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.
14,533 skills from 417 repositories · updated 20 hours ago
895 skills
- clay-observabilityjeremylongshore/tons-of-skills-marketplaceMonitor Clay enrichment pipeline health, credit consumption, and data quality metrics. Use when setting up dashboards for Clay operations, configuring alerts for credit burn, or tracking enrichment success rates. Trigger with phrases like "clay monitoring", "clay metrics", "clay observability", "monitor clay", "clay alerts", "clay dashboard", "clay credit tracking".DevOpsNo warnings★ 2.9K↓ —
- castai-cost-tuningjeremylongshore/tons-of-skills-marketplaceAnalyze CAST AI cost, available-savings, and realized-savings reports into a defensible optimization plan. Use when investigating spend, validating savings claims, applying private-price adjustments, or prioritizing workloads and clusters. Trigger with: "tune CAST AI costs", "verify CAST AI savings", "reduce Kubernetes spend with CAST AI".DevOpsNo warnings★ 2.9K↓ —
- anth-observabilityjeremylongshore/tons-of-skills-marketplaceSet up observability for Claude API integrations with metrics, logging, and alerting for latency, cost, errors, and token usage. Trigger with phrases like "anthropic monitoring", "claude observability", "anthropic metrics", "track claude usage", "claude dashboard".DevOpsNo warnings★ 2.9K↓ —
- navigating-githubjeremylongshore/tons-of-skills-marketplaceFirst-time GitHub setup and interactive git learning. Walks users from zero to a working GitHub repo, then teaches git through 9 hands-on lessons on their actual project. Adapts language and depth to skill level — inferred from environment, not questionnaires. Two modes: Setup (guided onboarding) and Learn (progressive curriculum from commits to CI/CD). Use when the user asks to set up GitHub, learn git, or says "teach me github". Trigger with "set up my repo", "help me with github", "teach me github", "learn git", "what are branches", "teach me PRs", or "how do I use github".DevOpsNo warnings★ 2.9K↓ —
- agent-platform-eval-flywheelgoogle/skillsMeasures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when generating synthetic user scenarios, evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For general production deployment, use agent-platform-deploy.OfficialDevOpsNo warnings★ 21.5K↓ —
- eu-ai-actSushegaad/Claude-Skills-Governance-Risk-and-ComplianceEU AI Act (Regulation (EU) 2024/1689) compliance advisor — risk classification across all four tiers, all 9 prohibited practices (Art. 5, including the nudification/CSAM prohibition from Dec 2, 2026), all 8 Annex III high-risk use case areas, provider and deployer obligations (Arts. 9–17, 26), GPAI model obligations including the July 2025 Code of Practice (Arts. 51–55), conformity assessment and CE marking (Arts. 43–48), EU AI database registration, Art. 50 transparency (chatbots, synthetic media, AI-generated content), governance (AI Office, AI Board), penalties (Art. 99), confirmed phase-in timeline (Digital Omnibus, Reg. (EU) 2026/1744, in force July 27, 2026: Annex III deferred to Dec 2, 2027; Annex I to Aug 2, 2028), and cross-framework mapping to ISO 42001, NIST AI RMF, and GDPR. Use for any EU AI regulation, AI system classification, or AI compliance question. Current as of August 2026. GPAI enforcement powers active since August 2, 2026.DevOpsNo warnings★ 976↓ —
- add-vercelnanocoai/nanoclawAdd Vercel deployment capability to NanoClaw agents. Installs the Vercel CLI in agent containers and sets up OneCLI credential injection for api.vercel.com. Use when the user wants agents to deploy web applications to Vercel.DevOpsNo warnings★ 31K↓ —
- wrap-upalirezarezvani/claude-skillsClose out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says "wrap up", "close this out", "what do I own now", "give me the summary", "recap the agent", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained ./my-agent/agent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.DevOpsNo warnings★ 28.5K↓ —
- hf-cloud-sagemaker-iam-preflighthuggingface/skillsEnsure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.OfficialDevOpsNo warnings★ 11.2K↓ —
- hf-cloud-sagemaker-production-defaultshuggingface/skillsCreate a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.OfficialDevOpsNo warnings★ 11.2K↓ —
- pinmeglitternetwork/pinmeUse this skill when the user mentions "pinme", or needs to upload files, store to IPFS, create/publish/deploy websites or full-stack services (including frontend pages, backend APIs, database storage, email sending, etc.), or any feature requiring backend database/server support.DevOpsNo warnings★ 3.8K↓ —
- pinme-r2glitternetwork/pinmeUse when a PinMe Cloudflare Worker needs R2 object storage, including secure file or image upload, streaming download, metadata lookup, deletion, listing, Range requests, or R2+D1 coordination. Guides AI to use PinMe's automatically injected env.R2 binding without R2 credentials or manual Wrangler configuration.DevOpsNo warnings★ 3.8K↓ —
