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.
49,492 skills from 2,391 repositories · updated 9 hours ago
48,451 skills
- model-mixhoangsonww/Claude-Code-Agent-MonitorBreak down Claude Code usage by model family (Opus / Sonnet / Haiku) from the Agent Monitor dashboard — each family's share of tokens, share of cost, and the spots where an expensive model is doing cheap work. Pulls per-model token and cost splits from /api/pricing/cost, current rates from /api/pricing, fleet token totals from /api/analytics, and per-session model assignment from /api/sessions. Use when deciding model routing or whether to downshift work to a cheaper tier.DataNo warnings★ 1.1K↓ —
- title-tagkostja94/marketing-skillsWhen the user wants to write, audit, or optimize an HTML title tag, SEO title, page title, SERP title, browser-tab title, duplicate title, or title rewrite issue. For a sitewide metadata lifecycle including implementation and production validation, use page-metadata.BrowserNo warnings★ 1.1K↓ —
- hf-cloud-python-env-setuphuggingface/skillsSet up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.OfficialEngineeringNo warnings★ 11.3K↓ —
- run-historyhoangsonww/Claude-Code-Agent-MonitorInspect CCAM dashboard-run history and relate live run handles to persisted Claude Code or Codex sessions. Use when finding a prior launched task, checking whether a run is still attached, reviewing start/end status, or deciding whether to resume, view, or relaunch work.EngineeringNo warnings★ 1.1K↓ —
- error-scanhoangsonww/Claude-Code-Agent-MonitorScan recent Claude Code activity for errors and failure signals across all sessions using Agent Monitor data — APIError events and PreToolUse→PostToolUse gaps (tools that started but never completed) — then group failures by tool and model and rank them by frequency. Use when checking for errors or asking "what's failing right now".EngineeringNo warnings★ 1.1K↓ —
- writing-relayflowsAgentWorkforce/relayUse when authoring a Relayflows flow (@relayflows/surface / @relayflows/sdk, the journal-based v2 engine — the CLI is `flows`, package versions 2.0.x) in TypeScript or YAML/JSON. Covers the three-rung ladder (run/llm/agent), the resident verbs (human/dispatch/done), verification gates, TypeScript vs YAML authoring, per-step cli/model selection and its resolution order, flows.json, and `flows check`/`run`/`resume` with their real refusal shapes and exit codes. Not for the older, unrelated `@relayflows/core` WorkflowBuilder engine (`.pattern('dag')`/.agent()/.step() chains) that `writing-agent-relay-workflows` and `migrating-persona-to-relayflow` cover — that's a different product despite the similar name.WritingNo warnings★ 1.1K↓ —
- dag-maphoangsonww/Claude-Code-Agent-MonitorRender the multi-agent orchestration DAG for a session — parent→child subagent edges, tree depth, and fan-out — from the Agent Monitor workflow intelligence API. Cross-checks the orchestration dataset against the raw agent records and session detail. Use when visualizing how a session's agent structure was organized.MediaNo warnings★ 1.1K↓ —
- slo-checkhoangsonww/Claude-Code-Agent-MonitorDefine and check simple service-level objectives for Claude Code from Agent Monitor data — session completion rate, tool success rate (PostToolUse/PreToolUse), and error rate (APIError/total) — then compare each to its target and report the error budget remaining. Use when reporting reliability or when someone asks "are we meeting our SLOs?".EngineeringNo warnings★ 1.1K↓ —
- run-agenthoangsonww/Claude-Code-Agent-MonitorLaunch and supervise Claude Code or Codex through the CCAM Run API. Use when the user wants to start a monitored agent, select a model, approval policy, sandbox, or working directory, send a follow-up, inspect live output, resume a native session, or stop a dashboard-launched run.EngineeringNo warnings★ 1.1K↓ —
- gamehashgraph-online/awesome-codex-pluginsMake or change a rules-plus-view multiplayer web game inside a Homie studio — the server runs the rules, each browser predicts its own movement and renders the game, strangers meet in public rooms, bots fill empty seats, rounds end and restart — prove it with two browsers finishing a round, and give it an epic landing page (a full-bleed hero from its own footage or art, the pitch, Play, phone / computer / TV, live rooms, how to play, credits). Use when someone in a Homie studio (a folder with studio.json) asks for a new game, a change to a game, a game whose own AI decides (opponents picking tactics, an NPC's reaction, a director's call, a turn's move), or a better page for a game ("make my game's landing page epic").DesignNo warnings★ 1.5K↓ —
- bug-diagnosismohitagw15856/pm-claude-skillsDiagnose a bug systematically instead of guessing — reproduce, isolate, form hypotheses, and test them to root cause. Use when debugging, chasing a defect, an intermittent failure, or 'why is this happening?'. Produces a structured diagnosis: a reliable repro, the narrowed-down location, ranked hypotheses with how to test each, and the root cause + fix once found.TestingNo warnings★ 1.5K↓ —
