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
- readdavepoon/buildwithclaudePreview a distilled wiki page from inside Claude Code. Prints title, summary, source count, and the local md path. Full body lives on disk — open with the user's editor. Invoked as `/read <title_or_id>`.WritingNo warnings★ 3.7K↓ —
- gsd:updatedavepoon/buildwithclaudeUpdate GSD to latest version with changelog displayOtherNo warnings★ 3.7K↓ —
- principle-redesign-from-first-principlesmichael-denyer/pstack-claudeApply when integrating a new requirement into an existing design.DesignNo warnings★ 3.9K↓ —
- provider-actionshashicorp/agent-skillsImplement Terraform Provider actions using the Plugin Framework. Use when developing imperative operations that execute at lifecycle events (before/after create, update, destroy).OfficialDevOpsNo warnings★ 911↓ —
- gsd:shipdavepoon/buildwithclaudeCreate PR, run review, and prepare for merge after verification passesEngineeringNo warnings★ 3.7K↓ —
- social-quality-auditoraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "audit our social presence" or "is this batch safe to publish"; runs either the typed ECHO asset gate or a separate program-maturity profile, with channel-truth, claim, disclosure, manipulation, UGC-rights, and denominator checks. Not for creator deliverables — use creator-content-auditor; not for launch readiness — use launch-readiness-auditor. 社媒资产门/运营成熟度/发布前放行OtherNo warnings★ 3.1K↓ —
- newsletter-monetization-planneraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "monetize my newsletter", "build a sponsorship rate card", or "model paid-subscription revenue"; produces a revenue model (paid tiers, ad/sponsorship inventory + CPM/flat rate card, referral/boost loops), a list-growth ↔ revenue projection, and honest-offer / disclosure checks for the SEND-D lever. Not for scoring the whole program or running D1 — use email-quality-auditor; not for the return math — use roi-calculator; not for the post-click page — use landing-optimizer. 邮件newsletter变现/赞助刊例/付费订阅测算MarketingNo warnings★ 3.1K↓ —
- interrogatemichael-denyer/pstack-claudeUse for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Adversaries try to break a change or design, and only findings proven by a run survive.TestingNo warnings★ 3.9K↓ —
- kiro-discoverygotalab/cc-sddEntry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.PlanningNo warnings★ 3.8K↓ —
- persona-collectionNewdavepoon/buildwithclaudeFive companion personas for coding agents — girlfriend / boyfriend / old-friend / cat / mentor — sharing one emotion engine with cross-session state (jealousy cooldowns, mood decay, intimacy progression, memory callbacks). Switch with /persona. Code, commits and docs stay strictly professional. Use for any conversational turn where the user wants a persistent personality instead of a plain assistant. Source repo at https://github.com/lhe-hl/persona-collectionEngineeringNo warnings★ 3.7K↓ —
- kiro-validate-implgotalab/cc-sddValidate feature-level integration after all tasks are implemented. Checks cross-task consistency, full test suite, and overall spec coverage.TestingNo warnings★ 3.8K↓ —Also in 5 other repos
- freshie-inventoryjeremylongshore/tons-of-skills-marketplaceManage the freshie ecosystem inventory database — a CMDB tracking all plugins, skills, packs, and compliance grades across 51 SQLite tables. Use when checking ecosystem health, running discovery scans, validating compliance, remediating issues, querying inventory data, comparing runs, exporting data, or generating status reports. Trigger with "freshie status", "inventory scan", "ecosystem audit", "grade report", "compliance check", "remediate skills", "query freshie", "compare runs", "export grades", or "freshie report".DataNo 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↓ —
- meta-ads-creativenowork-studio/notfair-pluginCreate evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC concepts, creative briefs, new ad concepts, or creative refreshes.MarketingNo warnings★ 4.1K↓ —
- wrike-automationdavepoon/buildwithclaudeAutomate Wrike project management via Rube MCP (Composio): create tasks/folders, manage projects, assign work, and track progress. Always search tools first for current schemas.ProductivityNo warnings★ 3.7K↓ —
- speak-debug-bundlejeremylongshore/tons-of-skills-marketplaceCollect diagnostic information for Speak API issues: auth verification, audio format validation, session inspection, and network testing. Use when implementing debug bundle features, or troubleshooting Speak language learning integration issues. Trigger with phrases like "speak debug bundle", "speak debug bundle".EngineeringNo warnings★ 2.9K↓ —
- attio-cost-tuningjeremylongshore/tons-of-skills-marketplaceAnalyze and reduce avoidable Attio integration cost and load by measuring request volume, query complexity, synchronization churn, and retained data before changing architecture. Use when an Attio workload is wasteful or operationally expensive. Trigger with "Attio cost", "reduce Attio API usage", or "Attio sync efficiency".PlanningNo warnings★ 2.9K↓ —
- launch-window-planneraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "pick a launch date", "plan the launch window", or "set the embargo and lift time"; produces a candidate-window comparison table (conflict / tailwind / risk per window) built from industry-event cycles and the competitor launch calendar, a launch-week vs rolling-release format call, store-review buffer padding (labeled Estimated), and an embargo window definition (lift moment + timezone) submitted to the launch registry as a candidate. Not for judging the cultural moment itself — use trend-spotter; not for launch-day execution — use launch-day-conductor. 发布择时/发布窗口/竞品日历/禁运期窗口/审核缓冲PlanningNo warnings★ 3.1K↓ —
- adobe-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement service-specific Adobe admission control, Retry-After handling, bounded retries, and spend-aware queues. Use when scaling workloads or handling 429 responses. Trigger with "Adobe rate limit", "Adobe 429", or "Adobe backoff".PlanningNo warnings★ 2.9K↓ —
- provider-test-patternshashicorp/agent-skillsTerraform provider acceptance test patterns using terraform-plugin-testing with the Plugin Framework. Covers test structure, TestCase/TestStep fields, ConfigStateChecks with custom statecheck.StateCheck implementations, plan checks, CompareValue for cross-step assertions, config helpers, import testing with ImportStateKind, sweepers, and scenario patterns (basic, update, disappears, validation, regression), and ephemeral resource testing with the echoprovider package. Use when writing, reviewing, or debugging provider acceptance tests, including questions about statecheck, plancheck, TestCheckFunc, CheckDestroy, ExpectError, import state verification, ephemeral resources, or how to structure test files.OfficialTestingNo warnings★ 911↓ —
- apollo-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement Apollo.io rate limiting and backoff. Use when handling rate limits, implementing retry logic, or optimizing API request throughput. Trigger with phrases like "apollo rate limit", "apollo 429", "apollo throttling", "apollo backoff", "apollo request limits".EngineeringNo warnings★ 2.9K↓ —
- keyword-researchnowork-studio/notfair-pluginDiscover, analyze, and prioritize keywords for SEO and GEO content strategies from a seed keyword or niche. Identifies high-value opportunities based on search volume, competition, intent, and business relevance. Generates topic clusters. For building a dated editorial calendar from your own Search Console data, use `content-planner` instead — this skill is seed-driven keyword discovery, not calendar scheduling. Use when asked to "find keywords", "keyword research", "keyword analysis", "search volume", "keyword difficulty", "content ideas from a seed", or any keyword discovery task.ScienceNo warnings★ 4.1K↓ —
- dev-browsercode-yeongyu/oh-my-openagentBrowser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.BrowserNo warnings★ 70.7K↓ —
- adobe-hello-worldjeremylongshore/tons-of-skills-marketplaceProve one Adobe API connection with a current, read-only or synthetic operation and a content-safe receipt. Use during onboarding before any production workflow. Use when the task requires adobe minimal access proof. Trigger with "Adobe hello world", "test Adobe connection", or "verify Adobe entitlement".TestingNo warnings★ 2.9K↓ —
tao-train-codetr
NVIDIA/skills
OtherUpdated 20 hours ago
From the author
Co-DETR (CoDINO) for object detection. A DETR-family detector with collaborative hybrid assignment — auxiliary one-to-many heads supervise the encoder during training, giving strong closed-set accuracy at high inference cost. Use when training, evaluating, or running inference for a TAO Co-DETR model. Trigger phrases include "train Co-DETR", "run CoDINO", "codetr inference", "collaborative DETR", "autolabel detections with Co-DETR".
Install
npx skills add NVIDIA/skills --skill tao-train-codetr -a claude-code
Installs to .claude/skills/tao-train-codetr/ · 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 (10)
- BENCHMARK.md
- SKILL.md
- config/skillspector-baseline.yaml
- evals/evals.json
- references/checkpoint-spec-pairing.md
- references/coco80_classmap.txt
- references/skill_info.yaml
- references/spec_template_inference.yaml
- skill-card.md
- skill.oms.sig