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.
49.492 de skill-uri din 2.391 de depozite · actualizat acum 15 ore
49.492 de skill-uri
- 01-auto-arenaagentscope-ai/OpenJudgeAutomatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.TestareFără avertismente★ 1 K↓ —
- error-propagationhoangsonww/Claude-Code-Agent-MonitorTrace error propagation through a multi-agent session by agent depth — where failures originated, the depth at which they appeared, and how they cascaded up to parent agents — using the Agent Monitor workflow intelligence API and the session event stream. Use when a multi-agent run failed and you need to find the origin and blast radius of the failure.InginerieFără avertismente★ 1,1 K↓ —
- concurrency-reporthoangsonww/Claude-Code-Agent-MonitorReport concurrency and parallelism for a session — how many agents ran in parallel, concurrency-lane utilization, peak parallel width, and serialization bottlenecks (sequential chains that could have run as parallel lanes) — using the Agent Monitor workflow intelligence API. Use when checking whether a multi-agent session used parallelism efficiently.InginerieFără avertismente★ 1,1 K↓ —
- shipping-page-generatorkostja94/marketing-skillsDeprecated compatibility entry for Shipping Policy Page construction. This page is now maintained in Pagina; install and use page-builder to build a new Shipping Policy Page.AlteleFără avertismente★ 1,1 K↓ —
- jira-expertalirezarezvani/claude-skillsJira setup and queries: JQL, workflows, custom fields, automation, dashboards. Use whenever the user needs a Jira search, filter, dashboard or rule set up, or a workflow fixed.ProductivitateFără avertismente★ 29,3 K↓ —
- optimization-suggesthoangsonww/Claude-Code-Agent-MonitorSuggest concrete optimizations for Claude Code usage based on historical session data. Covers cost reduction, speed improvement, error prevention, and workflow efficiency. Use for data-driven optimization planning.PlanificareFără avertismente★ 1,1 K↓ —
- add-table-to-offline-profilemicrosoft/power-platform-skillsInternal mobile-app workflow read and executed only by mobile orchestrators to add one Dataverse table to an existing Mobile Offline Profile.ProductivitateFără avertismente★ 1,1 K↓ —
- choosing-swarm-patternsAgentWorkforce/relayUse when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate SDK/YAML examples.PlanificareFără avertismente★ 1,1 K↓ —
- speak-human-twRaymondhou0917/speak-human-tw「說人話」:繁體中文的去 AI 味改寫 skill。審查與改寫文字,去除 AI 味道、校正中國用語與半形標點,讓文字讀起來像真人寫的。 觸發時機:用戶說「去 AI 味」「說人話」「這段好 AI」「改自然一點」「幫我潤稿去掉 AI 感」「校對一下再發」,或要求檢查電子報、社群貼文、銷售頁、課程文案、客服回信、簡報、公告、Email 等對外文字的語感。 不要觸發:逐字翻譯、模仿特定品牌 voice、事實查核(非風格問題)、程式碼/log/設定檔、要求「潤成雷蒙的語氣」(那是 content-writing skill 的事,本 skill 只去 AI 味、不加個人風格)。RedactareFără avertismente★ 1,1 K↓ —
- pinterest-postskostja94/marketing-skillsWhen the user wants to create Pinterest Pins, optimize Pin descriptions, or grow Pinterest presence. Also use when the user mentions "Pinterest," "Pin," "Pinterest SEO," "Pinterest description," "Pinterest board," or "Pinterest marketing." For asset specs, use visual-content.MarketingFără avertismente★ 1,1 K↓ —
- senior-frontendalirezarezvani/claude-skillsBuild and review React, Next.js, TypeScript or Tailwind frontends: components, scaffolding, performance and bundle size. Use whenever the user wants a new component or app, a page feels slow, the bundle is too big, or asks for a frontend code review.DesignFără avertismente★ 29,3 K↓ —
- 00-arena-routeragentscope-ai/OpenJudgeUse when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.PlanificareFără avertismente★ 1 K↓ —
- hf-cloud-serving-image-selectionhuggingface/skillsPick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.OficialMediaFără avertismente★ 11,3 K↓ —
- baoyu-format-markdownJimLiu/baoyu-skillsFormats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or improve article layout. Outputs to {filename}-formatted.md.RedactareFără avertismente★ 27,3 K↓ —
- deploying-to-staging-environmentAgentWorkforce/relayUse when deploying changes to staging across relay, relay-dashboard, and relay-cloud repos - coordinates multi-repo branch syncing using git worktrees, automatically triggers staging deployments via GitHub ActionsDevOpsFără avertismente★ 1,1 K↓ —
