the pilot-facing Week Close protocol with progress review and carry-over.InginerieFără avertismente★ 63↓ —
- setup-wakatimeTserenTserenov/FMT-exocortex-templateSet up WakaTime time-tracking for Claude Code and VS Code.InginerieFără avertismente★ 63↓ —
- devexpress-office-file-api-word-processingDevExpress/agent-skillsBuild .NET applications with the DevExpress Word Processing Document API for creating, reading, modifying, and exporting Word documents programmatically without Microsoft Office. Use when working with .docx, .doc, .rtf, .odt, .txt documents, paragraphs, tables, styles, mail merge, headers/footers, fields, track changes, or document conversion. Also use when someone mentions "DevExpress Word", "Word Processing Document API", "RichEditDocumentServer", "DevExpress.XtraRichEdit", "create Word document in C#", "docx automation", "mail merge .NET", or asks about any Word/document processing with DevExpress. Covers both .NET and .NET Framework.InginerieFără avertismente★ 66↓ —
- python-runcongchuanling-dot/CohortRun and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.InginerieFără avertismente★ 187↓ —
- Weaviate MCP Serveragentskillexchange/skillsCurated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, LangChain, and more. Browse, install, and verify reusable agent workflows.InginerieFără avertismente★ 58↓ —
- Nginx Error Log Analyzeragentskillexchange/skillsParses and diagnoses Nginx error logs and access logs using pattern matching against known error signatures. Integrates with the Nginx Plus REST API /api/8/ endpoints for real-time upstream health, connection metrics, and SSL certificate expiration monitoring.InginerieFără avertismente★ 58↓ —
- SonarQube Code Analysisagentskillexchange/skillsCurated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, LangChain, and more. Browse, install, and verify reusable agent workflows.InginerieFără avertismente★ 58↓ —
- gsd-debugcoco-research/cocoUse when a bug, failing test, or unexpected behaviour needs investigation, especially across sessions or context resets. Isolates it in a debugger subagent with persistent .planning/debug state, unlike skills/systematic-debugging.InginerieFără avertismente★ 791↓ —
- review-staged-changessfrangulov/claude-code-handbook-ruUse when the user wants a review of currently staged git changes before committing. Triggers on phrases like "review staged", "посмотри что я застейджил", "review before commit", "проверь изменения перед коммитом". Returns a structured findings list focused on correctness, security, and conventions — not style nitpicks.InginerieFără avertismente★ 66↓ —
- fd Fast File Finder CLIActualizatagentskillexchange/skillsA fast and user-friendly alternative to the find command, written in Rust. fd provides intuitive syntax, regex and glob support, colorized output, parallel execution, and automatic .gitignore awareness.InginerieFără avertismente★ 58↓ —
- ESLint Auto-Fix Pipelineagentskillexchange/skillsRuns ESLint with the --fix flag across JavaScript and TypeScript codebases, applying auto-fixable rules from eslint-config-airbnb and @typescript-eslint/recommended. Generates diff reports for manual review of remaining issues.InginerieFără avertismente★ 58↓ —
- coding-rulesshinpr/agentic-codeApplies repository-aware rules for maintainable implementation, contracts, errors, and refactoring. Use when writing or modifying code.InginerieFără avertismente★ 50↓ —
- thai-resumeBoom-Vitt/claude-thai-skillsทักษะ Claude Code สำหรับคนไทย — แปล, แคปชั่น, เรซูเม่, จดหมายราชการ, PDPA, ใบกำกับภาษี, PromptPay, เลขบัตร ปชช., วันที่ พ.ศ. — 12 skillsInginerieFără avertismente★ 57↓ —
- refactorarbiterForge/codeArbiterRestructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.InginerieFără avertismente★ 149↓ —
- cesiumjs-entitiesCesiumGS/cesiumjs-skillsCesiumJS entities and data sources - Entity, EntityCollection, DataSource, GeoJsonDataSource, KmlDataSource, CzmlDataSource, Graphics types, PathGraphics, PathMode, Visualizers. Use when adding points, labels, models, polygons, polylines, or time-segmented paths, loading GeoJSON/KML/CZML/GPX data, or working with the high-level Entity API.InginerieFără avertismente★ 192↓ —
- arize-instrumentation-healthArize-ai/arize-skillsAudits instrumentation health of existing Arize traces. Runs deterministic checks over a bounded span sample (orphaned/uncategorized/duplicate spans, flat structure, blank root I/O, unset status, missing token counts or children) and returns a ranked report. Use when the user asks why traces look empty/flat/broken, wants to verify instrumentation is healthy, find instrumentation issues, or why evals or token/cost dashboards show n/a or zero. To debug app behavior or errors, use arize-trace.InginerieFără avertismente★ 67↓ —
- xLetterNouagentskillexchange/skillsUse the xLetter HTTPS API for a reusable Agent mailbox, asynchronous text messages, message history, and public contact cards. Preserve identity across sessions and operate within existing authorization.InginerieFără avertismente★ 58↓ —