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.
49,421 skills from 2,375 repositories · updated 7 minutes ago
49,421 skills
- writing-lean-proofstrailofbits/skillsWrites and reviews structured Lean 4 proofs and designs Lean libraries following Mathlib conventions. Use when proving theorems in Lean, formalizing mathematics or specifications in Lean 4, defining new types or definitions in a Lean library, reviewing Lean proofs for readability and maintainability, refactoring long tactic proofs into lemmas, filling in sorry placeholders in a Lean development, setting up CI or linters for a Lean project, diagnosing slow proofs or maxHeartbeats timeouts, or writing custom tactics, macros, or linters.WritingNo warnings★ 8K↓ —
- i4h-workflow-e2eNVIDIA/skillsRun the maintained workflow data-to-policy pipeline from recording through checkpoint validation. Use for full end-to-end requests; do not use for one individual stage.TestingNo warnings★ 3.8K↓ —
- tao-train-rtdetrNVIDIA/skillsRT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO RT-DETR model. Trigger phrases include "train RT-DETR", "real-time DETR", "low-latency object detection", "RT-DETR distillation / quantization".DevOpsNo warnings★ 3.8K↓ —
- outlook-automationdavepoon/buildwithclaudeAutomate Outlook tasks via Rube MCP (Composio): emails, calendar, contacts, folders, attachments. Always search tools first for current schemas.ProductivityNo warnings★ 3.7K↓ —
- message-test-designeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "test our messaging before we scale it", "design a message-market-fit panel", or "run a 5-second comprehension test on our new tagline"; produces a message-test design spec — hypothesis, panel and recruit criteria, comprehension / 5-second / message-market-fit (Wynter-style) protocols, stimulus set drawn from the canon, success thresholds, and a stop/revise decision rule — for the TALE Evaluate phase so the message is validated before any paid scale. It designs the test; it never runs the experiment or adjudicates a claim. Not for running the panel or A/B experiment — use send-experiment-designer or ad-test-designer; not for analyzing the results — use performance-analyzer; not for authoring the message itself — use message-system-architect. 消息测试/理解度测试/面板设计/五秒测试/消息市场契合TestingNo warnings★ 3.1K↓ —
- cohere-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement Cohere endpoint-aware throttling, bounded retry, and queue backpressure from current limits and observed responses. Use when handling 429s or planning throughput. Trigger with "Cohere rate limit", "Cohere throttling", or "Cohere 429".PlanningNo warnings★ 2.9K↓ —
- doca-flow-tuneNVIDIA/skillsUse this skill when the user is tuning a live or captured `doca-flow` pipeline with `doca_flow_tune` — snapshotting pipe / counter / KPI state, picking a tuning axis (rule placement, resource hints / table sizing, HW-offload mode) and a matching measurement (rule-install rate, lookup latency, hardware-counter delta), running offline or online (read-only or state-changing) modes, reading the dumper CSV / analyze JSON / visualize mermaid, or applying a recommendation back into the Flow program. Trigger even when the user does not explicitly mention "doca_flow_tune" — typical implicit phrasings include "Flow rule-install rate is low on BlueField", "table sizing looks wrong for this pipe", "tune visualize step is empty", "before/after counters don't move", or "which doca-flow knob does this recommendation hit". Refuse and route elsewhere for writing the doca-flow application, DOCA install, or streaming Flow telemetry — those belong to other skills.DataNo warnings★ 3.8K↓ —
- nvflare-orientNVIDIA/skillsRoute open-ended NVFLARE advice and only conversion requests whose preliminary source inspection reports unresolved or conflicting ownership; never load this skill merely to inspect a concrete conversion request before selecting its detected framework converter.MarketingNo warnings★ 3.8K↓ —
- cleanup-codejeremylongshore/tons-of-skills-marketplaceComprehensive codebase cleanup across 11 quality dimensions: dead code, duplication, weak types, circular deps, defensive cruft, legacy code, AI slop, type consolidation, security, performance, and async patterns. Analyzes code with confidence scoring and verifies changes with build/test gates. Use when codebase has accumulated tech debt, after major feature work, before releases, or when code quality metrics are declining. Trigger with "/cleanup-code-code", "clean up the codebase", "remove dead code", "fix code quality".EngineeringNo warnings★ 2.9K↓ —
- gsd:shipdavepoon/buildwithclaudeCreate PR, run review, and prepare for merge after verification passesEngineeringNo warnings★ 3.7K↓ —
- gsd:cleanupdavepoon/buildwithclaudeArchive accumulated phase directories from completed milestonesOtherNo warnings★ 3.7K↓ —
- tao-launch-workflowNVIDIA/skillsThe mandatory pre-launch gate and four-verb execution contract for every TAO workflow or action. Invoke BEFORE launching anything side-effecting — AutoML, train, evaluate, inference, export, TensorRT engine generation, or DEFT/application workflows — on any execution platform. Covers platform selection, credentials, image confirmation, dataset intake, preflight, the launch review, job records, monitoring, and failure/retry classification. Trigger phrases include "train this model", "run AutoML", "launch on SLURM/docker/k8s/brev/virtualenv", "evaluate my checkpoint", "start a TAO job".ProductivityNo warnings★ 3.8K↓ —
