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.
49.415 skill-uri din 2.407 depozite · actualizat acum 3 ore
49.415 skill-uri
- create-issuefcakyon/claude-codex-settingsThis skill should be used when the user asks to "create an issue", "file a bug", "report a problem", "rewrite an issue", or "improve an issue title or body".AlteleFără avertismente★ 1,2 K↓ —
- cn-5s-auditmohitagw15856/pm-claude-skillsUse when asked 5S 检查表, 6S 管理, 现场管理检查, 5S 评分标准, 车间 6S 稽核, 做一份 5S 推行计划, or design a 5S or 6S audit for a workshop, warehouse or office in a Chinese factory. Produces an audit checklist for the area with scored criteria for 整理, 整顿, 清扫, 清洁, 素养 (and 安全 for 6S), a scoring guide with photo evidence rules, a results summary and red-tag list, a corrective-action tracker with owners and dates, and an audit rota, in Chinese.DesignFără avertismente★ 1,5 K↓ —
- sno-mem-cursorsno-ai/sno-stationUse Sno memory from Cursor through four explicit commands.ProductivitateFără avertismente★ 1 K↓ —
- relational-database-web-cloudbaseTencentCloudBase/CloudBase-AI-Toolkit[Deprecated] Existing CloudBase MySQL Web SDK only. Do not recommend MySQL for new relational apps — use postgresql-development and app.rdb(). Read this only when a browser app must keep using @cloudbase/js-sdk against an environment that already has MySQL.DateFără avertismente★ 1,2 K↓ —Apare și în 5 alte depozite
- podc-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when building the evidence for an ACM PODC paper — where "evidence" is a proof, not a benchmark. Covers matching upper and lower bounds, tightness arguments, model and assumption stress-tests, adversary-strength calibration, and the honest, clearly-optional role of any simulation in a distributed-computing-theory paper.TestareFără avertismente★ 1,4 K↓ —
- write-outreach-reply-readergooseworks-ai/goose-skillsStep of the write-outreach playbook: sorts outreach replies by type, matches each to its prospect row, sets that person's status and keeps useful exact words. Run write-outreach instead; not for direct use.RedactareFără avertismente★ 1,3 K↓ —
- analyze-performance-intakegooseworks-ai/goose-skillsStep of the analyze-performance playbook: gathers the week's numbers from tools, exports and pastes, cleans them, and writes the coverage line or switches to claims-only mode. Run analyze-performance instead; not for direct use.RedactareFără avertismente★ 1,3 K↓ —
- ecommerce-video-adshashgraph-online/awesome-codex-pluginsEcommerce video ad skills for Claude Code and AI agents: plans and makes short product videos that sell on TikTok, TikTok Shop, Instagram Reels and Meta ads, with AI or real footage. Asks the four questions that change the rules (where it runs, product facts, assets, budget), picks angle, hook, format and on-camera character, writes a second-by-second script, keeps the real product identical in AI shots, applies platform rules (AI labels, TikTok Shop bans on AI voices, slideshows and price mentions, the FTC fake-testimonial rule, music licensing), quotes cost before generating and plans different-concept variants. Use when someone wants a viral TikTok, Reels or TikTok Shop video for a product, ecommerce ad creatives or "10 ads for my product". Hands off to product-video-hooks, tiktok-shop-video, ai-ugc-ad-video, product-photo-to-video, ad-creative-testing and ecommerce-video-edit. NOT for app launch videos, music videos or brand films with nothing to sell.MediaFără avertismente★ 1,5 K↓ —
- <slug>gooseworks-ai/goose-skills<What it does and when to use it, in one or two sentences. This is what an agent matches on. At most 1,024 characters.>AlteleFără avertismente★ 1,3 K↓ —
- webhook-managementhoangsonww/Claude-Code-Agent-MonitorConfigure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.TestareFără avertismente★ 1,1 K↓ —
- make-static-ads-graphic-requestgooseworks-ai/goose-skillsMakes one simple non-ad brand graphic, such as an email header, social feed or story image, or a blog or link-preview image, in the brand's style with at most a short line of text, after claim and rights checks and a yes to the quote; returns the link and alt text. Not for carousels, decks or print. Use alone when you already have the purpose, placement and exact wording; otherwise run make-static-ads.MarketingFără avertismente★ 1,3 K↓ —
- long-task-continuationGanyuanRan/AegisUse when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.ProductivitateFără avertismente★ 1,4 K↓ —
- anti-entropy-governanceGanyuanRan/AegisUse when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.AlteleFără avertismente★ 1,4 K↓ —
- icml-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when stress-testing ICML experimental evidence before submission or rebuttal, including strong tuned baselines, mechanism-isolating ablations, seed variance and confidence intervals, compute disclosure, data leakage and split construction, reproducibility, negative results, and fit to ICML soundness, originality, and significance scoring.TestareFără avertismente★ 1,4 K↓ —
