Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
47,966 skills from 2,309 repositories · updated 12 hours ago
47,966 skills
- okx-defiinternet-court/internet-court-skillOKX-aggregated DeFi (no specific DApp named) — product discovery, deposit/withdraw/claim execution, AND positions viewing. **If the user names ANY third-party protocol/DApp (Aave, Lido, PancakeSwap, Uniswap, Curve, Compound, Morpho, Pendle, Kamino, Raydium, Hyperliquid, Polymarket, …), route to okx-dapp-discovery — NOT here, even for 'show my Aave positions'.** INVEST triggers: 'invest in DeFi', 'earn yield', 'find best APY', 'deposit/stake for yield', 'search DeFi products', 'redeem/withdraw position', 'claim DeFi rewards', 'borrow against asset', 'repay loan', 'add/remove CLMM liquidity', 'APY/TVL history', 'depth chart', yield farming, lending, staking, liquidity pools. PORTFOLIO triggers: 'check my DeFi positions', 'view DeFi holdings/portfolio', 'my staking/lending positions', 'DeFi balance', 'DeFi 持仓', '我的DeFi资产'. Do NOT use for: DEX swaps (okx-agentic-wallet), token prices (okx-dex-market), wallet token balances (okx-agentic-wallet).FinanceNo warnings★ 7K↓ —
- dotnet-webapidotnet/skillsGuides creation and modification of ASP.NET Core Web API endpoints with correct HTTP semantics, OpenAPI metadata, and error handling. USE FOR: adding new API endpoints (controllers or minimal APIs), wiring up OpenAPI/Swagger, creating .http test files, setting up global error handling middleware. DO NOT USE FOR: general C# coding style, EF Core data access or query optimization (use optimizing-ef-core-queries), frontend/Blazor work, gRPC services, or SignalR hubs.TestingNo warnings★ 5.8K↓ —
- dotnet-pinvokedotnet/skillsCorrectly call native (C/C++) libraries from .NET using P/Invoke and LibraryImport. Covers function signatures, string marshalling, memory lifetime, SafeHandle, and cross-platform patterns. USE FOR: writing new P/Invoke or LibraryImport declarations, reviewing or debugging existing native interop code, wrapping a C or C++ library for use in .NET, diagnosing crashes, memory leaks, or corruption at the managed/native boundary. DO NOT USE FOR: COM interop, C++/CLI mixed-mode assemblies, or pure managed code with no native dependencies.WritingNo warnings★ 5.8K↓ —
- designlang-tokensManavarya09/design-extractUse when styling UI for coinbase.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.DesignNo warnings★ 4.4K↓ —
- ppt-analysisOpenSenseNova/SenseNova-SkillsPPT (.pptx/.ppt) 全量解析。覆盖：所有 slide 文本/表格/图表提取、嵌入图片 caption、纯图片 slide 渲染识别、数据标签提取。DocumentsNo warnings★ 6K↓ —
- unity-animationgamedev-skills/awesome-gamedev-agent-skillsDrive Unity 6.3 LTS character animation with Animator Controllers: states, transitions, parameters, blend trees, animation layers, and humanoid Avatar IK. Use when wiring an Animator, setting parameters from script (SetFloat/SetBool/SetTrigger), building blend trees, or when the user mentions Animator, Mecanim, state machine, blend tree, or .controller.MediaNo warnings★ 5.8K↓ —
- oncall-irmgrafana/skillsRoute alerts, run on-call rotations, and drive incidents in Grafana IRM / OnCall — integrations (Alertmanager / Grafana Alerting / generic webhook / PagerDuty), Jinja2 routing + grouping templates, escalation chains (wait → notify schedule → notify team → webhook → auto-resolve), schedules (web + iCal + Terraform `grafana_oncall_schedule`), Slack chatops with Acknowledge/Resolve/Silence, and the P1-P4 incident lifecycle. Use when wiring Alertmanager to OnCall, deciding which team gets paged, building rotations from a Google Calendar / iCal, hooking up Slack notifications, or declaring an incident from an alert — even when the user says "page the platform team on critical alerts", "send Prometheus alerts to Slack", "set up our on-call rota", "escalation policy", or "auto-resolve when the alert clears" without naming OnCall / IRM. Heads up — OnCall OSS is in maintenance mode (archived March 2026); Grafana Cloud users should use IRM.OfficialDevOpsNo warnings★ 297↓ —
- time-series-and-categorical-analysisOpenSenseNova/SenseNova-Skills对时间序列或分类数据进行多维度趋势分析、百分比清洗、绩效分级建模与预测，并生成高分辨率的可视化综合报告，适用于业务指标监控与预测场景。OtherNo warnings★ 6K↓ —
- humanize-chinesebrycewang-stanford/Auto-Empirical-Research-SkillsDetect and humanize AI-generated Chinese text. 20+ rule detection categories plus statistical features (sentence-length CV, short-sentence fraction, comma density, perplexity, GLTR, DivEye) plus scene-aware LR fusion (rule × 0.2 + LR × 0.8) trained on three scenes: general / academic / longform 长文本 (≥1500 字)。Unified CLI: ./humanize {detect,rewrite,academic,style,compare}. 8 style transforms (casual/zhihu/xiaohongshu/wechat/academic/literary/weibo/novel)。 Multi-paragraph rewriting (paragraph length CV、跨段 trigram 重复) plus best-of-N humanize (默认 N=10 取最低 LR)。165 replacement patterns + CiLin 同义词词林 38873 with collision blacklist。 Academic paper AIGC reduction for CNKI/VIP/Wanfang (知网/维普/万方 AIGC 检测降重)。 Pure Python, no dependencies, offline。v5.0.0 — HC3 fused 准确率 95%、学术 hero 100→35 (-65)、 工作汇报 96→13 (-83)、长篇博客 96→41 (-55)。 Use when user says: "去AI味", "降AIGC", "人性化文本", "humanize chinese", "AI检测", "AIGC降重", "去除AI痕迹", "文本改写", "论文降重", "知网检测", "维普检测", "AI写作检测", "让文字更自然", "detect AI text", "humanize text", "reduce AIGC scWritingNo warnings★ 4.8K↓ —
