addyosmani/agent-skills

Production-grade engineering skills for AI coding agents.

92kStars on the repository
44Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

build

01

addyosmani/agent-skills

Command Claude Code

Part of agent-skills

Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.

not rated 92k +574 today A 27 tokens original MIT

code-simplify

02

addyosmani/agent-skills

Command Claude Code

Part of agent-skills

Simplify code for clarity and maintainability — reduce complexity without changing behavior.

not rated 92k +574 today A 14 tokens original MIT

constraints

03

addyosmani/agent-skills

Command Claude Code

Part of agent-skills

Define and enforce this project's quality bar — interview, sane defaults, CONSTRAINTS.md.

not rated 92k +574 today A 17 tokens original MIT

plan

04

addyosmani/agent-skills

Command Claude Code

Part of agent-skills

Break work into small verifiable tasks with acceptance criteria and dependency ordering.

not rated 92k +574 today A 13 tokens original MIT

review

05

addyosmani/agent-skills

Command Claude Code

Part of agent-skills

Conduct a five-axis code review — correctness, readability, architecture, security, performance.

not rated 92k +574 today A 16 tokens original MIT

ship

06

addyosmani/agent-skills

Command Claude Code

Part of agent-skills

Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.

not rated 92k +574 today A 21 tokens original MIT

spec

07

addyosmani/agent-skills

Command Claude Code

Part of agent-skills

Start spec-driven development — write a structured specification before writing code.

not rated 92k +574 today A 12 tokens original MIT

test

08

addyosmani/agent-skills

Command Claude Code

Part of agent-skills

Run TDD workflow — write failing tests, implement, verify. For bugs, use the Prove-It pattern.

not rated 92k +574 today A 23 tokens original MIT

webperf

09

addyosmani/agent-skills

Command Claude Code

Part of agent-skills

Run a web performance audit via the web-performance-auditor persona.

not rated 92k +574 today A 13 tokens original MIT

planning

10

addyosmani/agent-skills

Command Gemini CLI

Break work into small verifiable tasks with acceptance criteria and dependency ordering.

not rated 92k today A 0 tokens MIT

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: