Production-grade engineering skills for AI coding agents.
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.
9 slash commands that map to the development lifecycle. Each one activates the right skills automatically.
What you’re 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
Set the quality bar
/constraints
Decide it once, enforce it everywhere
Review before merge
/review
Improve code health
Audit web performance
/webperf
Measure before you optimize
Simplify the code
/code-simplify
Clarity over cleverness
Ship to production
/ship
Faster is safer
In Claude Code these install as plugin commands. Where a built-in command has the same name, as /review does, use the namespaced form: /agent-skills:review.
Want fewer manual steps once the spec exists? /build auto generates the plan and implements every task in a single approved pass — 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 — designing an API triggers api-and-interface-design, building UI triggers frontend-ui-engineering, and so on.
Quick Start
Fastest path — any agent, one command. The open skills CLI installs into 70+ agents (Claude Code, Cursor, Codex, Copilot, Cline, and more):
npx skills add addyosmani/agent-skills # install all 25 skills
npx skills add addyosmani/agent-skills --list # browse before installing
Or grab individual skills:
npx skills add addyosmani/agent-skills --skill code-review-and-quality # five-axis review before merge
npx skills add addyosmani/agent-skills --skill interview-me # requirements interrogation, one question at a time
npx skills add addyosmani/agent-skills --skill test-driven-development # red-green-refactor, enforced
Installing one skill? A per-skill npx install copies only
skills/<name>/, not the repo-level references/ directory. The skill still
works, but paths to supplementary shared checklists are unavailable. Use a
whole-repo integration, clone the repository, or copy the needed checklist into
a references/ directory inside the installed skill. This portability gap is
tracked in #361.
Prefer a native integration? Pick your tool below.
SSH errors? The marketplace clones repos via SSH. If you don’t have SSH keys set up on GitHub, either add your SSH key or use the full HTTPS URL to force HTTPS cloning during the marketplace-add step:
If /plugin install still fails with git@github.com: Permission denied (publickey) on Windows or macOS, the recommended workaround is to configure Git once to rewrite GitHub SSH URLs to HTTPS for subprocess clones:
git clone https://github.com/addyosmani/agent-skills.git
claude --plugin-dir /path/to/agent-skills
Cursor
Put workflow skills under .cursor/skills/ (sync from agent-skills/skills/) and short policies in .cursor/rules/*.mdc — do not paste full skills into rules. Both directories live in your project; this repo does not ship a .cursor/ folder. See docs/cursor-setup.md.
Antigravity CLI
Install as a native plugin for skills and subagents. In affected Antigravity CLI releases, legacy command TOMLs are reported as converted but their wrapper commands are not discoverable; invoke the underlying namespaced skills directly. See docs/antigravity-setup.md.
Copy skills to .opencode/skills/ (or ~/.config/opencode/skills/), add a project-local AGENTS.md, and use the built-in skill tool for agent-driven execution. Optional slash commands can be added under .opencode/commands/.
Use agent definitions from agents/ as Copilot personas and skill content in .github/copilot-instructions.md. The lifecycle slash commands (/spec, /plan, /build, /test, /review, /ship) are Claude Code commands and do not appear in Copilot; invoke the skills by name (/spec-driven-development, …) instead. See docs/copilot-setup.md.
Kiro IDE & CLI
Skills for Kiro reside under ".kiro/skills/" and can be stored under Project or Global level. Kiro also supports Agents.md. See Kiro docs at https://kiro.dev/docs/skills/
Codex
Install as a native Codex plugin (Codex CLI v0.122+):
The first command registers the marketplace; the second installs the plugin. Codex reads the root skills/ directory directly through .codex-plugin/plugin.json. Once installed, invoke skills in chat using @ (e.g., @spec-driven-development). See docs/codex-setup.md for local installation and troubleshooting.
Command Code
Install natively with the built-in cmd skills command. Command Code clones the repo, discovers every SKILL.md, and installs into .commandcode/skills/:
cmd skills add addyosmani/agent-skills # pick skills to install (project)
cmd skills add addyosmani/agent-skills --global # install for all projects (~/.commandcode/skills/)
cmd skills add addyosmani/agent-skills -s spec-driven-development # install a specific skill
Installed skills show up in the TUI slash menu, e.g. /spec-driven-development. See docs/commandcode-setup.md.
Other Agents
Skills are plain Markdown - they work with any agent that accepts system prompts or instruction files. See docs/getting-started.md. Hosts that install the pack but aren’t listed above are in docs/other-hosts.md.