- principle-sequence-verifiable-unitsmichael-denyer/pstack-claudeApply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.WritingNo warnings★ 3.7K↓ —
- hex-local-dev-loopjeremylongshore/tons-of-skills-marketplaceConfigure Hex local development with hot reload and testing. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with Hex. Trigger with phrases like "hex dev setup", "hex local development", "hex dev environment", "develop with hex".TestingNo warnings★ 2.9K↓ —
- hex-hello-worldjeremylongshore/tons-of-skills-marketplaceCreate a minimal working Hex example. Use when starting a new Hex integration, testing your setup, or learning basic Hex API patterns. Trigger with phrases like "hex hello world", "hex example", "hex quick start", "simple hex code".TestingNo warnings★ 2.9K↓ —
- linear-hello-worldjeremylongshore/tons-of-skills-marketplaceProve Linear authentication and workspace visibility with the smallest read-only GraphQL or SDK query. Use when establishing a new integration baseline without creating test issues. Trigger with "test Linear connection", "Linear hello world", or "verify Linear API key".TestingNo warnings★ 2.9K↓ —
- kiro-validate-designgotalab/cc-sddInteractive technical design quality review and validationDesignNo warnings★ 3.7K↓ —
- jetson-derive-carrierNVIDIA/skillsBootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for module-level or kernel-DTB changes.OtherNo warnings★ 3.8K↓ —
- offer-claims-registryaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "register this claim", "log our current offers", or "where is the proof for this figure"; curates claim wording, evidence, disclosures, terms, review dates, and live offers through the append-only claims event stream. Not for scoring claim vetoes — use the relevant auditor; not for writing ad copy — use ad-creative-builder. 广告声明台账/优惠信息登记/证据溯源MarketingNo warnings★ 3K↓ —
- exa-rate-limitsjeremylongshore/tons-of-skills-marketplaceBudget Exa throughput per endpoint and distinguish caller rate limiting from vendor overload and billing exhaustion. Use when operating or reviewing this Exa boundary. Trigger with "Exa rate limits", "review Exa rate limits", or "fix Exa rate limits".EngineeringNo warnings★ 2.9K↓ —
- pulumi-neo-handoffpulumi/agent-skillsHand off the current thread to a new Pulumi Neo task as a one-way transfer. Use when the user explicitly asks to hand off, send, transfer, or continue current work in Pulumi Neo (e.g. "hand this to Neo", "continue in Neo", "/neo-handoff"). Do not load when the user only mentions Neo, asks what Neo can do, asks for an AI-written PR or preview explanation, or hands off to a different agent.OfficialWritingNo warnings★ 78↓ —
- principle-guard-the-context-windowbacknotprop/pstackApply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.ProductivityNo warnings★ 3.2K↓ —Also in 1 other repo
- tao-run-dinov3-ssl-deftNVIDIA/skillsRun iterative DINOv3 SSL DEFT data selection and retraining from an unlabeled pool, using GRIT or multi-task weakness and fixed-encoder retrieval. Use for active-learning-style DINOv3 mining, not plain pretraining/fine-tuning (tao-train-dinov3) or AOI/PAS DEFT.ProductivityNo warnings★ 3.8K↓ —
- apify-rate-limitsjeremylongshore/tons-of-skills-marketplaceHandle Apify API rate limits with proper backoff and request queuing. Use when hitting 429 errors, optimizing API request throughput, or implementing rate-aware client wrappers. Trigger with "apify rate limit", "apify throttling", "apify 429", "apify retry", "apify backoff", "too many requests apify".EngineeringNo warnings★ 2.9K↓ —
- kiro-debuggotalab/cc-sddInvestigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.EngineeringNo warnings★ 3.7K↓ —Also in 7 other repos
- kiro-spec-initgotalab/cc-sddInitialize a new specification with detailed project descriptionPlanningNo warnings★ 3.7K↓ —
- cursor-ai-chatjeremylongshore/tons-of-skills-marketplaceMaster Cursor AI Chat with @-mentions, inline edit, and conversation patterns. Triggers on "cursor chat", "cursor ai chat", "ask cursor", "cursor conversation", "chat with cursor", "Cmd+L", "inline edit".WritingNo warnings★ 2.9K↓ —
openrlhf-training
Orchestra-Research/AI-Research-SKILLs
PlanningUpdated Oct 11, 2026
From the author
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill openrlhf-training -a claude-code
Installs to .claude/skills/openrlhf-training/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: MIT
Safety checks on SKILL.md
- Uses sudoLow
Why 91
Security95
Provenance90
Maintenance100
Licence100
Adoption65
Files (5)
- SKILL.md
- references/algorithm-comparison.md
- references/custom-rewards.md
- references/hybrid-engine.md
- references/multi-node-training.md