- transcript-replayhoangsonww/Claude-Code-Agent-MonitorWalk a Claude Code session transcript turn-by-turn from Agent Monitor data, summarizing each user, assistant, and tool message in order so a long conversation can be reviewed quickly. Anchors the recap to the session header (model, cost, turn_count). Use when reviewing what was actually said and done in a conversation.InginerieFără avertismente★ 1,1 K↓ —
- performance-profileralirezarezvani/claude-skillsUse for a slow endpoint, memory leak, CPU spike, large bundle or performance budget in Node.js, Python or Go, before optimizing. Measures before and after with performance_profiler.py, flamegraphs and k6 load tests.TestareFără avertismente★ 29,3 K↓ —
- usage-trendshoangsonww/Claude-Code-Agent-MonitorAnalyze Claude Code usage trends over time using the Agent Monitor's analytics API — daily session counts, daily event counts, token volumes by type, model distribution, tool usage rankings, and agent/event type distributions across 365-day retention windows.DateFără avertismente★ 1,1 K↓ —
- second-brain-queryundefined-ui/second-brain-osAnswer a question from a second-brain vault by reading its own pages, citing the pages used, and saying plainly when the vault does not contain the answer. Use this skill whenever the user asks what they know about a topic, what they have read on something, what connects two ideas, what they have changed their mind about, or asks any question that should be answered from their own notes rather than general knowledge. Do NOT use for ingesting new material, for general questions the vault has nothing to do with, or when the user explicitly wants an answer from the open web.ProductivitateFără avertismente★ 1,4 K↓ —
- cto-advisoralirezarezvani/claude-skillsCTO decisions: tech debt, architecture direction, scaling the engineering team, technology evaluation, DORA metrics. Use whenever the user asks whether to rewrite, how to grow the eng team or which tech to bet on.PlanificareFără avertismente★ 29,3 K↓ —
- git-worktree-manageralirezarezvani/claude-skillsUse when running several branches or agents in parallel on one repo. Creates worktrees with isolated ports and env via worktree_manager.py and removes stale ones with worktree_cleanup.py.InginerieFără avertismente★ 29,3 K↓ —
- dac-supplementarybrycewang-stanford/Awesome-Journal-SkillsUse when deciding what belongs inside the six reviewed pages of an ACM/IEEE Design Automation Conference (DAC) Research Manuscript versus in an external repository, given DAC's tight 6+1 budget, its references-only seventh page, the double-blind constraint on any linked material, and the absence of a formal reviewed-appendix or artifact-badging track.DesignFără avertismente★ 1,4 K↓ —
- isca-experimentsbrycewang-stanford/Awesome-Journal-SkillsUse when designing or auditing the evaluation of an ISCA paper — pinning simulator fidelity to the claims it must carry, documenting gem5-class configurations and sampling choices, selecting workload suites that represent the claim's domain, tuning baselines in good faith, and separating architectural effect from modeling artifact.ȘtiințăFără avertismente★ 1,4 K↓ —
- remote-collectionhoangsonww/Claude-Code-Agent-MonitorConfigure and troubleshoot CCAM Remote Data Sources that collect Claude Code and Codex history over SSH. Use when adding, editing, testing, syncing, or removing a remote machine, verifying provider paths, or deciding whether to retain or purge imported sessions.TestareFără avertismente★ 1,1 K↓ —
- cloudbase-cliActualizatTencentCloudBase/CloudBase-AI-ToolkitCloudBase CLI (tcb, 云开发CLI, Tencent CloudBase命令行) resource management skill. Use when deploying cloud functions, CloudRun, storage, NoSQL/MySQL, static hosting, permissions, CORS/domains via tcb; for CI/CD and batch ops; when the user prefers CLI; or as the first-session fallback when CloudBase MCP tools are not loaded yet (after install/config, before IDE restart). Also covers tcb login and site switching (国内站/国际站 via --intl or config isIntl), environment lifecycle (env create/modify/renew/delete/apikey/login/domain), tcb config and cloudbaserc.json sync, log search (logs search, CLS), metric monitoring (monitor), data model and PostgreSQL migrations (db model, db pg migration), sandbox/agent/integration management — do not default to tcb deploy.InginerieFără avertismente★ 1,2 K↓ —Apare și în 5 alte depozite
03-ref-hallucination-arena
agentscope-ai/OpenJudge
ȘtiințăActualizat acum 13 ore
De la autor
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
Instalare
npx skills add agentscope-ai/OpenJudge --skill 03-ref-hallucination-arena -a claude-code
Se instalează în .claude/skills/03-ref-hallucination-arena/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Doar instrucțiuniFolosește rețeauaLicență: APACHE-2.0
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență76
Întreținere100
Licență100
Adopție49
Fișiere (1)
- SKILL.md