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.
48,622 skills from 2,355 repositories · updated 2 hours ago
48,622 skills
- pulumi-best-practicespulumi/agent-skillsLoad when the user is writing, reviewing, or debugging Pulumi TypeScript/Python programs; asks about Output<T> or apply() usage; wants to create ComponentResource classes; needs to refactor resources without destroying them (aliases); is setting up secrets or config; or is configuring a pulumi preview/up CI workflow. Also load for questions about resource dependency order, parent/child resource relationships, or pulumi.interpolate.OfficialWritingNo warnings★ 78↓ —
- doca-bare-metal-deploymentNVIDIA/skillsRunning a DOCA-linked binary directly on the hardware, with no container or kubelet: on host x86 with a BlueField NIC over PCIe, or bare-metal on BlueField Arm. Use this skill for launching and supervising it (direct, tmux, systemd), and when it "exits 1 right after launch", "systemd keeps restarting it", reports "no matching device on the BF", or the BlueField itself is unhealthy: "bfb-install exited 0 but DPU is dead", "ping 192.168.100.2 works but ssh fails", "host PFs aren't showing netdevs". Refuse service containers under kubelet (doca-container-deployment). Covers PCI/NUMA/CPU/IRQ binding, co-tenant isolation (cgroup-v2/netns/numactl), a seven-layer error taxonomy, platform lifecycle (BFB install, RShim/TMFIFO, host PF rebind, post-BFB recovery) and a six-state BlueField lifecycle classifier. Destructive firmware burn / mlxconfig set requires explicit confirmation via doca-hardware-safety; library APIs, env prep, and build use other skills.DevOpsNo warnings★ 3.8K↓ —
- runway-hello-worldjeremylongshore/tons-of-skills-marketplaceCreate, observe, and preserve one approved Runway text-to-video task using the current per-model contract. Use when proving the first billable generation path. Trigger with: "Runway hello world", "first Runway video", "smoke test Runway generation".TestingNo warnings★ 2.9K↓ —
- coinpaprika-apidavepoon/buildwithclaudeAccess cryptocurrency market data from CoinPaprika: prices, tickers, OHLCV, exchanges, contract lookups for 12,000+ coins and 350+ exchanges. Free tier, no API key needed. Install MCP: add https://mcp.coinpaprika.com/sse as SSE server, or install plugin: /plugin marketplace add coinpaprika/claude-marketplaceEngineeringNo warnings★ 3.7K↓ —
- principle-outcome-oriented-executionmichael-denyer/pstack-claudeApply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.PlanningNo warnings★ 3.7K↓ —
- documentation-lookupforyourhealth111-pixel/Vibe-SkillsUse when the user needs current library, framework, or API documentation and version-specific code examples.PlanningNo warnings★ 3.8K↓ —
- trailmark-structuraltrailofbits/skillsRuns full Trailmark structural analysis by building a graph, running `preanalysis()`, and reporting hotspots, taint, blast radius, privilege boundaries, attack surface, and version-gated Trailmark 0.4+/0.5+ data such as proxy counts, subgraph edges, type/reference summaries, and entrypoint attributes. Use when vivisect needs detailed structural data for a target. Triggers: structural analysis, blast radius, taint analysis, complexity hotspots, proxy nodes, type references.ProductivityNo warnings★ 7.9K↓ —
- doca-compressNVIDIA/skillsHardware compression offload with DOCA Compress on a BlueField DPU, ConnectX NIC, or host: DEFLATE compress and decompress, plus LZ4 decompress (stream and block; LZ4 encode is NOT supported), instead of CPU zlib / zstd. Trigger on "offload this gzip", "decompress incoming network data on the NIC", "compress task returns INVALID_VALUE on alloc_init", "submitted a task but no completion arrives", or "decompress LZ4 on the BlueField", even without naming DOCA Compress. Covers enabling compress-deflate, decompress-deflate, decompress-lz4-stream and decompress-lz4-block tasks on a doca_compress context, sizing source / destination doca_buf against the per-task cap query, mmap permissions, offload vs CPU decisions, a round-trip smoke, and DOCA_ERROR_* from Compress calls. Refuse and route elsewhere for zstd / Snappy / brotli, LZ4 encode (a CPU LZ4 library), pure mmap-to-mmap copies (doca-dma), or DOCA Core lifecycle internals.ProductivityNo warnings★ 3.8K↓ —