- pinme-shareglitternetwork/pinmeUse this skill when the user wants to share, publish, or upload a static result through PinMe, especially by generating a static HTML share page for a PinMe project link, deployed full-stack app, Codex conversation summary, report, file, demo, or any 分享/发布/上传分享页 request that should end with `pinme upload`.DevOpsNo warnings★ 3.8K↓ —
- pinme-uniwebpayglitternetwork/pinmeUse when generating, modifying, or reviewing PinMe Worker (Cloudflare Worker TypeScript) code that accepts payments through UniwebPay — payment links, products/prices, checkout sessions, payment status reads, refunds, subscriptions, or handling UniwebPay webhooks with @uniwebpay/sdk in a PinMe project.DevOpsNo warnings★ 3.8K↓ —
- doca-comchNVIDIA/skillsUse this skill when the user is doing hands-on DOCA Comch work on a host + BlueField pair — bringing up host ↔ DPU PCIe control-plane messaging, picking server (DPU) vs client (host) roles, choosing slow-path send-task / recv-callback vs fast-path producer / consumer, querying max-msg-size or max-clients capabilities, registering connection callbacks, or debugging DOCA_ERROR_* returns from the Comch API. Trigger even when the user does not explicitly mention "DOCA Comch" or "Comm Channel" (renamed in DOCA 2.5) — typical implicit phrasings include "send a control message from host to BlueField over PCIe", "DPU can't see the host representor", "DOCA_ERROR_NOT_PERMITTED on server_create", "DOCA_ERROR_AGAIN on task_send submit", "connect callback never fires", or "stream bulk data from a host driver to a DPU agent". Refuse and route elsewhere for installing DOCA itself, BFB / firmware bring-up, non-Comch DOCA libraries, or deploying Comch apps at scale — those belong to other skills.DevOpsNo warnings★ 3.7K↓ —
- launch-nemo-rlNVIDIA/skillsPlaybook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.DevOpsNo warnings★ 3.7K↓ —
- rtvi-cv-customize-modelNVIDIA/skillsHow to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2d_cv) mode - covers ONNX export, custom bbox parsers, compose mount gotchas, nvinfer config, runtime TRT engine build, deployment, and a segmentation-capable model addendum handoff.DevOpsNo warnings★ 3.7K↓ —
- release-itciembor/agent-rules-booksApply Michael T. Nygard-inspired production reliability rules when designing failure handling, timeouts, retries, circuit breakers, observability, or deployment behavior.DevOpsNo warnings★ 3.1K↓ —
- brooks-debthyhmrright/brooks-lintTech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refactoring roadmap — drawing on twelve classic engineering books. Triggers when: user asks about tech debt, refactoring priorities, what to clean up first, or asks "why is this so hard to change?", "what should we fix first?", or "how do I justify refactoring to management?". Do NOT trigger for: server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime — "health" in those contexts is infrastructure, not code quality. Also not for single-function refactoring questions.DevOpsNo warnings★ 1.5K↓ —
- model-cardmohitagw15856/pm-claude-skillsDocument a deployed ML/AI model so others can use it responsibly. Use when asked to write a model card, document a model's intended use and limitations, or prepare an AI model for review/launch. Produces a complete model card — intended use, training data, evaluation metrics across slices, limitations, ethical considerations, and a deployment checklist.DevOpsNo warnings★ 1.5K↓ —
- handbook-pagemohitagw15856/pm-claude-skillsWrite the handbook page that ends the repeated explanation — the answer-shaped structure (task-first, context second), the ownership and freshness header, and the write-once-point-forever discipline that turns tribal knowledge into infrastructure. Use when asked document how we do X, write the wiki page for this process, I explain this every month, or make this knowledge survive me. Produces the page with task-first structure, the header block, the worked example, and the pointer habit.DevOpsNo warnings★ 1.5K↓ —
- legacy-lettermohitagw15856/pm-claude-skillsWrite a letter to the people you love, to be read later — the things you'd want them to know, the stories only you hold, the permission and the love that outlive you. Use when someone says 'help me write a letter to my kids/partner', 'legacy letter', 'ethical will', 'something for them to have when I'm gone', or is facing illness, aging, deployment, or simply wants to. Produces a warm, true letter in the writer's own voice — one to each person, or one to all — plus a light plan for when and how it's found. An emotional-legacy tool, not legal (it is not a will).DevOpsNo warnings★ 1.5K↓ —
- devops-infrastructureCloudAI-X/claude-workflow-v2Guides Docker, CI/CD pipelines, deployment strategies, infrastructure as code, and observability setup. Use when writing Dockerfiles, configuring GitHub Actions, planning deployments, setting up monitoring, or when asked about containers, pipelines, Terraform, or production infrastructure.DevOpsNo warnings★ 1.4K↓ —
- release-runbookamplifthq/openmeldUse when asked to deploy, release, publish, or ship OpenMeld to production — workers, Web, CLI, or local components. Routes to `pnpm run deploy`; never deploy raw.DevOpsNo warnings★ 1.4K↓ —