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 6 hours ago
48,168 skills
- blast-radiusmichael-denyer/pstack-claudeFind what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', reviewing a small diff you don't trust, or a brief that asserts something about existing code ('make X public', 'X already handles Y') before you design against that assertion.DesignNo warnings★ 3.7K↓ —
- clerk-rate-limitsjeremylongshore/tons-of-skills-marketplaceUnderstand and manage Clerk rate limits and quotas. Use when hitting rate limits, optimizing API usage, or planning for high-traffic scenarios. Trigger with phrases like "clerk rate limit", "clerk quota", "clerk API limits", "clerk throttling".PlanningNo 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↓ —
- orca-replaydavepoon/buildwithclaudeAnswers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use when asked why an earlier run did something, or to reproduce a failure.ProductivityNo warnings★ 3.7K↓ —
- speak-hello-worldjeremylongshore/tons-of-skills-marketplaceCreate your first Speak AI tutoring session with pronunciation feedback. Use when starting a new Speak integration, testing your setup, or learning basic language learning API patterns. Trigger with phrases like "speak hello world", "speak example", "speak quick start", "first speak lesson".TestingNo warnings★ 2.9K↓ —
- shopify-load-scalejeremylongshore/tons-of-skills-marketplaceLoad test Shopify integrations respecting API rate limits, plan capacity with k6, and scale for Shopify Plus burst events (flash sales, BFCM). Use when preparing for high-traffic events, benchmarking API throughput, or sizing infrastructure for Shopify webhook volume. Trigger with phrases like "shopify load test", "shopify scale", "shopify BFCM", "shopify flash sale", "shopify capacity", "shopify k6 test".TestingNo warnings★ 2.9K↓ —
- auto-subtitleZJU-REAL/Easel自动字幕 / 语音转字幕：把音频或视频里的语音识别成字幕文件（SRT/ASS/TXT/JSON），可选把字幕烧录进视频。当用户说自动字幕、语音转字幕、视频加字幕、上字幕、转录、听写、字幕文件、生成字幕、烧字幕时使用。OtherNo warnings★ 4.2K↓ —
- 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↓ —
- ops-godavepoon/buildwithclaudeToken-efficient morning briefing. Pre-gathers all data via shell scripts, then presents a unified business dashboard with prioritized actions.OtherNo warnings★ 3.7K↓ —
- sharpenmichael-denyer/pstack-claudeMake a task deeper, not bigger, then rewrite the prompt. Use for /sharpen.ProductivityNo warnings★ 3.7K↓ —
- doca-spcx-ccNVIDIA/skillsUse this skill when the user is invoking `doca_spcx_cc` (the host-side CLI under /opt/mellanox/doca/tools/) to load, parameterize, start, observe, or stop an SPC-X congestion-control algorithm on a BlueField with a DPA processor against a live RDMA / RoCE fabric, or picking SPCX vs the established `doca-pcc` surface. Trigger even when the user does not say "DOCA SPCX" or "doca_spcx_cc" — typical implicit phrasings include "I want to write a custom RTT-based CC algorithm for my RoCE fabric", "my SPCX session loaded but throughput / latency didn't change", "doca_pcc status shows Active but factory CC seems to still be in charge", "DOCA_PCC_PS_ERROR on start", "is the programmable-CC surface available on my install", or "DPA-side algorithm image won't load". Refuse and route elsewhere for DPA-side algorithm authoring detail, factory PCC firmware configuration, read-only PCC counter inspection, raw DPA cycle profiling, RDMA library programming, or general DOCA install — those belong to other skills.MediaNo warnings★ 3.8K↓ —
- batch-processZJU-REAL/Easel批量处理：对一个目录里的一批图片/视频/音频统一套用同一操作——批量压缩、加水印、转格式、缩放、转比例、音量归一化等。当用户说 批量处理、批量压缩、批量加水印、批量转格式、一批图片/视频、给这个文件夹、全部转成、批量缩放、批量转竖版、整个目录 时使用。基于 shared/scripts/batch_process.py（委派 image_ops/video_ops/audio_ops）。与 image-editing/video-editing/audio-editing 区别：那些处理单文件，本 SKILL 批量套用到整个目录。MediaNo warnings★ 4.2K↓ —
- canva-load-scalejeremylongshore/tons-of-skills-marketplaceDesign a mock-first Canva capacity test and a tightly authorized provider probe. Use when sizing queues, workers, token-refresh serialization, or endpoint concurrency without inventing universal quotas. Trigger with: "load test Canva", "size Canva workers", "Canva capacity plan".TestingNo warnings★ 2.9K↓ —
