41,017 tagged agent-skills, measured the same way as everything else here.
Browse within: agentic-ai 454coding-agents 214agents 192academic-research 182academic-writing 182journal 182azure 169foundry 169sdk 169agent-plugins 158ai-coding-agent 155ai-skills 151anthropic-claude 136claude-ai 136
Skill Codex
Autonomously plan, run, and assess evidence-driven tests for Electron applications. Use after implementing or refactoring Electron behavior, when reproducing an issue, or when validation crosses main, preload, renderer, IPC, multi-window, lifecycle, packaged-runtime, or native desktop boundaries. Select the smallest…
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Skill Claude CodeCodex
Review content against the Microsoft Writing Style Guide, reporting issues by severity (Critical/High/Medium/Low) with specific fixes. Use this skill whenever the user asks you to review, edit, or check text for compliance with Microsoft style, including documentation, UI strings, developer docs, blog posts, error…
Skill Claude CodeCodex
Discover, inventory, dedupe, score, and monitor public SOURCES of agent skills (repos, directories, awesome-lists, mirrors) across GitHub, GitLab, Bitbucket, Codeberg/Forgejo, SourceHut, generic git, and websites. Keeps a durable SQLite inventory with no duplicate rows and no duplicate notifications, and emits…
Skill Claude CodeCodex
Action GitHub pull request review feedback. Use when the user wants to address PR review comments, respond to code review feedback, fix review issues, or says things like "action the review", "address feedback", "handle review comments", or "go through the PR comments". Fetches all unresolved review threads, triages…
Skill Claude CodeCodex
Run and operationalize VertaaUX UX, accessibility, and conversion audits across CLI, CI/CD, SDK, API, and MCP. Use when the user needs to audit a URL, investigate WCAG issues, set quality gates, compare audit runs, select an audit profile, or generate remediation plans from VertaaUX results.
Skill Claude CodeCodex
Transform any software repository into a contributor-friendly, production-ready open source project. Analyzes repo health, generates documentation, creates GitHub community files, identifies contribution opportunities, and produces a readiness report. Agent-independent and technology-agnostic.
Skill Claude CodeCodex
Add the official EU AI-content labels (EU icons for labelling AI-generated content, AI Act Art. 50) to images and videos. Use when the user asks to label, watermark, mark, or badge media as AI-generated, AI-modified, or a deepfake, mentions the EU AI icons / AI Act transparency disclosure, or asks to put an "AI"…
Skill Claude CodeCodex
React component design conventions focusing on Server/Client component boundaries, composition patterns, and data flow. Auto-triggers when writing or modifying React components to ensure correct RSC patterns and optimal component architecture.
Skill Codex
Initialize, plan, run, inspect, and review resumable Ralph-style autonomous implementation loops with sequential chunks, persistent scratchpad memory, manifests, and idempotent post-sprint hooks. Use for .ralph orchestration or similar long-running coding-agent sprint systems.
Skill Codex
Provides information about how to setup various kinds of projects. Useful for initializing projects based on requirements and scaffolding the project.
blackwell-systems/agentskills-cli
Skill Claude Code
Interactive guide for converting skills to progressive disclosure pattern. Use when you have a skill >500 lines and want to split it into core + references for better context economy.
VectorPeak/vectorpeak-agent-skills
Skill Codex
Manage the user's external GitHub PR workflow from project name to fork/clone, multi-agent bug hunting, PR-value validation, formal PR creation, reviewer feedback, and detailed PR comment section expansion. Use when the user asks to fork or clone a GitHub project, find small fixable PR opportunities, launch…
Skill Claude CodeCodex
Decide how much review a change has earned, before reviewing it. Selects quick, standard, or deep from stated signals (reviewable changed lines, directory spread, trust-boundary risk flags, blast radius, documentation-only scope), reports the signal table and the rule that fired, then runs house-review at the selected…
Skill Claude Code
Generate commit message for staged changes, pause for approval, then commit. Stage files first with git add, then run this skill.
Skill Claude CodeCodex
Use when installing or operating Claude Code as an MCP worker.
Skill Codex
Use when substantive project work, structural code questions, research, planning, debugging, architecture, decisions, document ingest, incident recovery, or verified context and results should survive future sessions; also when the user invokes $using-lwc or asks to search, update, repair, configure, or maintain an…
alexpolonsky/agent-skill-strikeradar
Skill Claude CodeCodex
Monitor US-Iran strike probability using open-source indicators - news alerts, Iran internet connectivity, oil prices, flight traffic, military tanker detection, weather, Polymarket odds, and Pentagon activity. Use when user asks about "Iran strike probability", "strike radar", "Iran situation", "US attack Iran"…
Skill Claude CodeCodex
Generate a structured instrument-approach briefing from a plate (image or PDF). The agent reads the plate using its own vision, extracts every briefing-critical datum into a strict JSON schema, and renders a pilot-facing briefing card. Covers ILS / LOC / LPV / RNAV / VOR / NDB / RNP approaches. Use whenever a pilot…
Skill Cursor
A design skill for planning how websites, dashboards, mobile screens, and agent interfaces look and move, including cinematic pages with layered motion.
humbleteam/accessibility-audit
Skill Claude CodeCodex
Runs a WCAG 2.2 accessibility audit of a screenshot, URL, or HTML/JSX and reports findings by severity (P0 blocks use, P1 degrades use, P2 friction), each with a success-criterion citation. Use for "check accessibility", "run an a11y audit", "is this WCAG compliant", "is this accessible", or "audit contrast and…
Skill Claude CodeCodex
Establish and apply a design direction using a curated visual reference library, plain-language weighted choices and a project lock file. Use for web design direction, "my taste", "min stil", visual alternatives, or reviewing UI against an existing direction. Also supports maintaining this reference library. A…
ddalgrande/dining-places-skill
Skill Claude CodeCodex
Turns a user's exported Google Maps saved places (starred places + custom Lists from a Google Takeout "Saved" + "Maps" export) into a personal dining knowledge base, then gives eating-out advice that (1) surfaces relevant places they already saved, (2) infers their taste, and (3) supplements with fresh web/Places…
Skill Claude Code
Enforces a warm, plain, human writing voice and strips AI-sounding patterns from ALL written output. MUST be used for every piece of prose the model produces for the user in any language — emails, essays, articles, cover letters, application answers, resumes, chat replies, social posts, documentation, translations.…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: