233i/agent-skills

Production-grade engineering skills for AI coding agents.

6Stars on the repository
35Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

build

01

233i/agent-skills

Command Claude Code

A command for completing planned tasks one at a time through testing, implementation, building, verification, and a clear commit. It uses the task's acceptance criteria and existing project patterns as guidance.

6 4mo ago A 18 tokens original MIT

code-simplify

02

233i/agent-skills

Command Claude Code

A command for making recently changed or user-selected code easier to read and maintain without changing what it does. It looks for issues such as deep nesting, long functions, repeated logic, vague names, and unused code.

6 4mo ago A 23 tokens original MIT

plan

03

233i/agent-skills

Command Claude Code

A command for breaking planned work into small, verifiable tasks with clear acceptance criteria and dependencies. It reads the project specification and saves the plan in tasks/plan.md and the task list in tasks/todo.md.

6 4mo ago A 20 tokens original MIT

review

04

233i/agent-skills

Command Claude Code

A command for reviewing code changes across correctness, readability, architecture, security, and performance. It reports findings with file-and-line references and suggested fixes.

6 4mo ago A 21 tokens original MIT

ship

05

233i/agent-skills

Command Claude Code

A command for checking whether a project is ready for production deployment. It reviews code quality, security, performance, accessibility, infrastructure, and documentation, while requiring a rollback plan.

6 4mo ago A 12 tokens original MIT

spec

06

233i/agent-skills

Command Claude Code

A command for defining a project before coding begins. It asks clarifying questions, creates a structured specification, and saves it as SPEC.md for approval.

6 4mo ago A 17 tokens original MIT

test

07

233i/agent-skills

Command Claude Code

A command for test-driven development, or TDD: writing a test that fails, implementing the behavior, and then checking that the test passes before refactoring. For bugs, it first adds a failing test that proves the problem.

6 4mo ago A 25 tokens original MIT