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.
48,622 skills from 2,355 repositories · updated 17 hours ago
48,622 skills
- tao-train-dinov3NVIDIA/skillsDINOv3 continual self-supervised pre-training. Domain-adapts public DINOv3 ViT backbones on unlabeled images via teacher-student self-distillation (DINO + iBOT + KoLeo, optional Gram anchoring) and converts the EMA teacher into a timm-format backbone for downstream tasks. Trigger phrases include "train DINOv3", "DINOv3 SSL", "domain-adapt a foundation backbone", "continual pretraining", "self-supervised finetune DINOv3".ProductivityNo warnings★ 3.8K↓ —
- route-handlersdavepoon/buildwithclaudeThis skill should be used when the user asks to "create an API route", "add an endpoint", "build a REST API", "handle POST requests", "create route handlers", "stream responses", or needs guidance on Next.js API development in the App Router.EngineeringNo warnings★ 3.7K↓ —
- gsd:inteldavepoon/buildwithclaudeQuery, inspect, or refresh codebase intelligence files in .planning/intel/PlanningNo warnings★ 3.7K↓ —
- managing-api-cachejeremylongshore/tons-of-skills-marketplaceImplement intelligent API response caching with Redis, Memcached, and CDN integration. Use when optimizing API performance with caching. Trigger with phrases like "add caching", "optimize API performance", or "implement cache layer".EngineeringNo warnings★ 2.9K↓ —
- offensive-sstiSnailSploit/Claude-RedDense description covering Server-Side Template Injection across Jinja2, Twig, Freemarker, Velocity, Pebble, Smarty, Mako, Handlebars, ERB, Thymeleaf, EJS, Pug. Engine fingerprinting, filter bypass, blind exploitation, WAF evasion, SSTI-to-RCE chains. Tools: tplmap. CWE-1336. MITRE T1190. Use when testing template rendering endpoints or exploiting template injection for code execution.TestingNo warnings★ 10.2K↓ —
- obsidian-layout-adjustmentAr9av/obsidian-wikiAdjust the user's Obsidian visual layout with CSS snippets. Use for restyling tabs, sidebars, note surfaces, properties, backlinks, graph or file-explorer UI, or diagnosing CSS changes that did not take effect.ProductivityNo warnings★ 3.6K↓ —
- nemo-rl-session-memoryNVIDIA/skillsManage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.ProductivityNo warnings★ 3.8K↓ —
- reproduce-regressiontrailofbits/skillsUse when deploying before/after systems and building a live-system PoC for a regression candidate.DevOpsNo warnings★ 7.9K↓ —
- apply-aestheticplugin87/ux-ui-agent-skillsApply a visual direction, an archetype (high-end agency, editorial minimal, brutalist, soft-SaaS, dark-tech) or one of 2,144 named design systems (apple, linear-app, stripe, vercel, notion, material, shadcn, spotify, tesla…), by resolving it into the token system. Use when the user wants a specific look/vibe/brand feel, or asks to make a design feel premium/expensive/non-generic.DesignNo warnings★ 3.1K↓ —
- variant-analysistrailofbits/skillsHunts for the other instances of a bug already found — the variants of one root cause across a codebase. Use immediately after a vulnerability, logic bug, or bad pattern turns up in a specific file and the question becomes where else it occurs, including the bare conversational form ("are there others like this?", "is this the same bug?"). Also for generalizing one known instance into a CodeQL or Semgrep query for its whole pattern family, and for triaging a set of look-alike candidates against a known root cause. Not for initial discovery with no bug in hand.SecurityNo warnings★ 7.9K↓ —
- figmaheygen-com/hyperframesBring Figma into a HyperFrames video - rendered assets, brand tokens, components, storyboard frames as reconstructed motion (frames read as states, not slides), shaders and connector-assisted motion. Use when the person pastes a figma.com link or asks to use a Figma design, frame, logo or brand.OfficialDesignNo warnings★ 76.9K↓ —
- replay-regressiontrailofbits/skillsUse when independently verifying a supplied PoC against fresh live before/after deployments.DevOpsNo warnings★ 7.9K↓ —
- datadog-automationdavepoon/buildwithclaudeAutomate Datadog tasks via Rube MCP (Composio): query metrics, search logs, manage monitors/dashboards, create events and downtimes. Always search tools first for current schemas.ProductivityNo warnings★ 3.7K↓ —
- artifact-creatorjeremylongshore/tons-of-skills-marketplaceCreate or revise Agent Skills, host plugins and subagents, MCP servers and client configurations, hooks, and marketplace catalogs against their actual specifications. Use when building reusable agent capabilities or consolidating creator tooling without inventing a universal host format. Trigger with "create an agent skill", "build a plugin", "create an MCP server", "add a subagent", or "scaffold an agent integration".PlanningNo warnings★ 2.9K↓ —
- ops-firesdavepoon/buildwithclaudeProduction incidents dashboard. Reads ECS health, Sentry errors, CI failures. Offers to dispatch fix agents for active fires.OtherNo warnings★ 3.7K↓ —
- mcore-create-issueNVIDIA/skillsInvestigate a failing GitHub Actions run or job and create a GitHub issue for the failure.DevOpsNo warnings★ 3.8K↓ —
- figma-load-scalejeremylongshore/tons-of-skills-marketplaceLoad test Figma API integrations and plan for scale. Use when benchmarking API throughput, testing rate limit behavior, or planning capacity for high-volume Figma integrations. Trigger with phrases like "figma load test", "figma scale", "figma benchmark", "figma capacity", "figma throughput".DesignNo 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★ 3.7K↓ —
- closedavepoon/buildwithclaudeCommit the session to durable vault memory and prepare a clean resume pointEngineeringNo warnings★ 3.7K↓ —
- meeting-prepjeremylongshore/tons-of-skills-marketplaceMeeting preparation assistant for Product Managers. Use when the user needs to prepare a meeting, create talking points, anticipate questions, or structure a decision. Trigger with "prepare for meeting", "meeting prep", "talking points", "get ready for", or "1:1 prep".OtherNo warnings★ 2.9K↓ —
- mocking-apisjeremylongshore/tons-of-skills-marketplaceGenerate mock API servers for testing and development with realistic response data. Use when creating mock APIs for development and testing. Trigger with phrases like "create mock API", "generate API mock", or "setup mock server".TestingNo warnings★ 2.9K↓ —
- groq-cost-tuningjeremylongshore/tons-of-skills-marketplaceOptimize Groq costs through model routing, token management, and usage monitoring. Use when analyzing Groq billing, reducing API costs, or implementing usage monitoring and budget alerts. Trigger with phrases like "groq cost", "groq billing", "reduce groq costs", "groq pricing", "groq expensive", "groq budget".EngineeringNo warnings★ 2.9K↓ —
- mutation-testingtrailofbits/skillsConfigures mewt or muton campaigns, analyzes surviving mutants, and investigates bugs exposed by testing gaps. Use when setting up mutation testing, reviewing campaign results, identifying equivalent mutants, or finding bugs from surviving mutations.TestingNo warnings★ 7.9K↓ —
- gsd:check-todosdavepoon/buildwithclaudeList pending todos and select one to work onOtherNo warnings★ 3.7K↓ —
verifying-external-behavior
kajisho5/ffmpeg-skill
From the author
Confirms what a third-party library, remote API, build backend, or scraped document actually does before writing code that depends on it — throwaway probes that run in seconds, permissive clients that forward wrong arguments instead of rejecting them, per-endpoint docs that don't generalize, response shapes that make a "fast path" always-false, fakes that encode your assumption rather than the service's behavior, and dry-runs that skip the step that fails. Use when integrating a new dependency or endpoint, writing a tolerated-status or error branch, choosing a client argument name, testing against a fake, or reviewing code that asserts an upstream contract.
Install
npx skills add kajisho5/ffmpeg-skill --skill verifying-external-behavior -a claude-code
Installs to .claude/skills/verifying-external-behavior/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Safety checks on SKILL.md
No warnings.
Why 90
Files (1)
- SKILL.md