ishandutta2007/awesome-agent-skills
Developer toolsSkills for coding agents ๐ Star if you like it! ๐
Overview
Skills encode the workflows, quality gates, and best practices that senior engineers use when building software. These ones are packaged so AI agents follow them consistently across every phase of development. 7 slash commands that map to the development lifecycle. Each one activates the right skills automatically. Want fewer manual steps once the spec exists? generates the plan and implements every task in a single approved pass โ you approve the plan once, then it runs autonomously. It removes the human stepping between tasks, not the verification: every task is still test-driven and committed individually, and it pauses on failures or risky steps. Skills also activate automatically based on what you're doing โ designing an API triggers api-and-interface-design, building UI triggers frontend-ui-engineering, and so on. The marketplace clones repos via SSH.
README
๐ Awesome AI Skills
Production-grade engineering Awesome AI Skills for AI coding agents. ๐
Skills encode the workflows, quality gates, and best practices that senior engineers use when building software. These ones are packaged so AI agents follow them consistently across every phase of development.
DEFINE PLAN BUILD VERIFY REVIEW SHIP
โโโโโโโโ โโโโโโโโ โโโโโโโโ โโโโโโโโ โโโโโโโโ โโโโโโโโ
โ Idea โ โโโโถ โ Spec โ โโโโถ โ Code โ โโโโถ โ Test โ โโโโถ โ QA โ โโโโถ โ Go โ
โRefineโ โ PRD โ โ Impl โ โDebug โ โ Gate โ โ Live โ
โโโโโโโโ โโโโโโโโ โโโโโโโโ โโโโโโโโ โโโโโโโโ โโโโโโโโ
/spec /plan /build /test /review /ship
๐ ๏ธ Commands
7 slash commands that map to the development lifecycle. Each one activates the right skills automatically.
| What youโre doing | Command | Key principle |
|---|---|---|
| Define what to build | /spec |
Spec before code |
| Plan how to build it | /plan |
Small, atomic tasks |
| Build incrementally | /build |
One slice at a time |
| Prove it works | /test |
Tests are proof |
| Review before merge | /review |
Improve code health |
| Simplify the code | /code-simplify |
Clarity over cleverness |
| Ship to production | /ship |
Faster is safer |
Want fewer manual steps once the spec exists? /build auto generates the plan and implements every task in a single approved pass โ you approve the plan once, then it runs autonomously. It removes the human stepping between tasks, not the verification: every task is still test-driven and committed individually, and it pauses on failures or risky steps.
Skills also activate automatically based on what youโre doing โ designing an API triggers api-and-interface-design, building UI triggers frontend-ui-engineering, and so on.
๐ Quick Start
๐ All 30 Skills
The commands above are entry points. The pack includes 27 skills total โ 26 lifecycle skills plus the using-awesome-ai-skills meta-skill. Each skill is a structured workflow with steps, verification gates, and anti-rationalization tables. You can also reference any skill directly.
Meta - Discover which skill applies
| Skill | What It Does | Use When |
|---|---|---|
| using-awesome-ai-skills | Maps incoming work to the right skill workflow and defines shared operating rules | Starting a session or deciding which skill applies |
Define - Clarify what to build
| Skill | What It Does | Use When |
|---|---|---|
| interview-me | One-question-at-a-time interview that extracts what the user actually wants instead of what they think they should want, until ~95% confidence | The ask is underspecified, or the user invokes โinterview meโ / โgrill meโ |
| idea-refine | Structured divergent/convergent thinking to turn vague ideas into concrete proposals | You have a rough concept that needs exploration |
| spec-driven-development | Write a PRD covering objectives, commands, structure, code style, testing, and boundaries before any code | Starting a new project, feature, or significant change |
Plan - Break it down
| Skill | What It Does | Use When |
|---|---|---|
| planning-and-task-breakdown | Decompose specs into small, verifiable tasks with acceptance criteria and dependency ordering | You have a spec and need implementable units |
Build - Write the code
| Skill | What It Does | Use When |
|---|---|---|
| incremental-implementation | Thin vertical slices - implement, test, verify, commit. Feature flags, safe defaults, rollback-friendly changes | Any change touching more than one file |
| test-driven-development | Red-Green-Refactor, test pyramid (80/15/5), test sizes, DAMP over DRY, Beyonce Rule, browser testing | Implementing logic, fixing bugs, or changing behavior |
| context-engineering | Feed agents the right information at the right time - rules files, context packing, MCP integrations | Starting a session, switching tasks, or when output quality drops |
| source-driven-development | Ground every framework decision in official documentation - verify, cite sources, flag whatโs unverified | You want authoritative, source-cited code for any framework or library |
