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.
49,399 skills from 2,375 repositories · updated 26 minutes ago
49,397 skills
- tao-run-dinov3-ssl-deftNVIDIA/skillsRun iterative DINOv3 SSL DEFT data selection and retraining from an unlabeled pool, using GRIT or multi-task weakness and fixed-encoder retrieval. Use for active-learning-style DINOv3 mining, not plain pretraining/fine-tuning (tao-train-dinov3) or AOI/PAS DEFT.ProductivityNo warnings★ 3.8K↓ —
- clerk-cost-tuningjeremylongshore/tons-of-skills-marketplaceOptimize Clerk costs and understand pricing. Use when planning budget, reducing costs, or understanding Clerk pricing model. Trigger with phrases like "clerk cost", "clerk pricing", "reduce clerk cost", "clerk billing", "clerk budget".PlanningNo warnings★ 2.9K↓ —
- search-to-slackjeremylongshore/tons-of-skills-marketplaceTakes web search results and formats them as polished Slack messages, digests, or thread summaries ready to post to channels. Use when the user wants to research a topic and share findings on Slack. Trigger with phrases like "research and post to Slack", "create a Slack digest", "summarize and share in #channel", or "format search results for Slack".ScienceNo warnings★ 2.9K↓ —
- figure-it-outbacknotprop/pstackDesign an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'.DesignNo warnings★ 3.5K↓ —
- ad-test-designeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试TestingNo warnings★ 3.1K↓ —
- fathom-cost-tuningjeremylongshore/tons-of-skills-marketplaceOptimize Fathom API usage and plan selection. Trigger with phrases like "fathom cost", "fathom pricing", "fathom plan".PlanningNo warnings★ 2.9K↓ —
- ramp-debug-bundlejeremylongshore/tons-of-skills-marketplaceCollect a minimal, safe Ramp API diagnostic bundle centered on trace IDs and reproducible contract evidence. Use when escalating a persistent API, webhook, deferred-task, or accounting failure. Trigger with "Ramp debug bundle" or "Ramp support evidence".EngineeringNo warnings★ 2.9K↓ —
- howmichael-denyer/pstack-claudeUse for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.PlanningNo warnings★ 3.9K↓ —
- bid-strategy-planneraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "pick a bid strategy", "set a tCPA/tROAS target", or "plan the learning-phase entry"; produces a bid-strategy choice (tCPA / tROAS / max-conversions / manual CPC), the starting target math, a portfolio grouping map, and a learning-phase entry plan. Not for splitting the budget across campaigns — use budget-optimizer; not for in-flight pacing/scale moves — use budget-pacing-monitor; not for scoring the account — use ad-account-auditor. 出价策略/tCPA目标/tROAS/学习期PlanningNo warnings★ 3.1K↓ —
- gsd:add-testsdavepoon/buildwithclaudeGenerate tests for a completed phase based on UAT criteria and implementationTestingNo warnings★ 3.7K↓ —
- audit-context-buildingtrailofbits/skillsUnderstand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting an audit, threat model, or architecture review on unfamiliar code, and before any vulnerability-hunting pass.ProductivityNo warnings★ 8K↓ —
- doca-dmaNVIDIA/skillsUse this skill when the user is doing hands-on DOCA DMA programming — bringing up a doca_dma context, configuring the single doca_dma_task_memcpy task type, sizing buffers via the doca_dma_cap_task_memcpy_* queries, setting LOCAL_READ_ONLY / LOCAL_READ_WRITE permissions on source / destination doca_mmap regions (plus doca_mmap_export_* for cross-peer copies), driving the progress engine, or debugging DOCA_ERROR_* returns. Trigger even when the user does not explicitly mention "DOCA DMA" or "doca_mmap" — typical implicit phrasings include "memcpy host buffer to BlueField without using the CPU", "offload a bulk copy to the DPU", "copy returns NOT_PERMITTED on first submit", "buffer too big for one DMA task", "task submitted but no completion", or "scatter-gather copy between two memory regions". Refuse and route elsewhere for cross-network copies (DOCA RDMA), producer/consumer messaging (DOCA Comch), DOCA Core / progress-engine internals, or DOCA install — those belong to other skills.EngineeringNo warnings★ 3.8K↓ —
- wiki-narrateAr9av/obsidian-wikiTurn a wiki topic into a cited Markdown briefing, plain-language explanation, or progressive lecture. Use this skill for topic-based briefing, explanation, and lecture requests that must stay within the evidence compiled in an Obsidian vault.ProductivityNo warnings★ 3.7K↓ —
