--- title: "awesome-agent-skills" description: "Skills for AI coding agents: code review, test writing, design docs, debugging, security and dependency audits, git history surgery, refactoring, copywriting, and cleaning up AI-written code and text. Every skill is a pl" canonical: https://agentpluginsdirectory.com/plugins/awesome-agent-skills last-updated: 2026-10-12 --- # awesome-agent-skills Skills for AI coding agents: code review, test writing, design docs, debugging, security and dependency audits, git history surgery, refactoring, copywriting, and cleaning up AI-written code and text. Every skill is a plain SKILL.md folder under the open Agent Skills standard, stack-agnostic, and ends with the check that proves its claim. - Slug: awesome-agent-skills - Publisher: Khasky - Repository: https://github.com/khasky/awesome-agent-skills - Manifest: plugin.json - Version: 1.17.0 - License: MIT - Category (editorial): other - Skills: 49 (awesome-accessibility-audit, awesome-agents-md-generator, awesome-api-design, awesome-architecture-audit, awesome-bug-fix, awesome-claims-audit, awesome-code-cleanup, awesome-code-docs, awesome-code-explainer, awesome-code-review-feedback, awesome-code-review-jury, awesome-code-review, awesome-code-standards, awesome-content-campaign, awesome-content-image-adapter, awesome-content-publisher, awesome-content-repurpose, awesome-content-voice, awesome-copywriting, awesome-database-audit, awesome-dependency-audit, awesome-dependency-upgrade, awesome-design-doc, awesome-document-style, awesome-error-standards, awesome-git-author-rewrite, awesome-git-commit-plan, awesome-git-history-rebuild, awesome-git-history-reset, awesome-git-history-salvage, awesome-grammar-check, awesome-humanize-en, awesome-landing-audit, awesome-leak-audit, awesome-logging-standards, awesome-pentest, awesome-performance-audit, awesome-plan-simplify, awesome-privacy-audit, awesome-regression-sweep, awesome-root-cause, awesome-security-audit, awesome-seo-audit, awesome-skills-purge, awesome-slop-audit, awesome-style-mimic, awesome-test-gap-audit, awesome-test-writing, awesome-translate-ru-en) - MCP servers: 0 - Stars: 12 - Repository created: 2026-03-22 - Repository last pushed: 2026-10-10 - Publisher type: User - Listing: https://agentpluginsdirectory.com/plugins/awesome-agent-skills - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What awesome-agent-skills does, in the publisher's words Skills for AI coding agents: code review, test writing, design docs, debugging, security audits, refactoring, and cleaning up AI-written code and text. Each skill is a folder with a SKILL.md in the Agent Skills format: install by copying it into your agent's skills directory. Distilled from widely-used public collections and the documented practice of large open-source projects, then sharpened over several rounds of use on real repositories. Compatible with Claude Code, Claude.ai, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, opencode, Amp, Windsurf, Antigravity, Kilo Code, Qwen Code, and any other agent that supports the standard. See Install for exact paths. - Awesome Agent Skills - Contents - Quick start - Install as a plugin - Install - Skills From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/khasky/awesome-agent-skills/HEAD/README.md ## Skills - awesome-accessibility-audit: Read-only WCAG audit of UI and markup with a concrete fix per finding. Use when asked to check accessibility, a11y, keyboard or screen-reader support, or contrast. - awesome-agents-md-generator: Mines a codebase's real commands, conventions and boundaries into an agent-agnostic AGENTS.md, nested per package in monorepos, every rule backed by counted evidence. Use when asked to write, generate or refresh AGENTS.md or agent instructions for a repo. - awesome-api-design: Designs or reviews an HTTP API's shape before code: resources, versioning, pagination, idempotency, filtering. Use when asked to design an API or an endpoint. - awesome-architecture-audit: Read-only audit of a whole codebase's design: module boundaries, dependency direction, docs-vs-code drift, extensibility, with a verdict. Use when asked to audit the architecture. - awesome-bug-fix: Fixes a bug by building a runnable reproduction and finding the root cause before any fix. Use for errors, crashes, failing tests or builds, flaky behavior, or repeated failed fixes. - awesome-claims-audit: Checks public claims (site, README, store listing, privacy policy, structured data) against the code and config that decide them, then fixes drift. Use when asked whether the site still matches the product. - awesome-code-cleanup: Behavior-preserving cleanup of AI-like code noise: narrating comments, dead code, vague names, over-abstraction; applies a slop-audit report. Use when asked to clean up code or comments, or to de-slop. - awesome-code-docs: Generates a full technical documentation set for a codebase, from a local folder or a clone of any git host URL: architecture, per-module and API reference, data model, flows, config, operations, how-to guides, written bottom-up along the dependency graph, cited. Use when asked to document a repo. - awesome-code-explainer: Explains how a codebase works, from a local folder or a clone of any git host URL, as one illustrated page: purpose, stack, structure, entry points, main flow, patterns, where to start reading, every claim cited. Use when asked to explain a repo or get up to speed on one. - awesome-code-review-feedback: Responds to code review feedback: verifies each point before changing code, clarifies unclear items, pushes back with reasons when a point is wrong. Use when asked to address reviewer or bot comments. - awesome-code-review-jury: Reviews a code change with a jury: independent read-only subagents on different models review blind, a separate judge cross-examines them and returns one verdict. Use when asked for a second opinion, a multi-model or panel review, or a high-stakes review. - awesome-code-review: Reviews a diff, patch or pull request for correctness, security and team standards, with severity-ranked findings. Use when asked to review a change or PR, or before merging. - awesome-code-standards - awesome-content-campaign - awesome-content-image-adapter - awesome-content-publisher - awesome-content-repurpose - awesome-content-voice - awesome-copywriting - awesome-database-audit - awesome-dependency-audit - awesome-dependency-upgrade - awesome-design-doc - awesome-document-style - awesome-error-standards - awesome-git-author-rewrite - awesome-git-commit-plan - awesome-git-history-rebuild - awesome-git-history-reset - awesome-git-history-salvage - awesome-grammar-check - awesome-humanize-en - awesome-landing-audit - awesome-leak-audit - awesome-logging-standards - awesome-pentest - awesome-performance-audit - awesome-plan-simplify - awesome-privacy-audit - awesome-regression-sweep - awesome-root-cause - awesome-security-audit - awesome-seo-audit - awesome-skills-purge - awesome-slop-audit - awesome-style-mimic - awesome-test-gap-audit - awesome-test-writing - awesome-translate-ru-en Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.