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.
48,168 skills from 2,325 repositories · updated 3 hours ago
48,168 skills
- arenabacknotprop/pstackSpawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.ProductivityNo warnings★ 3.3K↓ —
- doca-hardware-safetyNVIDIA/skillsUse this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter write, NIC firmware burn, BFB reflash, NIC ↔ DPU mode flip, SR-IOV or device-emulation slot enable, kernel boot-parameter change (IOMMU, hugepages, VFIO), PCIe rebind / rescan / link-state flip, BlueField cold reboot, or remediation of a BlueField thermal shutdown. Wrap the change in pre-flight inventory, OOB reachability, a maintenance window, replica rehearsal, and rollback. Trigger on implicit phrasing: "flip BlueField mode over SSH", "enable SR-IOV and reboot", "burned firmware but mlxconfig shows old value", "BlueField thermal shutdown". Not for read-only inventory or version queries (doca-version, doca-caps). Refuse orientation (doca-public-knowledge-map), install or env debug (doca-setup), and program-side debug (doca-debug, doca-programming-guide).WritingNo warnings★ 3.8K↓ —
- tddwesammustafa/Claude-Code-Everything-You-Need-to-KnowTODOTestingNo warnings★ 3.5K↓ —
- think-harderforyourhealth111-pixel/Vibe-Skills4-phase structured analysis wrapper for vibe pre-routing (compatible with claude-code-settings think-harder semantics).EngineeringNo warnings★ 3.8K↓ —
- hyperplancode-yeongyu/oh-my-openagentAdversarial multi-agent planning: a hostile team cross-critiques a plan before it is formalized. Use when planning needs maximum rigor or the user asks for a hyperplan / adversarial or cross-critique plan.PlanningNo warnings★ 70.5K↓ —
- ultracostdavepoon/buildwithclaudeQuality-first per-stage model routing AND a pre-flight cost gate for Claude Code dynamic workflows. Use when authoring or running ultracode / dynamic-workflow scripts, spawning subagents, or writing agent() stages — pin the right model and effort on every stage, then estimate cost and confirm with the user before launching. Verify scripts with /ultracost:check.WritingNo warnings★ 3.7K↓ —
- gsd:progressdavepoon/buildwithclaudeCheck project progress, show context, and route to next action (execute or plan). Use --forensic to append a 6-check integrity audit after the standard report.SecurityNo warnings★ 3.7K↓ —
- excel-pivot-wizardjeremylongshore/tons-of-skills-marketplaceCreate advanced Excel pivot tables with calculated fields and slicers. Use when building data summaries or creating interactive dashboards. Trigger with phrases like 'excel pivot', 'create pivot table', 'data summary'.DocumentsNo warnings★ 2.9K↓ —
- exa-cost-tuningjeremylongshore/tons-of-skills-marketplaceControl Exa spend through endpoint selection, bounded result and content work, per-key budgets, and response-derived cost evidence. Use when operating or reviewing this Exa boundary. Trigger with "Exa cost tuning", "review Exa cost tuning", or "fix Exa cost tuning".EngineeringNo warnings★ 2.9K↓ —
- vastai-hello-worldjeremylongshore/tons-of-skills-marketplaceRent, verify, use, and destroy a first Vast.ai GPU instance with bounded cost and explicit failure cleanup. Use when running a safe platform canary or onboarding exercise. Trigger with: "rent my first Vast.ai GPU", "run a Vast.ai canary", "test Vast.ai end to end".TestingNo warnings★ 2.9K↓ —
- zarr-pythonforyourhealth111-pixel/Vibe-SkillsChunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.EngineeringNo warnings★ 3.8K↓ —
- anti-ui-slopdavepoon/buildwithclaudeStop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use for web or iOS UI design, implementation, redesign, critique, and pre-ship review in Codex, Claude Code, Cursor, Copilot, and other coding agents.DesignNo warnings★ 3.7K↓ —
- hey-researchNewdavepoon/buildwithclaudeResearches Robinhood Chain (chain id 4663) projects and tokens with HEY Research Lab's public, source-backed record. Use when someone asks about a Robinhood Chain project, token, $TICKER or 0x contract: is it still being built, what did it ship and when, what changed this week, which project a contract belongs to, or what HEY does not know. Read-only, no key. Not price predictions, trading advice or safety verdicts.ScienceNo warnings★ 3.7K↓ —
- vercel-cost-tuningjeremylongshore/tons-of-skills-marketplaceOptimize Vercel costs through plan selection, function efficiency, and usage monitoring. Use when analyzing Vercel billing, reducing function execution costs, or implementing spend management and budget alerts. Trigger with phrases like "vercel cost", "vercel billing", "reduce vercel costs", "vercel pricing", "vercel expensive", "vercel budget".PlanningNo warnings★ 2.9K↓ —
- 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↓ —