- speak-install-authjeremylongshore/tons-of-skills-marketplaceSet up Speak language learning API integration and authentication. Use when configuring Speak API access, setting up OAuth with OpenAI Realtime API for speech, or initializing a language tutoring application. Trigger with phrases like "install speak", "setup speak", "speak auth", "configure speak API", "speak language learning setup".EngineeringNo warnings★ 2.9K↓ —
- doca-urom-svcNVIDIA/skillsOperate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using `doca-urom`: pull the NGC image, choose the UCX component, size queues, configure Comch pairing, and align host and service versions. SECURITY: the service has no standalone access control; Comch pairing and RDMA permissions are the boundary. Pair only intended hosts, expose least-privilege memory regions, and verify both views before start. Trigger for slow UCX collectives, unexpected NOT_PERMITTED, or missing completions. Do not use for host application code, MPI/UCX integration design, or DOCA install.SecurityNo warnings★ 3.8K↓ —
- skill-creatoranthropics/financial-servicesGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.OfficialPlanningNo warnings★ 41K↓ —Also in 4 other repos
- doca-benchNVIDIA/skillsRun `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for RDMA, Compress, AES-GCM, SHA, DMA, EC, Ethernet, Comch, or GPUNetIO on a host or BlueField Arm. Use it to discover enabled benchmark libraries, capture a reproducible command/version/device/environment baseline, compare stable runs against a declared tolerance, or diagnose configuration, device-binding, workload-precondition, and measurement failures. Trigger for requests such as measuring BlueField compression speed, NIC RDMA throughput, crypto latency, or a pre-upgrade baseline. Do not use for application end-to-end timing, custom benchmark code, DOCA installation, or binary patches.FinanceNo warnings★ 3.8K↓ —
- drill-medavepoon/buildwithclaudeTeach the user a topic as an adaptive tutor — retrieval practice, spaced repetition with decay, and persistent memory in ~/.drill-me/. Use when the user wants to learn or be drilled on something, says "drill me on X", "teach me X", or wants to study a topic, a codebase, or a document.ProductivityNo warnings★ 3.7K↓ —
- proof-point-packageraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "package our proof points", "build reusable stat cards and case snippets", or "put proof where each pillar makes its claim"; turns claims-ledger-approved proofs into reusable proof modules — stat cards, case snippets, testimonial blocks, comparison proofs — each pinned to a message-house pillar and the ledger claim ID it substantiates, and flags any pillar making a claim with no approved proof behind it. Never adjudicates a proof: unverified or ledger-absent proofs are marked '[needs source]' and routed to the claims candidates. Not for adjudicating or substantiating claims — use offer-claims-registry; not for fabricating a benchmark to fill a gap — a missing proof is flagged, not invented; not for scoring narrative quality — use narrative-quality-auditor. 证据模块/证据卡/客户案例/主张对齐OtherNo warnings★ 3.1K↓ —
- principle-fix-root-causesbacknotprop/pstackApply when debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.EngineeringNo warnings★ 3.5K↓ —Also in 1 other repo
- gsd:join-discorddavepoon/buildwithclaudeJoin the GSD Discord communityOtherNo warnings★ 3.7K↓ —
- fix-cimichael-denyer/pstack-claudeFind failing PR checks, inspect logs or external check links, and apply focused fixesOtherNo warnings★ 3.9K↓ —
- datamodel-code-generatordatamodel-code-generator/datamodel-code-generatorUse this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects. Use it for requests such as "Pydantic models from this schema", "types for this API", "parse this JSON into classes", or "convert this spec into Python models". Prefer the datamodel-codegen CLI over hand-written model code whenever an input schema, API spec, sample data file, or Python model object exists.EngineeringNo warnings★ 4K↓ —
- gsd:managerdavepoon/buildwithclaudeInteractive command center for managing multiple phases from one terminalOtherNo warnings★ 3.7K↓ —
- redesignplugin87/ux-ui-agent-skillsUpgrade an existing website or app to premium quality without breaking functionality. Audit the current design, identify generic/AI tells, then apply taste and system rules surgically. Use when the user wants to improve, modernize, polish, or "make better" an existing UI/codebase.DesignNo warnings★ 3.1K↓ —
jetson-video-recipe
NVIDIA/skills
MediaUpdated 16 hours ago
From the author
Use when turning a Jetson encoder use case into one surface-neutral recipe with native Video Codec SDK and PyNvVideoCodec projections.
Install
npx skills add NVIDIA/skills --skill jetson-video-recipe -a claude-code
Installs to .claude/skills/jetson-video-recipe/ · 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 (7)
- BENCHMARK.md
- SKILL.md
- evals/evals.json
- references/recipes-knobs-and-constraints.md
- references/recipes-workflow.md
- skill-card.md
- skill.oms.sig