| doubt-driven-development | Adversarial fresh-context review of every non-trivial decision in-flight - CLAIM โ EXTRACT โ DOUBT โ RECONCILE โ STOP, with optional user-authorized cross-model escalation | Stakes are high (production, security, irreversible), working in unfamiliar code, or a confident output is cheaper to verify now than to debug later |
| frontend-ui-engineering | Component architecture, design systems, state management, responsive design, WCAG 2.1 AA accessibility | Building or modifying user-facing interfaces |
| api-and-interface-design | Contract-first design, Hyrumโs Law, One-Version Rule, error semantics, boundary validation | Designing APIs, module boundaries, or public interfaces |
| mcp-tool-integration | Implementing and connecting Model Context Protocol tools. | Extending agent capabilities with external data sources |
External Data & Agent Integrations
| Skill | What It Does | Use When |
|---|---|---|
| Guides LinkedIn automation workflows with structured output and authentication checks | Working with LinkedIn profiles, companies, messages, posts, or connections | |
| xquik-public-data | Guides safe public X/Twitter data workflows through documented Xquik routes | Reading public tweets, profiles, trends, lists, communities, articles, media, or search results |
| hermes-tweet | Guides safe Hermes Tweet plugin setup, reads, and gated X/Twitter actions | Installing Hermes Tweet or choosing read versus action tools for X/Twitter workflows |
Creative Media
| Skill | What It Does | Use When |
|---|---|---|
| video-router | Selects and locks generation, deterministic composition, footage editing, or an end-to-end video-production route | Classifying a video brief before production, asset generation, editing, or rendering begins |
Verify - Prove it works
| Skill | What It Does | Use When |
|---|---|---|
| browser-testing-with-devtools | Chrome DevTools MCP for live runtime data - DOM inspection, console logs, network traces, performance profiling | Building or debugging anything that runs in a browser |
| debugging-and-error-recovery | Five-step triage: reproduce, localize, reduce, fix, guard. Stop-the-line rule, safe fallbacks | Tests fail, builds break, or behavior is unexpected |
| eval-driven-development | Building rigorous LLM evaluation pipelines for AI features | Tuning prompts, building RAG pipelines, or changing models |
Review - Quality gates before merge
| Skill | What It Does | Use When |
|---|---|---|
| code-review-and-quality | Five-axis review, change sizing (~100 lines), severity labels (Nit/Optional/FYI), review speed norms, splitting strategies | Before merging any change |
| ax-extract-workflow | Reconstructs the evidence trail behind a shipped artifact with ax sessions, recall, commits, and PR context | After a successful PR, demo, incident fix, or feature and you want the reusable workflow |
| code-simplification | Chestertonโs Fence, Rule of 500, reduce complexity while preserving exact behavior | Code works but is harder to read or maintain than it should be |
| security-and-hardening | OWASP Top 10 prevention, auth patterns, secrets management, dependency auditing, three-tier boundary system | Handling user input, auth, data storage, or external integrations |
| performance-optimization | Measure-first approach - Core Web Vitals targets, profiling workflows, bundle analysis, anti-pattern detection | Performance requirements exist or you suspect regressions |
Ship - Deploy with confidence
| Skill | What It Does | Use When |
|---|---|---|
| git-workflow-and-versioning | Trunk-based development, atomic commits, change sizing (~100 lines), the commit-as-save-point pattern | Making any code change (always) |
| ci-cd-and-automation | Shift Left, Faster is Safer, feature flags, quality gate pipelines, failure feedback loops | Setting up or modifying build and deploy pipelines |
| deprecation-and-migration | Code-as-liability mindset, compulsory vs advisory deprecation, migration patterns, zombie code removal | Removing old systems, migrating users, or sunsetting features |
| documentation-and-adrs | Architecture Decision Records, API docs, inline documentation standards - document the why | Making architectural decisions, changing APIs, or shipping features |
| observability-and-instrumentation | Structured logging, RED metrics, OpenTelemetry tracing, symptom-based alerting - instrument as you build | Adding telemetry, or shipping anything that runs in production |
| shipping-and-launch | Pre-launch checklists, feature flag lifecycle, staged rollouts, rollback procedures, monitoring setup | Preparing to deploy to production |
Agent Personas
Pre-configured specialist personas for targeted reviews:
| Agent | Role | Perspective |
|---|---|---|
| code-reviewer | Senior Staff Engineer | Five-axis code review with โwould a staff engineer approve this?โ standard |
| test-engineer | QA Specialist | Test strategy, coverage analysis, and the Prove-It pattern |
| security-auditor | Security Engineer | Vulnerability detection, threat modeling, OWASP assessment |
| web-performance-auditor | Web Performance Engineer | Core Web Vitals audit with Quick/Deep modes and a metric-honesty rule; run it via /webperf |
See docs/personas.md for the decision matrix, orchestration rules, and how personas compose with skills and slash commands.
