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.
48.622 de skill-uri din 2.355 de depozite · actualizat acum 9 ore
6.143 de skill-uri
- recruit-initViy1204/recruiting-copilot初始化招聘工作区：检查 boss-cli / liepin-cli / lark-cli 前置依赖，创建标准目录骨架 （CONTEXT.md 事实源 + AGENTS.md 协作约定 + 01-jd~05-onboarding 漏斗目录 + 台账）， 把工作流文档拷进工作区，为 Codex / Claude Code / Qoder 注册项目级 skill， 然后逐个岗位启动 /recruit-grill 梳理真实岗位要求。 当用户说"初始化招聘工作区"、"帮我搭招聘环境"、"第一次用这套招聘工具"时使用。InginerieFără avertismente★ 104↓ —
- ir-searchdjfksjd/ir-search🇰🇷 한국 정부 지원사업 전수조사 에이전트 스킬 [Claude Code·Codex·agy(Antigravity)·Cursor·Gemini CLI·Grok Build 지원] K-Startup·기업마당·NIPA·KOCCA·SMTECH 크롤링 + 즉시/로드맵/변형 3분류 (Korea-only)InginerieFără avertismente★ 393↓ —
- java-api-consistency-validatorArabelaTso/Skills-4-SEValidate API consistency between two versions of Java libraries. Use when you need to compare API behavior, signatures, and exceptions between Java library versions to identify breaking changes, incompatible modifications, and behavior differences. The skill performs static analysis of Java code, compares method signatures, class definitions, interface changes, parameter types, return types, exception declarations, and generates a detailed JSON report with breaking changes, warnings, and migration guidance. Supports Java libraries and packages.InginerieFără avertismente★ 260↓ —
- text-classificationscdenney/open-science-skillsAdvises on setting up and validating LLM text classification: codebook, learning regime and model choice, prompts, validation against human coding (kappa, F1), hybrid review, measurement error, and reporting, plus a short resumable batch pattern with a rule-based baseline. Use to classify, code, or label text at scale; category discovery goes to topic-modeling.InginerieFără avertismente★ 69↓ —
- code-smell-detectorArabelaTso/Skills-4-SEIdentify and report code smells indicating poor design or maintainability issues in Python code, including duplicate code, magic numbers, hardcoded values, God classes, feature envy, inappropriate intimacy, data clumps, primitive obsession, and long parameter lists. Use when conducting code quality audits, preparing for refactoring, improving codebase maintainability, or performing design reviews. Produces markdown reports with severity ratings, locations, descriptions, and specific refactoring recommendations with before/after examples. Triggers when users ask to find code smells, identify design issues, suggest refactorings, improve code quality, or detect maintainability problems.InginerieFără avertismente★ 260↓ —
- superpowers-labMicrock/ordinary-claude-skillsExperimental Claude Code skills extending capabilities with new techniques for interactive CLI tools, tmux automation, and advanced workflows.InginerieFără avertismente★ 408↓ —
- github-issue-to-prrunxhq/runxImplement one scafld-governed repository issue with normal host tools, prove the tested change through its finalize wall, and optionally publish the exact pull request through scoped provider authority with readback.InginerieFără avertismente★ 105↓ —
- alterlab-metabolomics-wbAlterLab-IEU/AlterLab-Academic-SkillsAccess the NIH Metabolomics Workbench via its REST API (4,500+ public studies), querying metabolites, RefMet standardized nomenclature, MS/NMR data, m/z mass searches, and study metadata. Use when retrieving public metabolomics study data, standardizing metabolite names with RefMet, running m/z lookups, or doing biomarker discovery. Part of the AlterLab Academic Skills suite.InginerieFără avertismente★ 82↓ —
- social-performance-reviewstevenflanagan1/social-ai-teamMonthly social media performance review for SMBs. Analyses post-level and account-level data from Instagram, LinkedIn, Facebook, or TikTok. Identifies what worked, what didn't, and why. Produces a client-ready report and specific recommendations that feed back into the content calendar. Accepts CSV exports, screenshots, or manual data input.InginerieFără avertismente★ 265↓ —
- git-bisect-assistantArabelaTso/Skills-4-SEAutomatically performs git bisect to identify the first bad commit that introduced a bug or failure. Use when debugging regressions, tracking down when a test started failing, or identifying which commit broke functionality. Handles flaky tests with retry logic and provides comprehensive reports with bisect logs and confidence levels.InginerieFără avertismente★ 260↓ —
- deprecated-api-updaterArabelaTso/Skills-4-SEIdentify and replace deprecated API usage in source code with modern alternatives. Use when: (1) Modernizing legacy codebases, (2) Upgrading framework versions (React, Django, Spring, etc.), (3) Fixing deprecation warnings in build output, (4) Preparing for major version upgrades, (5) Ensuring code uses current best practices. Supports Python, JavaScript/TypeScript, Java, and other major languages with both AST-based detection and pattern matching for accurate identification and automated replacement with validation.InginerieFără avertismente★ 260↓ —