- pulumi-overviewpulumi/agent-skillsUse this skill for any task that creates, modifies, inspects, or destroys cloud infrastructure or SaaS configuration, from one-off CLI operations to full multi-resource projects, across providers in the Pulumi ecosystem. A typical project spans many providers (AWS or Azure or GCP, Kubernetes, Cloudflare, Auth0, Datadog, Vercel, and others), and Pulumi drives them through one CLI, one state model, and one credential layer. Trigger even when the user does not name Pulumi; phrasings like "deploy this app," "provision a database," "stand up a VPC," "configure Auth0," "set up Datadog monitoring," or "tear down staging" qualify. Also trigger for tasks that migrate, port, or convert existing infrastructure code (Terraform, CloudFormation, CDK, Bicep, ARM) to Pulumi. Do not trigger for application runtime code that reads or writes data via cloud SDKs; that is application code, not infrastructure.OfficialDevOpsNo warnings★ 78↓ —
- humanize-pptnexu-io/open-designA presentation system for agent-made PPTs — born for the talk, not just the template. It turns raw material into an AST (audience-state-transfer) outline with per-page visual-enhancement decisions (image / SVG diagram / video), hands a production brief to a downstream renderer (HTML-PPT skills or native PPTX), then runs a capped 3-round presentation checkup (演讲体检) on the rendered deck. It never renders slides itself. Use before generating PPT/HTML slides from raw material, and after rendering when the user says things like "给这份 deck 做演讲体检" or "PPT 渲染质检". If all you want is one beautiful template page with no outline and no checkup, a rendering skill alone is enough.WritingNo warnings★ 105.3K↓ —
- task-observerrebelytics/one-skill-to-rule-them-allMonitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology worth preserving to the workspace, turns them into skill updates in a weekly review, and flags repeating work as new skills. Use during ANY multi-step task, agentic workflow, or work session. Also triggers in post-task feedback discussions and when the user mentions skill observations, the observation log, or skill taxonomy. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: invoke this skill before the FIRST tool call of any session and before writing or proposing a plan — any turn that will involve a tool call counts. This sentence is the session-start trigger and the only activation layer that survives an unreachable config file; pair it with a CLAUDE.md instruction or a session-start hook (references/environments.md). A subagent dispatched by a session already running it does not run it: it writes nothing and puts its findings in its report.ProductivityNo warnings★ 3.7K↓ —
- metric-calculatorforyourhealth111-pixel/Vibe-SkillsCompute well-defined metrics from existing formulas, datasets, or test outputs. Use as an explicit/manual helper when the metric definition is already known, not for choosing the overall analysis owner or dashboard strategy.TestingNo warnings★ 3.8K↓ —
- atheristrailofbits/skillsSets up and runs Atheris, the coverage-guided Python fuzzer built on libFuzzer. Covers TestOneInput harnesses, FuzzedDataProvider, instrumenting both pure Python and native C extensions, and running under AddressSanitizer. Use when fuzzing a Python package, hunting memory corruption in a Python C extension, or choosing between Atheris and Hypothesis for a Python target.EngineeringNo warnings★ 7.9K↓ —
- attio-debug-bundlejeremylongshore/tons-of-skills-marketplaceAssemble a minimal redacted Attio diagnostic bundle with request fingerprints, schema context, retry evidence, and environment metadata. Use when escalating an Attio integration failure without leaking CRM data or secrets. Trigger with "Attio debug bundle", "Attio support evidence", or "collect Attio diagnostics".EngineeringNo warnings★ 2.9K↓ —