- creating-claude-rulesAgentWorkforce/relayUse when creating or fixing .claude/rules/ files - provides correct paths frontmatter (not globs), glob patterns, and avoids Cursor-specific fields like alwaysApplyPlanificareFără avertismente★ 1,1 K↓ —
- baoyu-electron-extractJimLiu/baoyu-skillsExtracts resources and JavaScript from any installed Electron app (`.asar` bundle), restoring original sources from `.js.map` files when available or formatting minified code with Prettier otherwise. Use when user wants to "extract Electron app", "decompile Electron", "get the source code of <app>", "inspect app.asar", "看 Electron 应用源码", "提取 .asar", or asks how a desktop Electron app is built. Skips `node_modules` and supports both macOS and Windows.InginerieFără avertismente★ 27,3 K↓ —
- browser-testing-with-screenshotsAgentWorkforce/relayUse when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionalityTestareFără avertismente★ 1,1 K↓ —
- planning-with-filesOthmanAdi/planning-with-filesPersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.PlanificareFără avertismente★ 27,9 K↓ —
- Error Resolverforyourhealth111-pixel/Vibe-SkillsLegacy error-resolution reference archive retained for migration. Do not route user tasks here; use systematic-debugging for active bug, stack-trace, and root-cause work.InginerieFără avertismente★ 3,8 K↓ —
- migration-architectalirezarezvani/claude-skillsPlan a safe database, schema, service or data migration: phased plan, compatibility check and rollback scripts. Use whenever the user must move data, change a live schema, switch databases or migrate without downtime.PlanificareFără avertismente★ 29,3 K↓ —
- expense-policymohitagw15856/pm-claude-skillsWrite a clear company expense & reimbursement policy. Use when asked to write an expense policy, a reimbursement policy, a travel & expense (T&E) policy, or spending guidelines. Produces a practical policy — what's covered, limits by category, the approval and submission process, timelines, and what's not reimbursable — that's fair, easy to follow, and reduces finance back-and-forth. Not tax/legal advice.FinanțeFără avertismente★ 1,5 K↓ —
- varg-unboxing-videohashgraph-online/awesome-codex-pluginsTurns product photos into an unboxing or ASMR video ad on varg: hands-only, top-down or POV, the box tapped, opened and the product lifted out and switched on, with native ASMR sound (taps, crinkle, lid pop) and no music, in timed VISUAL / ACTION / SOUND blocks on Seedance 2.5 with the box and the product as references. Unboxing has the highest winner rate of any Meta ad format (9.8%, Motion 2026) while only 2.1% of ads use it. Use when a seller (TikTok Shop, Shopify, dropshipping, Amazon) asks for an unboxing video, an ASMR or satisfying product video, "open the box" content, a packaging reveal, or a hands-only product demo made from photos. Not for talking-head UGC (use ai-ugc-ad-video), the full 60 s guide reel (varg-dropship-reel) or a studio spin of the product alone (product-photo-to-video).MediaFără avertismente★ 1,5 K↓ —
- knowledge-consolidationhuytieu/COG-second-brainBuild frameworks from scattered insights across all braindumps and notesProductivitateFără avertismente★ 1,3 K↓ —Apare și în 1 alt depozit
writing-livekit-scenarios
fcakyon/claude-codex-settings
De la autor
Creates and maintains the scenarios a LiveKit agent simulation runs, and wires the agent to consume them. Use when the user asks "what should I test", "generate simulation scenarios", "write scenarios for my agent", "add a scenario for X", "organize my scenario files", "my simulations are flaky", "the scenario hits my real database", "seed state per scenario", "it passed but booked the wrong thing", "grade the final state", or wants to stress-test a flow before shipping. Covers generating a baseline with the LiveKit scenario generator and refining it, writing the cases generation misses, phrasing simulated-user instructions so they steer reliably, splitting scenarios into sets across files, and the agent-side code that seeds deterministic state from a scenario and fails a run on its final state. To run them use running-livekit-simulations.
Instalare
npx skills add fcakyon/claude-codex-settings --skill writing-livekit-scenarios -a claude-code
Se instalează în .claude/skills/writing-livekit-scenarios/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Fișiere (4)
- SKILL.md
- references/connecting-the-agent.md
- references/risk-coverage.md
- references/scenario-craft.md