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.
49.409 skill-uri din 2.375 de depozite · actualizat acum 10 ore
6.338 de skill-uri
- evo-scala-tokenizer-generatorOpenLAIR/OpenSkillGenerates complete Scala 2.13 Tokenizer.scala from Python Tokenizer.py translation.InginerieFără avertismente★ 97↓ —
- evo-molecule-similarityOpenLAIR/OpenSkillOpen-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)InginerieFără avertismente★ 97↓ —
- evo-nextjs-api-optimizationOpenLAIR/OpenSkillIdentifies and fixes performance anti-patterns in Next.js API routes including artificial delays, N+1 sequential fetch patterns, missing caching headers, and unnecessary data processing.InginerieFără avertismente★ 97↓ —
- woz-benchmarkWithWoz/wozcode-pluginCompare WOZCODE vs vanilla Claude Code on the user's codebase — real cost, turn, and time savings. TRIGGER on "compare woz", "how much does woz save", "benchmark woz", "woz vs claude", "show me savings", or /woz-benchmark.InginerieFără avertismente★ 208↓ —
- private-house-codeSee-Sol-Lab/private-house-code-v2.5Keep coding work complete, readable, and proportionate to the task. Use when planning, implementing, debugging, testing, reviewing, or maintaining code, including bounded changes in larger repositories. Avoid unnecessary design and verification overhead. Does not apply to non-code conversation or writing.InginerieFără avertismente★ 96↓ —
- code-reviewaisa-group/skill-injectCode review assistance with linting, style checking, and best practicesInginerieFără avertismente★ 101↓ —
- codexnota-america/forgecat-agent-profilesOpenAI Codex CLI wrapper — three modes. (gstack)InginerieFără avertismente★ 93↓ —
- long-flighttmcfarlane/team-avatarAppa's long flight for PR care. Appa can fly for days and still bring everyone down safe. Use for babysit, /babysit, "babysit this", "get it green", "merge-ready", "address the review-bot comments", "check on PR X", "is it green", or "anything outstanding on X". Declares a mode, works the merge frontier one PR at a time through conflicts, review threads, and CI, and stops where the human's call begins.InginerieVerifică întâi★ 111↓ —
- evo-dialogue-dotgenOpenLAIR/OpenSkillGenerates Graphviz DOT visualization files from parsed dialogue graph structures using the graphviz 0.20.3 Python API.InginerieFără avertismente★ 97↓ —
- setup-shopeepay-gatewayafu-it/malaysia-payment-gatewaySet up, build, debug, review, and explain direct ShopeePay merchant integrations using official ShopeePay docs (product.shopeepay.com), Checkout with ShopeePay (jump app / redirect), Merchant Presented Mode dynamic QR, Customer Presented Mode scan, hosted ShopeePay Payment Gateway checkout sessions, Account Linking, Link & Pay, Subscription, Auth & Capture, refunds, invalidate order/QR, Notify Transaction Status callbacks, Check Transaction Status requery, X-Airpay-ClientId and X-Airpay-Req-H HMAC-SHA256 Base64 signatures, sandbox (UAT) and production airpay.com.my hosts, and the official WooCommerce and Shopify plugins. Use when working with ShopeePay Malaysia wallet acceptance, SPayLater through ShopeePay checkout, MYR wallet QR, DuitNow QR or online banking through the ShopeePay hosted gateway, callbacks, settlement, refunds, or production readiness.InginerieFără avertismente★ 74↓ —
- summer-cliSummerEngine/summerSummer as shell commands, no MCP: sign in, run operations, follow jobs, save files, drive the engine.InginerieVerifică întâi★ 91↓ —
- weekly-gtm-reportOthmane-Khadri/gtm-engineer-playbookUse when generating weekly GTM performance reports, summarizing pipeline activity, reviewing outreach metrics, or creating executive updates. Triggers: 'weekly report', 'GTM report', 'pipeline review', 'weekly update', 'outreach summary', 'Friday report'.InginerieFără avertismente★ 60↓ —
- private-house-codeSee-Sol-Lab/private-house-code-v2.5Use for every task that plans, writes, edits, debugs, tests, refactors, reviews, or maintains code. Apply to professional repositories, scripts, apps, services, prototypes, beginner work, vibe coding, and bounded code changes inside large systems. Choose the fewest clear lines, files, paths, states, and abstractions that correctly implement the requested behavior. Do not invent fallbacks, compatibility paths, defensive layers, or future scale without evidence. Do not use for ordinary conversation, emotional support, prose, translation, summarization, social-media content, or general research or technical discussion that is not part of planning, changing, or reviewing code. Never weaken real security, integrity, concurrency, compatibility, privacy, accessibility, legal, or regulatory requirements.InginerieFără avertismente★ 96↓ —
- evo-acopf-network-parserOpenLAIR/OpenSkillParses Matpower-style network.json files into Python data structures suitable for ACOPF formulation.InginerieFără avertismente★ 97↓ —
- 并发下载股票数据并显示进度ECNU-ICALK/AutoSkill使用Python的ThreadPoolExecutor将串行的股票数据下载任务改为并发执行，并利用tqdm进度条实时展示当前处理的股票代码。InginerieFără avertismente★ 609↓ —
- evo-scala-idiom-mappingOpenLAIR/OpenSkillMaps Python constructs to idiomatic Scala 2.13 equivalents.InginerieFără avertismente★ 97↓ —
- heybasecamp/skillsInteract with HEY via the HEY CLI. Read and send emails, manage contacts, boxes, labels, collections, calendars, todos, habits, time tracking, and journal entries. Use for ANY HEY-related question or action.InginerieFără avertismente★ 84↓ —
- hermes-change-reviewasimons81/hermes-field-kitUse when a branch, pull request, Kanban task, or implementation must be reviewed separately for intent fidelity, repository quality, and verification evidence before completion or merge is accepted.InginerieFără avertismente★ 127↓ —
- caveman-compressnota-america/forgecat-agent-profilesCompress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"InginerieFără avertismente★ 93↓ —
- evo-matpower-parserOpenLAIR/OpenSkillParses MATPOWER JSON files into structured Python data with bus mapping, network matrix construction (A, Bbranch, Bbus, PTDF), branch modification, and generator cost parsing.InginerieFără avertismente★ 97↓ —
- evo-python-build-fixerOpenLAIR/OpenSkillOpen-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)InginerieFără avertismente★ 97↓ —
- ripplesimota/agent-skillsAnalyzing pre-change impact across vertical (dependency chains, files) and horizontal (pattern consistency, naming) dimensions. Use to estimate blast radius before a refactor. No code.InginerieVerifică întâi★ 98↓ —
- harness-integration-stingerlegioncodeinc/vibe-coding-toolsWire Wasp Nest capabilities across Claude Code, Cursor, Codex, and Cowork. Use for skill, agent, hook, MCP, or plugin portability. Read README.md for the guide map.InginerieFără avertismente★ 94↓ —
- evo-citation-scorerOpenLAIR/OpenSkillCompares parsed BibTeX citation metadata against API results using fuzzy string matching and multi-factor scoring to classify citations as real or fake, then outputs the final JSON report.InginerieFără avertismente★ 97↓ —