Adoption
Already installed? How you roll the pack out depends on your codebase. The Adoption Guide covers two paths: the full lifecycle from day one for a greenfield project, or an incremental, verification-first rollout for an established codebase.
All 25 Skills
The commands above are entry points. The pack includes 25 skills total — 24 lifecycle skills plus the using-agent-skills meta-skill. Each skill is a structured workflow with steps, verification gates, and anti-rationalization tables. You can also reference any skill directly.
Interviews you for a quality bar with sane default thresholds, writes CONSTRAINTS.md, places each check by cost, and catches agents silencing checks or skipping tests to get green
No standards are written down, or an agent is producing more than anyone reads
Endorsed multi-persona orchestration patterns, anti-patterns, and the “personas don’t invoke personas” rule
How Skills Work
Every skill follows a consistent anatomy:
┌─────────────────────────────────────────────────┐
│ SKILL.md │
│ │
│ ┌─ Frontmatter ─────────────────────────────┐ │
│ │ name: lowercase-hyphen-name │ │
│ │ description: Guides agents through [task].│ │
│ │ Use when… │ │
│ └───────────────────────────────────────────┘ │
│ Overview → What this skill does │
│ When to Use → Triggering conditions │
│ Process → Step-by-step workflow │
│ Rationalizations → Excuses + rebuttals │
│ Red Flags → Signs something's wrong │
│ Verification → Evidence requirements │
└─────────────────────────────────────────────────┘
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., “I’ll add tests later”) with documented counter-arguments.
Verification is non-negotiable. Every skill ends with evidence requirements - tests passing, build output, runtime data. “Seems right” is never sufficient.
Progressive disclosure. The SKILL.md is the entry point. Supporting references load only when needed, keeping token usage minimal.
Project Structure
The portable core stays in shared directories. Host-specific paths are native discovery conventions, not branding aliases; renaming or merging them would break the tools that scan those exact locations.
Layer / consumer
Repository paths
Purpose
Shared workflow core
skills/ (25 skills)
Portable SKILL.md workflows used by every integration
Shared review material
agents/ (4 personas), references/ (7 checklists)
Specialist reviewers and pack-level checklists carried by whole-repo installs
Codex plugin metadata and marketplace registration; Codex consumes skills/ directly
GitHub Copilot CLI adapter
plugin.json
Root plugin metadata; Copilot CLI discovers skills/ by convention and does not register the lifecycle wrappers
Contributor tooling
scripts/ (13 scripts), evals/ (25 case files), .github/workflows/
Validation, routing evals, and CI
Documentation
docs/
Universal guidance and per-tool setup guides
Tools without a checked-in adapter directory install or copy the shared skills/ core into their own native location. The Quick Start links the setup guide for each supported host.
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 aren’t generic prompts - they’re the kind of opinionated, process-driven workflows that separate production-quality work from prototype-quality work.
Skills bake in best practices from Google’s engineering culture — including concepts from Software Engineering at Google and Google’s engineering practices guide. You’ll find Hyrum’s Law in API design, the Beyonce Rule and test pyramid in testing, change sizing and review speed norms in code review, Chesterton’s 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 aren’t abstract principles — they’re embedded directly into the step-by-step workflows agents follow.
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 what’s needed to guide the agent).
Agent Skills
Production-grade engineering skills for AI coding agents.
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.
Commands
9 slash commands that map to the development lifecycle. Each one activates the right skills automatically.
/spec/plan/build/test/constraints/review/webperf/code-simplify/shipIn Claude Code these install as plugin commands. Where a built-in command has the same name, as
/reviewdoes, use the namespaced form:/agent-skills:review.Want fewer manual steps once the spec exists?
/build autogenerates the plan and implements every task in a single approved pass — 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 — designing an API triggers
api-and-interface-design, building UI triggersfrontend-ui-engineering, and so on.Quick Start
Fastest path — any agent, one command. The open skills CLI installs into 70+ agents (Claude Code, Cursor, Codex, Copilot, Cline, and more):
Or grab individual skills:
Prefer a native integration? Pick your tool below.
Claude Code (recommended)
Marketplace install:
Local / development:
Cursor
Put workflow skills under
.cursor/skills/(sync fromagent-skills/skills/) and short policies in.cursor/rules/*.mdc— do not paste full skills into rules. Both directories live in your project; this repo does not ship a.cursor/folder. See docs/cursor-setup.md.Antigravity CLI
Install as a native plugin for skills and subagents. In affected Antigravity CLI releases, legacy command TOMLs are reported as converted but their wrapper commands are not discoverable; invoke the underlying namespaced skills directly. See docs/antigravity-setup.md.
