Claude Skills by tjdwls101010

Design, generate, validate, and maintain a complete Claude Code harness (CLAUDE.md, rules, skills, hooks, permissions, agents, workflows) for a project through a structured interview. Use when the user wants to create or set up a harness / CLAUDE.md / skills / hooks for a project, improve or extend an existing .claude/ setup, or asks how Claude should be configured to work on their codebase. Also triggers on Korean requests like "하네스 만들어줘", "하네스 구성해줘", "클로드 세팅해줘".

This body is unreachable via auto-trigger because the frontmatter above never closed.

A skill that references files that don't exist, to test dead-link detection.

A skill whose frontmatter hooks block is wrong in two ways, for the linter to find. Use when testing validate_harness.py against skill-scoped hooks.

This skill has no description field at all, so it can never auto-trigger.

Exercises argparse shapes the CLI self-description check must stay silent on. Use only as a false-positive fixture for validate_harness.py.

Handles the example domain task for this fixture project. Use whenever the user asks to run the example task or mentions the example workflow.

Guard the deploy script against being pointed at production by accident. Use when the user asks to deploy, ship, or release, and when a deploy command is being drafted. Not for local builds or test runs, which no guard covers.

Fixture skill for the package-closure check. Use when exercising validate_harness.py against a plugin-packaged skill.

A real skill. Use when testing the spec status check.

A skill the spec refers to by bare name rather than by a backticked repo-relative path. Use when testing that the two scripts agree on what counts as mentioned.

The one component in this fixture that actually exists on disk. Use when exercising the spec-vs-disk drift check in the direction that finds nothing missing.