- Agent Cost Reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.DataNo warnings★ 108.6K↓ —Also in 4 other repos
- property-based-testingforyourhealth111-pixel/Vibe-SkillsProperty-based testing with fast-check (TypeScript/JavaScript) and Hypothesis (Python). Generate test cases automatically, find edge cases, and test mathematical properties. Use when user mentions property-based testing, fast-check, Hypothesis, generating test data, QuickCheck-style testing, or finding edge cases automatically.TestingNo warnings★ 3.8K↓ —
- attio-rate-limitsjeremylongshore/tons-of-skills-marketplaceAnalyze and design an Attio request governor with separate read and write budgets, query-score awareness, bounded retries, and observable backpressure. Use when an Attio integration receives 429 responses or needs safe concurrency controls. Trigger with "Attio rate limits", "Attio 429", or "throttle Attio requests".DesignNo warnings★ 2.9K↓ —
- product-briefjeremylongshore/tons-of-skills-marketplaceStructured product brief and PRD creation assistant. Use when the user needs to create a product brief, PRD, or feature spec that defines what to build and why. Trigger with "product brief", "PRD", "spec", "feature doc", "write a brief", or "define this feature".WritingNo warnings★ 2.9K↓ —
- tao-train-single-stepNVIDIA/skillsStandard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset without iterative data augmentation, AutoML, or DEFT loops. Trigger phrases include "single train run", "train then evaluate then export", "plain TAO training", "normal training", "no AutoML", "skip the loop". Routes through the per-model SKILL.md for action specifics and through `tao-launch-workflow` for platform/credentials/dataset intake.PlanningNo warnings★ 3.8K↓ —
- scholarly-publishingforyourhealth111-pixel/Vibe-SkillsUse when planning an end-to-end scholarly publishing workflow, including manuscript source-of-truth, submission assets, revision/rebuttal files, camera-ready checks, reproducible build expectations, and publication package structure.PlanningNo warnings★ 3.8K↓ —
- brandkitplugin87/ux-ui-agent-skillsGenerate a complete, accessible brand design system from a brief, as primitive → semantic → component DTCG tokens (color, type, spacing, radius, shadow, motion), light + dark, plus a single theme.css, verified for WCAG. Use when the user wants a from-scratch brand/design foundation, a new palette + type system, or a themeable token kit for a product.DesignNo warnings★ 3.1K↓ —
- capturedavepoon/buildwithclaudeSave a memory to Origin in flow. Active capture verb — use proactively when the user states a preference, makes a decision, corrects you, or shares a durable fact. Invoked as `/capture <content>`.ProductivityNo warnings★ 3.7K↓ —
- navan-rate-limitsjeremylongshore/tons-of-skills-marketplaceConfigure Navan integration concurrency and retry controls from the tenant contract and observed responses. Use when controlling throughput or throttling. Trigger with "Navan rate limit", "throttle Navan sync", or "Navan backpressure".LegalNo warnings★ 2.9K↓ —
- x-twitter-scraperdavepoon/buildwithclaudeX (Twitter) data extraction and monitoring via Xquik: tweet search, user lookup, follower extraction, giveaway draws, trending topics, account monitoring with webhooks, reply/retweet/quote extraction, community and Space data, follow checks. 22 MCP tools + REST API.BrowserNo warnings★ 3.7K↓ —
nemo-rl-auto-research
NVIDIA/skills
ScienceUpdated 2 days ago
From the author
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.
Install
npx skills add NVIDIA/skills --skill nemo-rl-auto-research -a claude-code
Installs to .claude/skills/nemo-rl-auto-research/ · 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 90
Security100
Provenance83
Maintenance100
Licence100
Adoption57
Files (8)
- BENCHMARK.md
- SKILL.md
- evals/evals.json
- references/experiment-log-template.md
- references/exploration-ideas.md
- references/git-workflow.md
- skill-card.md
- skill.oms.sig