Install from the repo:
Install from a local clone:
Gemini CLI
Install as native skills for auto-discovery, or add to
GEMINI.mdfor persistent context. See docs/gemini-cli-setup.md.Install from the repo:
Install from a local clone:
Windsurf
Add skill contents to your Windsurf rules configuration. See docs/windsurf-setup.md.
OpenCode
Copy skills to
.opencode/skills/(or~/.config/opencode/skills/), add a project-localAGENTS.md, and use the built-inskilltool for agent-driven execution. Optional slash commands can be added under.opencode/commands/.See docs/opencode-setup.md.
GitHub Copilot
Use agent definitions from
agents/as Copilot personas and skill content in.github/copilot-instructions.md. The lifecycle slash commands (/spec,/plan,/build,/test,/review,/ship) are Claude Code commands and do not appear in Copilot; invoke the skills by name (/spec-driven-development, …) instead. See docs/copilot-setup.md.Using the standalone
copilotCLI? Install it as a plugin — see docs/copilot-cli-setup.md.Kiro IDE & CLI
Skills for Kiro reside under ".kiro/skills/" and can be stored under Project or Global level. Kiro also supports Agents.md. See Kiro docs at https://kiro.dev/docs/skills/Codex
Install as a native Codex plugin (Codex CLI v0.122+):
The first command registers the marketplace; the second installs the plugin. Codex reads the root
skills/directory directly through.codex-plugin/plugin.json. Once installed, invoke skills in chat using@(e.g.,@spec-driven-development). See docs/codex-setup.md for local installation and troubleshooting.Command Code
Install natively with the built-in
cmd skillscommand. Command Code clones the repo, discovers everySKILL.md, and installs into.commandcode/skills/:Installed skills show up in the TUI slash menu, e.g.
/spec-driven-development. See docs/commandcode-setup.md.Other Agents
Skills are plain Markdown - they work with any agent that accepts system prompts or instruction files. See docs/getting-started.md. Hosts that install the pack but aren’t listed above are in docs/other-hosts.md.
Adoption
Already installed? How you roll the pack out depends on your codebase. The Adoption Guide covers two paths: the full lifecycle from day one for a greenfield project, or an incremental, verification-first rollout for an established codebase.
All 25 Skills
The commands above are entry points. The pack includes 25 skills total — 24 lifecycle skills plus the
using-agent-skillsmeta-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
Define - Clarify what to build
Plan - Break it down
Build - Write the code
Verify - Prove it works
Review - Quality gates before merge
Ship - Deploy with confidence
Agent Personas
Pre-configured specialist personas for targeted reviews:
/webperfSee docs/agents.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:
How Skills Work
Every skill follows a consistent anatomy:
Key design choices:
SKILL.mdis the entry point. Supporting references load only when needed, keeping token usage minimal.Project Structure
The portable core stays in shared directories. Host-specific paths are native discovery conventions, not branding aliases; renaming or merging them would break the tools that scan those exact locations.
skills/(25 skills)SKILL.mdworkflows used by every integrationagents/(4 personas),references/(7 checklists).claude/commands/(9 commands),.claude-plugin/,hooks/.gemini/commands/(9 commands)commands/(9 commands),plugin.json.codex-plugin/,.agents/plugins/skills/directlyplugin.jsonskills/by convention and does not register the lifecycle wrappersscripts/(13 scripts),evals/(25 case files),.github/workflows/docs/Tools without a checked-in adapter directory install or copy the shared
skills/core into their own native location. The Quick Start links the setup guide for each supported host.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 aren’t generic prompts - they’re the kind of opinionated, process-driven workflows that separate production-quality work from prototype-quality work.
Skills bake in best practices from Google’s engineering culture — including concepts from Software Engineering at Google and Google’s engineering practices guide. You’ll find Hyrum’s Law in API design, the Beyonce Rule and test pyramid in testing, change sizing and review speed norms in code review, Chesterton’s 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 aren’t abstract principles — they’re embedded directly into the step-by-step workflows agents follow.
How it compares
Wondering how this stacks up against Superpowers or Matt Pocock’s skills? See docs/comparison.md for an honest, side-by-side look at how the three are shaped differently and when to reach for each — including a link to a controlled head-to-head experiment.
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 what’s needed to guide the agent).
See docs/skill-anatomy.md for the format specification, CONTRIBUTING.md for guidelines, and docs/advanced-per-agent-configuration.md for applying model routing, tool restrictions, and other per-agent runtime controls without breaking the portable
SKILL.mdfrontmatter.Team
agent-skills is built and maintained by:
License
MIT - use these skills in your projects, teams, and tools.