- principle-separate-before-serializing-shared-statemichael-denyer/pstack-claudeApply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.WritingNo warnings★ 3.9K↓ —
- speak-rate-limitsjeremylongshore/tons-of-skills-marketplaceHandle Speak API rate limits with exponential backoff, request queuing, and optimization strategies. Use when implementing rate limits features, or troubleshooting Speak language learning integration issues. Trigger with phrases like "speak rate limits", "speak rate limits".EngineeringNo warnings★ 2.9K↓ —
- fondo-debug-bundlejeremylongshore/tons-of-skills-marketplaceCollect diagnostic information for Fondo support including integration status, transaction discrepancies, and financial data reconciliation issues. Trigger: "fondo debug", "fondo support", "fondo diagnostic", "fondo reconciliation".EngineeringNo warnings★ 2.9K↓ —
- wiki-updateAr9av/obsidian-wikiSync knowledge from the current project into the Obsidian wiki. Use when work already in the current project should be distilled into the vault; named-vault routing includes @work update wiki. wiki-capture saves the current conversation and wiki-ingest handles external/new sources.ProductivityNo warnings★ 3.7K↓ —
- nemotron-retrieval-recipesNVIDIA/skillsUse when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.DevOpsNo warnings★ 3.8K↓ —
- apify-sdk-patternsjeremylongshore/tons-of-skills-marketplaceProduction-ready patterns for Apify SDK and apify-client in TypeScript. Use when building Actors with Crawlee, managing datasets/KV stores, or implementing robust client wrappers with retry and validation. Trigger with "apify SDK patterns", "apify best practices", "apify client wrapper", "crawlee patterns", "idiomatic apify".BrowserNo warnings★ 2.9K↓ —
- nvshmem-tune-performanceNVIDIA/skillsRoute NVSHMEM tuning to data collection, remote transport, NIC-to-PE mapping, or TMA. Do not use for unrelated CUDA, NCCL, or application tuning.OtherNo warnings★ 3.8K↓ —
- genotoxictrailofbits/skillsGraph-informed mutation testing triage. Parses codebases with Trailmark, runs mutation testing and necessist, then uses survived mutants, unnecessary test statements, and call graph data to identify false positives, missing test coverage, and fuzzing targets. Use when triaging survived mutants, analyzing mutation testing results, identifying test gaps, finding fuzzing targets from weak tests, running mutation frameworks (including circomvent and cairo-mutants), or using necessist.TestingNo warnings★ 8K↓ —
- risk-analysisjeremylongshore/tons-of-skills-marketplaceAnalyze supplied contract clauses and prepare an evidence-linked issue register with triggers, possible impacts and questions for review. Use when assessing contract risks from an identified party's perspective. Trigger with "risk-analysis" or "what are the risks in this contract".LegalNo 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↓ —
- groq-data-handlingjeremylongshore/tons-of-skills-marketplaceUse when you need to keep PII out of Groq API calls, filter model responses, audit-log conversations, or track token cost and usage for a Groq integration. Implements prompt sanitization, PII redaction, response filtering, and usage tracking. Trigger with phrases like "groq data", "groq PII", "groq GDPR", "groq data retention", "groq privacy", "groq compliance".LegalNo warnings★ 2.9K↓ —
tao-finetune-video-clip
NVIDIA/skills
MediaUpdated 20 hours ago
From the author
InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment. Use when the user asks to "fine-tune IV2CLIP", "run video_clip train/evaluate/inference/export", "build a Video-CLIP TensorRT engine", "InternVideo2-CLIP on KPI chunks", or "TAO video_clip on vadr1_chunks JSON".
Install
npx skills add NVIDIA/skills --skill tao-finetune-video-clip -a claude-code
Installs to .claude/skills/tao-finetune-video-clip/ · 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 (17)
- BENCHMARK.md
- SKILL.md
- config/skillspector-baseline.yaml
- eval.config
- evals/evals.json
- references/skill_info.yaml
- references/spec_template_deploy_evaluate.yaml
- references/spec_template_deploy_inference.yaml
- references/spec_template_evaluate.yaml
- references/spec_template_export.yaml
- references/spec_template_gen_trt_engine.yaml
- references/spec_template_inference.yaml
- +5 more