- huggingface-vision-trainerhuggingface/skillsTrains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.OfficialMediaNo warnings★ 11.3K↓ —
- add-mcscopilotmicrosoft/power-platform-skillsAdds Microsoft Copilot Studio connector to a Power Apps code app. Use when invoking Copilot Studio agents, sending prompts to agents, or integrating agent responses.EngineeringNo warnings★ 1.1K↓ —
- huggingface-community-evalshuggingface/skillsRun evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.OfficialOtherNo warnings★ 11.3K↓ —
- huggingface-paper-publisherhuggingface/skillsPublish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.OfficialScienceNo warnings★ 11.3K↓ —
- youtube-video-kithuytieu/COG-second-brainSelf-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.MediaNo warnings★ 1.3K↓ —
- stripe-paymentsjezweb/claude-skillsAdd Stripe payments to a web app — Checkout Sessions, Payment Intents, subscriptions, webhooks, customer portal, and pricing pages. Covers the decision of which Stripe API to use, produces working integration code, and handles webhook verification. No MCP server needed — uses Stripe npm package directly. Triggers: 'add payments', 'stripe', 'checkout', 'subscription', 'payment form', 'pricing page', 'billing', 'accept payments', 'stripe webhook', 'customer portal'.EngineeringNo warnings★ 1.1K↓ —
- train-sentence-transformershuggingface/skillsTrain or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.OfficialProductivityNo warnings★ 11.3K↓ —
- postgresql-planningamplifthq/openmeldPlan and implement OpenMeld PostgreSQL business persistence, schemas and migrations, transactions, Hyperdrive access, and data cutover. Use for the shared relational database transition or PostgreSQL work; not for unrelated D1 performance fixes or OpenConnector's upstream database.DataNo warnings★ 1.4K↓ —
- http-api-cloudbaseUpdatedTencentCloudBase/CloudBase-AI-ToolkitCloudBase official HTTP API client guide. This skill should be used when backends, scripts, or non-SDK clients must call CloudBase platform APIs over raw HTTP instead of using a platform SDK or MCP management tool.EngineeringNo warnings★ 1.2K↓ —
- azure-usagefcakyon/claude-codex-settingsThis skill should be used when user asks to "query Azure resources", "list storage accounts", "manage Key Vault secrets", "work with Cosmos DB", "check AKS clusters", "use Azure MCP", or interact with any Azure service.DevOpsNo warnings★ 1.2K↓ —
- cloudbase-miniprogramTencentCloudBase/CloudBase-AI-ToolkitUse when building a WeChat Mini Program (微信小程序 / 小程序) with a real backend on 腾讯云开发 CloudBase — from an idea to a published release. Triggers on: 小程序, 微信小程序, wx.cloud, 云开发, 云函数, 数据库, 集合, 云存储, 上传图片, 登录, openid, 订阅消息, 支付, 体验版, 预览, 上传代码, 提交审核, 发布, 合法域名, 真机调试, 分包. Covers project scaffolding, project.config.json / appid / miniprogramRoot, the wx.cloud data path, cloud functions, storage, auth, subscription messages, and the preview → upload → review → release chain. Do NOT use for Web/H5 frontends (use a web skill), pure backend services, or mini programs that do not use CloudBase.EngineeringNo warnings★ 1.2K↓ —
- planhashgraph-online/awesome-codex-pluginsPlan a game or app with the person before building it — sensible defaults from their request, with an interview only when requested that ends in the game's Game Codex, games/<id>/CODEX.md, drawn as a page in the game's own palette, fonts and art that anyone can read and steer (a Claude artifact where the app has artifacts, else a page in their browser, and a private page on the studio's site), kept true as decisions change, with the build's progress on it. Use for step 4 of a new studio, or when someone says "let's plan my game", "what should my game be", "make a design doc, a game bible or a codex", "show me the plan", or before a big change to a game.PlanningNo warnings★ 1.5K↓ —
- brainstormingmohitagw15856/pm-claude-skillsRun a real brainstorm — divergent generation without judgment, then convergent selection with explicit criteria — instead of listing ten obvious ideas and calling it creativity. Use when asked to brainstorm, generate ideas or options, explore a solution space, or name something. Produces a genuinely wide option set (including the weird tail), then a shortlist selected against named criteria with the rejects preserved.PlanningNo warnings★ 1.5K↓ —
review-fix-signoff-loop
AgentWorkforce/relay
EngineeringUpdated 15 hours ago
From the author
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts, iteration-count reporting, PR signoff comments, and blocked-state handling.
Install
npx skills add AgentWorkforce/relay --skill review-fix-signoff-loop -a claude-code
Installs to .claude/skills/review-fix-signoff-loop/ · 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 onlyNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance76
Maintenance100
Licence100
Adoption49
Files (1)
- SKILL.md