Reference Checklists
Quick-reference material that skills pull in when needed:
| Reference | Covers |
|---|---|
| testing-patterns.md | Test structure, naming, mocking, React/API/E2E examples, anti-patterns |
| security-checklist.md | Pre-commit checks, auth, input validation, headers, CORS, OWASP Top 10 |
| performance-checklist.md | Core Web Vitals targets, frontend/backend checklists, measurement commands |
| accessibility-checklist.md | Keyboard nav, screen readers, visual design, ARIA, testing tools |
| observability-checklist.md | On-call questions, structured logging, RED/USE metrics, tracing, symptom-based alerting, pre-launch gate |
| orchestration-patterns.md | Endorsed multi-persona orchestration patterns, anti-patterns, and the โpersonas donโt invoke personasโ rule |
How Skills Work
Every skill follows a consistent anatomy:
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ SKILL.md โ
โ โ
โ โโ Frontmatter โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ โ name: lowercase-hyphen-name โ โ
โ โ description: Guides agents through [task].โ โ
โ โ Use whenโฆ โ โ
โ โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ โ
โ Overview โ What this skill does โ
โ When to Use โ Triggering conditions โ
โ Process โ Step-by-step workflow โ
โ Rationalizations โ Excuses + rebuttals โ
โ Red Flags โ Signs something's wrong โ
โ Verification โ Evidence requirements โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Key design choices:
- Process, not prose. Skills are workflows agents follow, not reference docs they read. Each has steps, checkpoints, and exit criteria.
- Anti-rationalization. Every skill includes a table of common excuses agents use to skip steps (e.g., โIโll add tests laterโ) with documented counter-arguments.
- Verification is non-negotiable. Every skill ends with evidence requirements - tests passing, build output, runtime data. โSeems rightโ is never sufficient.
- Progressive disclosure. The
SKILL.mdis the entry point. Supporting references load only when needed, keeping token usage minimal.
๐ Project Structure
awesome-agent-skills/
โโโ skills/ # 27 skills (26 lifecycle + 1 meta)
โ โโโ interview-me/ # Define
โ โโโ idea-refine/ # Define
โ โโโ spec-driven-development/ # Define
โ โโโ planning-and-task-breakdown/ # Plan
โ โโโ incremental-implementation/ # Build
โ โโโ context-engineering/ # Build
โ โโโ source-driven-development/ # Build
โ โโโ doubt-driven-development/ # Build
โ โโโ frontend-ui-engineering/ # Build
โ โโโ test-driven-development/ # Build
โ โโโ api-and-interface-design/ # Build
โ โโโ browser-testing-with-devtools/ # Verify
โ โโโ debugging-and-error-recovery/ # Verify
โ โโโ eval-driven-development/ # Verify
โ โโโ mcp-tool-integration/ # Build
โ โโโ code-review-and-quality/ # Review
โ โโโ ax-extract-workflow/ # Review
โ โโโ code-simplification/ # Review
โ โโโ security-and-hardening/ # Review
โ โโโ performance-optimization/ # Review
โ โโโ git-workflow-and-versioning/ # Ship
โ โโโ ci-cd-and-automation/ # Ship
โ โโโ deprecation-and-migration/ # Ship
โ โโโ documentation-and-adrs/ # Ship
โ โโโ observability-and-instrumentation/ # Ship
โ โโโ shipping-and-launch/ # Ship
โ โโโ using-awesome-ai-skills/ # Meta: how to use this pack
โโโ agents/ # 4 specialist personas
โโโ checklists/ # 6 supplementary checklists
โโโ hooks/ # Session lifecycle hooks
โโโ .claude/commands/ # 7 slash commands (Claude Code)
โโโ .gemini/commands/ # 7 slash commands (Gemini CLI)
โโโ commands/ # 8 slash commands (Antigravity CLI)
โโโ plugin.json # Antigravity plugin manifest
โโโ docs/ # Setup guides per tool
Why Agent Skills?
AI coding agents default to the shortest path - which often means skipping specs, tests, security reviews, and the practices that make software reliable. Agent Skills gives agents structured workflows that enforce the same discipline senior engineers bring to production code.
Each skill encodes hard-won engineering judgment: when to write a spec, what to test, how to review, and when to ship. These arenโt generic prompts - theyโre the kind of opinionated, process-driven workflows that separate production-quality work from prototype-quality work.
Skills bake in best practices from Googleโs engineering culture โ including concepts from Software Engineering at Google and Googleโs engineering practices guide. Youโll find Hyrumโs Law in API design, the Beyonce Rule and test pyramid in testing, change sizing and review speed norms in code review, Chestertonโs Fence in simplification, trunk-based development in git workflow, Shift Left and feature flags in CI/CD, and a dedicated deprecation skill treating code as a liability. These arenโt abstract principles โ theyโre embedded directly into the step-by-step workflows agents follow.
Contributing
Skills should be specific (actionable steps, not vague advice), verifiable (clear exit criteria with evidence requirements), battle-tested (based on real workflows), and minimal (only whatโs needed to guide the agent).
See docs/skill-anatomy.md for the format specification and CONTRIBUTING.md for guidelines.
License
MIT - use these skills in your projects, teams, and tools.
Star History
Recommended Tools
Try a different keyword or remove a filter.
Install
npx skillfish add ishandutta2007/awesome-agent-skills