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.
49.105 skill-uri din 2.358 de depozite · actualizat acum 20 de ore
6.206 skill-uri
- isolated-setup-doctorActualizatapache/magpieProbe the secure-agent setup for restrictions that block legitimate work — SSH agent reachability, port binding, containers, the scratch directory, the signing key, `gh` outside the sandbox, `prek` and `uv` inside it, the global git hook dir. Names the troubleshooting entry and settings fix for each. Read-only.InginerieVerifică întâi★ 135↓ —
- vault-cleanup-auditorBrianRWagner/ai-marketing-claude-code-skillsAudit your Obsidian vault in Claude Code — finds stale drafts, empty folders, duplicate filenames, and incomplete files. Saves a dated report.InginerieFără avertismente★ 451↓ —
- git-workflownetresearch/git-workflow-skillUse when establishing branching strategies, implementing Conventional Commits, creating or reviewing PRs, resolving PR review comments, merging PRs (including CI verification, auto-merge queues, and post-merge cleanup), managing PR review threads, merging PRs with signed commits, handling merge conflicts, verifying a merge didn't silently drop changes, syncing a long-diverged branch (e.g. master into integration), rebasing a long-lived branch onto a moved base or splitting one into several PRs, integrating Git with CI/CD, setting up git hooks (lefthook, captainhook, husky, pre-commit), debugging hook-install failures in git worktrees, or working in a bare-repo plus per-branch-worktree layout, including consolidating a directory that holds both a plain clone and a .bare. The pull-request tooling is GitHub-only; references/pull-request-workflow.md carries the GitLab equivalents. Not for creating releases (use github-release) or diagnosing BLOCKED/won't-merge PRs (use github-project).InginerieFără avertismente★ 59↓ —
- automate-whatsappgokapso/agent-skillsBuild and debug Kapso WhatsApp workflows, triggers, functions, and executions.InginerieFără avertismente★ 198↓ —
- daily-briefing-builderBrianRWagner/ai-marketing-claude-code-skillsGenerate a clean morning brief in Claude Code — pulls today's priorities, unposted content, and weather from your vault.InginerieFără avertismente★ 451↓ —
- scikit-learnKalarisLabs/research-agent-skillsCovers classical machine learning in Python with scikit-learn (sklearn): classification and regression estimators, clustering and dimensionality reduction, preprocessing, Pipeline and ColumnTransformer, cross-validation, metrics, and GridSearchCV hyperparameter tuning. Use when training or comparing classifiers and regressors on tabular or text data, clustering data and choosing the cluster count, building leakage-free preprocessing pipelines, evaluating models with cross-validation and metrics, or tuning hyperparameters. Not for deep learning; use a dedicated neural network framework instead.InginerieFără avertismente★ 95↓ —
- context7netresearch/context7-skillUse when looking up library documentation, API references, framework patterns, or code examples for ANY library (React, Next.js, Vue, Django, Laravel, etc.) and the Context7 MCP server is unavailable or not configured. Fetches the same current docs directly via the Context7 REST API as a fallback. Triggers on: how to use library, API docs, framework pattern, import usage, library example.InginerieFără avertismente★ 84↓ —
- dotnet-rate-limitingronnythedev/dotnet-clean-architecture-skillsImplements ASP.NET Core rate limiting middleware for API protection. Covers fixed window, sliding window, token bucket, and concurrency limiters with custom policies.InginerieFără avertismente★ 77↓ —
- gitaiskillstore/marketplaceManages Git commits, branches, conflict resolution, and recovery. Use when the task requires Git operations or history analysis; follow the repository workflow.InginerieVerifică întâi★ 452↓ —
- dotnet-legacy-api-controllersronnythedev/dotnet-clean-architecture-skillsGenerates RESTful API Controllers with proper routing, versioning, authorization, and MediatR integration. Follows REST conventions and Clean Architecture patterns.InginerieFără avertismente★ 77↓ —
- dotnet-minimal-api-endpointsronnythedev/dotnet-clean-architecture-skillsGenerates Minimal API endpoints following Microsoft's recommended approach. Creates fast, testable HTTP APIs with minimal code using MapGet/MapPost/MapPut/MapDelete. Preferred over controller-based APIs for new projects.InginerieFără avertismente★ 77↓ —
- code-bloat-stingerlegioncodeinc/vibe-coding-toolsRead-only bloat audit of any repo. jscpd duplication, knip or language dead-code tools with a spot-check, cloc size, function and closure structure, split plans, banded verdict.InginerieVerifică întâi★ 94↓ —
- execgo-agent-bridgeiammm0/secbotRoute shell, runtime.command, runtime.script, mcp.call, cli.run, or task_graph.submit work through Secbot's ExecGo-backed control tools.InginerieFără avertismente★ 77↓ —
- meeting-prep-ccBrianRWagner/ai-marketing-claude-code-skillsGenerate a pre-meeting prep brief in Claude Code. Researches participants, pulls vault context, builds agenda, surfaces sharp questions. Use when user says "prep for this meeting," "I have a call with," "meeting tomorrow with," or "prep brief for [name/company]."InginerieFără avertismente★ 451↓ —
- brand-modcofoundy/brand-skillsPut a brand inside Claude Code — a branded spinner for the terminal and the desktop app (brand colors, the brand's own words, its logo), previewed in HTML for approval before it is generated as an installable mod. Use when the user says "brand our Claude Code", "branded spinner", "Claude Code mod with our brand", "custom spinner", "make the terminal on-brand", "brand the agent", "spinner with our logo", "show our brand while Claude works", or wants their team's or a client's Claude Code to look like their brand (for screen recordings, demos, or daily use). Claude Code only — mods don't exist in other agents.InginerieFără avertismente★ 68↓ —
- aqua-communicationquailyquaily/aquaAqua is a CLI-first message tool for AI agents. Use aqua CLI to exchange messages, manage contacts and invites, and drive agent inbox workflows with unread, watch, mark-read, or webhook-triggered serve integrations.InginerieFără avertismente★ 259↓ —
- code-reviewomergocmen/vibe-coder-kitSystematic code review skill covering both requesting a review (pre-commit checklist) and receiving and responding to review feedback. Checks code quality, security, test coverage, architectural alignment, and documentation before any code is committed.InginerieVerifică întâi★ 99↓ —
- scaffoldingOdradekAI/bundles-forgeUse when generating project structure for new bundle-plugins, adding or removing platform support (Claude Code, Cursor, Codex, OpenCode, Gemini CLI, OpenClaw), updating platform manifests, or migrating hooks and configuration between platformsInginerieFără avertismente★ 227↓ —
- pokemon-champions-teampmwl0128/quark_drive_skillsPokémon Champions single/double team building, legality validation, and diagnostics. Use for producing, completing, changing, reviewing, or evaluating a team; do not trigger from isolated words like core/style/include. Examples include "帮我组一队", "配一套双打", "围绕X做一队", "这队怎么改", "这队怎么选"; "build me a team", "team around X", "rework this team", "review/evaluate my team"; "チームを組んで", "ダブルの構築を作って", "X入りで組んで", "この構築を直して", "選出を見て". The mandatory UEP flow uses context-audit, intake, frame, slate-evaluate, checkpoint, and answer-audit receipt gates before presenting build results. Also use to parse or validate teams, diagnose coverage/speed/role gaps, analyze 6v6 selection, compare matchups, tune SP, retrieve real-team evidence, scan metagame OHKO/2HKO tables, compare metagame speed lines (环境速度线 / speed ladder / 環境の素早さ), query type effectiveness and current rules, or query observed answers to a Pokémon (谁能应对X / who counters X / Xへの対策).InginerieFără avertismente★ 78↓ —Apare și în 1 alt depozit
- code-audit-brief-stingerlegioncodeinc/vibe-coding-toolsRender the Audit My Code brief, one self-contained Field Guide styled HTML file per run, from the workspace only. Escapes repo text, merges duplicates, prints cleanly to PDF.InginerieVerifică întâi★ 94↓ —
- verify-msp-skillsServosity/msp-skillsDrive one msp-skills connector (skills/<slug>, any of the 84) the way a user does and prove it with evidence: install.sh, the <slug>-cli CLI, and the <slug>-mcp server over stdio and over HTTP, in an isolated HOME against a local fake vendor. Use to check a connector's user path before or after a reprint, to compare press versions across the fleet, or when a connector 'builds green' but nobody has watched it run.InginerieFără avertismente★ 69↓ —
- dingtalk-skill-creatorbreath57/dingtalk-skills创建新的钉钉技能（dingtalk skill）。当用户提到"创建新技能"、"新建技能"、"开发钉钉技能"、"新增钉钉功能"、"添加钉钉接口支持"、"我需要一个钉钉 xxx 技能"、"钉钉待办"、"钉钉签到"、"钉钉考勤"、"钉钉审批"、"钉钉日程"等希望将某个钉钉 API 领域封装成可复用 skill 时，必须使用此技能。此技能包含完整的技能创建流程：SDK 探索 → SDK Python 测试 → 纯 HTTP Python 测试（两步全通过）→ SKILL.md 编写。测试未全部通过不得创建 skill。InginerieFără avertismente★ 101↓ —
- dyz-med-screening-pipelineNouduyunzhoudyz/dyz-med-paper-skills管理系统综述、Meta 分析或范围综述从检索导入、保守去重、标题摘要与全文筛选，到研究/报告关联、数据提取 和 PRISMA 计数的可审计证据链。当用户要执行文献筛选、记录纳排理由或准备证据合成输入时使用；研究问题与 方案设计不是本技能的主要任务，流程图交给 dyz-med-flowchart，原始研究数据统计与合并模型交给 dyz-med-analyze。 Use for systematic review and meta-analysis screening, extraction and PRISMA counts.InginerieFără avertismente★ 115↓ —
- Skywork SearchSkyworkAI/Skywork-SkillsSearch the web for real-time information using the Skywork web search API. Use this skill whenever the user needs up-to-date information from the internet — for example, researching a topic, looking up recent events, finding facts or statistics, gathering material for a document or presentation, or answering questions that require current data. Also trigger when the user says things like "search for" / "搜索" / "検索" / "검색", "look up" / "查询" / "調べる" / "조회하다", "find information about" / "查找关于……的信息" / "……に関する情報を探す" / "…에 대한 정보를 찾다", "what's the latest on" / "……最新进展" / "……の最新情報" / "…의 최신 소식", or any request that implies needing information beyond your training data.InginerieFără avertismente★ 207↓ —