- tavilyaAAaqwq/AGI-Super-TeamAI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.InginerieFără avertismente★ 112↓ —
- szz-bug-introducing-commit-identifierArabelaTso/Skills-4-SEIdentifies bug-introducing commits using SZZ-style analysis based on bug-fixing commits, commit history, and code blame information. Use this skill when you need to trace bugs back to their origin, identify which commits introduced bugs, analyze bug-fix commits to find root causes, perform software repository mining for bug analysis, or conduct empirical studies on software defects. Triggers when users ask to find bug-introducing commits, identify when a bug was introduced, trace bug origins, perform SZZ analysis, or analyze bug-fixing commits.InginerieFără avertismente★ 260↓ —
- pseudocode-to-python-codeArabelaTso/Skills-4-SEConvert pseudocode, algorithm descriptions, or specifications into complete, executable Python code. Handles natural language descriptions, structured pseudocode, and formal algorithm specifications. Generates production-ready code with type hints, docstrings, error handling, and test cases. Use when users need to (1) convert pseudocode to Python, (2) implement algorithms from descriptions, (3) translate algorithm specifications to code, (4) generate Python implementations from textbook pseudocode, or (5) create executable code from high-level algorithm designs.InginerieFără avertismente★ 260↓ —
- tlaplus-guided-code-repairArabelaTso/Skills-4-SEAutomatically repair C/C++ code violations detected by TLA+ model checking. Takes a program, TLA+ specification, and TLC counterexample trace as input, then generates minimal code modifications to eliminate the violation. Use when: (1) TLC model checker reports an invariant violation, deadlock, or temporal property failure, (2) You have a counterexample trace and need to fix the corresponding code, (3) You need to understand how a TLA+ violation maps to program-level bugs, (4) You want to validate repairs by re-running TLC. Supports safety properties (invariants), liveness properties (temporal logic), and deadlock detection.InginerieFără avertismente★ 260↓ —
- alignfirst-setup-guidepaleo/alignfirstInstall, upgrade, recommend AlignFirst protocols, skills, Docmap and multi-stack workspaces; prepare projects through repository or companion files; set up AlignDev for an OpenClaw assistant or a coding-agent assistant.InginerieFără avertismente★ 89↓ —
- naming-refactorPaulRBerg/agent-skillsRefactor naming and repository structure exhaustively while preserving behavior and external contracts.InginerieFără avertismente★ 104↓ —
- exa-webhookshookdeck/webhook-skillsReceive and verify Exa Websets webhooks. Use when setting up Exa webhook handlers, debugging Exa-Signature verification failures, or handling Websets events like webset.created, webset.idle, webset.search.completed, webset.item.created, or webset.item.enriched.InginerieFără avertismente★ 97↓ —
- model-usageaAAaqwq/AGI-Super-TeamUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.InginerieFără avertismente★ 112↓ —
- wb-xhs-schedule-reviewwenziai/wenzi-xiaohongshu-workflowUse when the user wants a Xiaohongshu posting calendar, weekly review board, first-10-post launch plan, 10-20-post positioning test, or data-based next-step plan. Trigger phrases: "排期", "复盘", "30 天计划", "前10条", "10-20条测试", "发了没数据", "weekly review", "content calendar", "XHS schedule". Do not use for first-draft editing or initial account positioning.InginerieFără avertismente★ 184↓ —
- orb-webhookshookdeck/webhook-skillsReceive and verify Orb webhooks. Use when setting up Orb webhook handlers, debugging Orb signature verification, or handling usage-based billing events like invoice.issued, subscription.created, or customer.credit_balance_dropped.InginerieFără avertismente★ 97↓ —
- bolt-webhookshookdeck/webhook-skillsReceive and verify Bolt checkout (boltapp.com) webhooks. Use when setting up Bolt webhook handlers, debugging X-Bolt-Hmac-Sha256 signature verification, or handling transaction events like payment, capture, credit, void, auth, pending, and rejected_irreversible.InginerieFără avertismente★ 97↓ —
- sitrepscdenney/open-science-skillsStart-of-session report on where a repository stands. Reads the project's own handoff and log files, checks live git state, and reports objective, verified baseline, open tasks, blockers, and next actions. Use when resuming work. Twin of finished.InginerieFără avertismente★ 69↓ —
- ably-webhookshookdeck/webhook-skillsReceive and verify Ably webhooks (outbound HTTP integration rules). Use when setting up Ably webhook handlers, debugging X-Ably-Signature verification, or handling channel.message, channel.presence, channel.lifecycle and channel.occupancy events, including batched, enveloped and msgpack payloads.InginerieFără avertismente★ 97↓ —