diff options
| author | Craig Jennings <c@cjennings.net> | 2026-05-06 06:17:08 -0500 |
|---|---|---|
| committer | Craig Jennings <c@cjennings.net> | 2026-05-06 06:17:08 -0500 |
| commit | aa6924591127970d3241ab6b1a50f4bab457da27 (patch) | |
| tree | 7e97590f711a173c8e7adfdff99e8d8298e64605 /root-cause-trace | |
| parent | ce66de633129abc94df03ab5da91ba2ca2e93330 (diff) | |
| download | rulesets-aa6924591127970d3241ab6b1a50f4bab457da27.tar.gz rulesets-aa6924591127970d3241ab6b1a50f4bab457da27.zip | |
refactor(skills): convert 16 user-invoked skills to commands
I converted 16 user-invoked skills to commands. Skills cost ~150-300 tokens each per session for descriptions the model uses to auto-route. Commands cost nothing until you type the slash. These 16 are workflows I always trigger deliberately. The auto-routing wasn't earning its keep. This reclaims ~4-5k tokens per session.
Nine skills stayed where auto-routing genuinely helps: debug, root-cause-trace, five-whys, add-tests, frontend-design, humanizer, playwright-js, playwright-py, and pairwise-tests. Pairwise-tests stays a skill because its helper files don't fit a single-file command shape.
For arch-decide, I preserved the upstream MIT LICENSE alongside the command at .claude/commands/arch-decide.LICENSE so attribution stays intact.
Diffstat (limited to 'root-cause-trace')
0 files changed, 0 insertions, 0 deletions