- sentry-cost-tuningjeremylongshore/tons-of-skills-marketplaceOptimize Sentry costs, reduce event volume, and manage quota spend. Use when analyzing Sentry billing, reducing error/transaction volume, configuring sampling rates, or preventing overage charges. Trigger: "reduce sentry costs", "sentry billing optimization", "sentry quota management", "optimize sentry spend", "sentry sampling".OtherNo warnings★ 2.9K↓ —
- design-artifactplannotator/effective-htmlDesign principles and creative direction for building HTML artifacts — pages, reports, plans, landing pages, demos, decks, and small tools. Use when creating or restyling any visual HTML deliverable and deciding its palette, type pairing, layout, theming, or overall register, or when the output must not look generically AI-generated.DesignNo warnings★ 3.8K↓ —
- 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↓ —
- splitting-datasetsjeremylongshore/tons-of-skills-marketplaceProcess split datasets into training, validation, and testing sets for ML model development. Use when requesting "split dataset", "train-test split", or "data partitioning". Trigger with relevant phrases based on skill purpose.TestingNo warnings★ 2.9K↓ —
- ramp-common-errorsjeremylongshore/tons-of-skills-marketplaceAnalyze and resolve Ramp API failures using status, error_v2, x-trace-id, OAuth scope, and retry safety. Use when an integration returns 400, 401, 403, 404, 422, 429, 5xx, or 504. Trigger with "Ramp API error" or "Ramp forbidden".EngineeringNo warnings★ 2.9K↓ —
- stakeholder-updatejeremylongshore/tons-of-skills-marketplaceCreate and review stakeholder status updates, progress reports, and executive summaries. Use when the user needs to write concise upward communication. Trigger with "stakeholder update", "status update", "progress report", "update leadership", "weekly update", or "executive summary".WritingNo warnings★ 2.9K↓ —
- ramp-observabilityjeremylongshore/tons-of-skills-marketplaceInstrument Ramp API clients, webhook consumers, deferred tasks, and accounting syncs with safe service and financial-correctness signals. Use when defining dashboards, alerts, traces, or reconciliation health. Trigger with "monitor Ramp integration" or "Ramp observability".DevOpsNo warnings★ 2.9K↓ —
- doca-gpunetioNVIDIA/skillsUse this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the GPU-visible queue, running the dual capability check (DOCA cap-query plus cudaGetDeviceProperties), registering cudaMalloc pools via doca_buf_arr_create_*, or debugging DOCA_ERROR_* returns from the GPUNetIO API. Trigger even when the user does not explicitly mention "DOCA GPUNetIO" or "persistent kernel" — typical implicit phrasings include "CUDA kernel reading packets directly from the NIC", "GPU-initiated networking on BlueField", "DOCA_ERROR_DRIVER on doca_gpu_create", "nvidia_peermem not loaded", "kernel-per-packet is too slow", or "which GPU supports GPU-side packet I/O". Refuse and route elsewhere for general CUDA programming, DOCA Ethernet queue bring-up, DOCA DPA, or DOCA install — those belong to other skills.EngineeringNo warnings★ 3.8K↓ —
- figma-rate-limitsjeremylongshore/tons-of-skills-marketplaceHandle Figma REST API rate limits with exponential backoff and request queuing. Use when encountering 429 errors, implementing retry logic, or optimizing API request throughput for Figma. Trigger with phrases like "figma rate limit", "figma throttling", "figma 429", "figma retry", "figma backoff".DesignNo warnings★ 2.9K↓ —
doca-bf4-deployment
NVIDIA/skills
DevOpsUpdated yesterday
From the author
WARNING: guides IRREVERSIBLE BlueField-4 hardware operations (PLDM firmware burns, ISO reflashes, power cycles, BMC factory resets); every mutating step is governed by doca-hardware-safety (window, rollback). BlueField-4 only: BlueField-3 bring-up is doca-bf3-deployment. Use this skill for BlueField-4 (BF4) day-1 platform bring-up from the BMC: installing the BlueField/DOCA bundle ISO onto the DPU (Grace, the Arm complex) over UEFI HTTP Boot, PXE, or Redfish Virtual Media; the PLDM platform-firmware update via the Redfish UpdateService and pldmtool; and a Grace Ubuntu image with optional cloud-init. Trigger on BlueField-4/BF4 bring-up phrasings even without "BF4": {bring up my new BlueField-4}, {the BlueField ISO will not boot over HTTP from the BMC}, {attach BF4 virtual media via Redfish}, {BF4 firmware Task stuck at Running}, {prepare a BlueField-4 host: platform support, version alignment, safest first smoke test}. Route application launch and library APIs to other skills.
Install
npx skills add NVIDIA/skills --skill doca-bf4-deployment -a claude-code
Installs to .claude/skills/doca-bf4-deployment/ · 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
- CAPABILITIES.md
- SKILL.md
- TASKS.md
- evals/evals.json
- references/details.md
- skill-card.md
- skill.oms.sig