- reasoningjeremylongshore/tons-of-skills-marketplaceUse BEFORE answering analytical, diagnostic, planning, or multi-step reasoning questions. Trigger phrases include "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs", "help me think through", "diagnose", "root cause", "plan/design X", "what are the implications of", "compare these approaches". Also fires on cross-domain analysis, strategy questions, architecture decisions, or anything requiring multiple factors to be weighed before responding. The skill calls the reasoning MCP tool to retrieve a cognitive scaffold (named failure pattern, executable procedure, suppression vectors, falsification test) the model absorbs internally before generating its response. Catches causal shortcuts, premature conclusions, generic templates, and surface pattern matching that produce confidently-wrong answers. Do NOT trigger for simple factual lookups, syntax questions, file reads, code execution, or restating the user's input.TestingNo warnings★ 2.9K↓ —
- nvshmem-enable-tmaNVIDIA/skillsPrepare or review NVSHMEM CUDA kernels for TMA SMEM registration and direct-SMEM transfers. Do not use for unrelated CUDA tuning.EngineeringNo warnings★ 3.8K↓ —
- strategic-clarityjeremylongshore/tons-of-skills-marketplaceAnalyze and audit team context to establish identity, boundaries, and strategic clarity. Use when starting a new role, inheriting ambiguity, or defining ownership. Trigger with "strategic clarity", "team identity", "new role", "inherited ambiguity", "what does my team own", or "define our boundaries".ProductivityNo warnings★ 2.9K↓ —
- campaign-architectaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "plan my paid account structure", "pick Search vs PMax", "lay out ad groups / asset groups", or "audit paid-vs-organic cannibalization"; designs campaign-type selection, ad-group/asset-group layout, targeting + match types, negative/exclusion hygiene, and a paid↔organic overlap audit, and scores the ROAS A (Audience) dimension + structure. Not for computing the final RQS — use ad-account-auditor; not for budget split — use budget-optimizer; not for organic site architecture — use site-structure-optimizer. 付费广告账户结构/广告系列规划/否定关键词MarketingNo warnings★ 3K↓ —
- correctmichael-denyer/pstack-claudeFind the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.TestingNo warnings★ 3.7K↓ —
- paperclippaperclipai/paperclipInteract with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.PlanningNo warnings★ 109.2K↓ —
- segment-automationdavepoon/buildwithclaudeAutomate Segment tasks via Rube MCP (Composio): track events, identify users, manage groups, page views, aliases, batch operations. Always search tools first for current schemas.ProductivityNo warnings★ 3.7K↓ —
- abridge-cost-tuningjeremylongshore/tons-of-skills-marketplaceEvaluate Abridge adoption, workflow value, and avoidable operational friction without inventing prices or vendor billing meters. Use when reviewing an Abridge rollout or renewal. Trigger with "analyze Abridge value".ProductivityNo warnings★ 2.9K↓ —
- clerk-webhooksclerk/skillsClerk webhooks for real-time events and data syncing. Verify with verifyWebhook from the framework-specific package. Handle user, session, organization, billing, and payment events. Build event-driven features like database sync, notifications, and integrations.OfficialDataNo warnings★ 89↓ —
- memory-bridgeAr9av/obsidian-wikiBrowse or compare wiki knowledge by originating AI tool. Use for cross-tool memory questions, tool-specific knowledge, or gap/diff analysis between Codex, Claude, Hermes, and other agents.ProductivityNo warnings★ 3.6K↓ —
- clerk-billingclerk/skillsClerk Billing for subscription management - render Clerk's PricingTable and in-app checkout drawer, configure subscription plans, seat-limit plans for B2B, feature entitlements with has(), and billing webhooks. Use for SaaS monetization, plan gating, checkout flows, trials, invoicing, and subscription lifecycle management.OfficialMediaNo warnings★ 89↓ —
agentic-actions-auditor
trailofbits/skills
SecurityUpdated 3 days ago
From the author
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
Install
npx skills add trailofbits/skills --skill agentic-actions-auditor -a claude-code
Installs to .claude/skills/agentic-actions-auditor/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (CC-BY-SA-4.0) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Instructions onlyNo network use seenLicence: CC-BY-SA-4.0
Safety checks on SKILL.md
No warnings.
Why 90
Security100
Provenance87
Maintenance100
Licence80
Adoption61
Files (15)
- SKILL.md
- agents/openai.yaml
- assets/trail-of-bits-mark.svg
- references/action-profiles.md
- references/cross-file-resolution.md
- references/foundations.md
- references/vector-a-env-var-intermediary.md
- references/vector-b-direct-expression-injection.md
- references/vector-c-cli-data-fetch.md
- references/vector-d-pr-target-checkout.md
- references/vector-e-error-log-injection.md
- references/vector-f-subshell-expansion.md
- +3 more