Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yeachan-heo/local-build-reminder
Remind the user to rebuild OMC after editing TypeScript when running from a local fork. Triggered automatically by the AI whenever it notices it (or the user) just changed a src/**/*.ts file in an OMC dev install.
Passed 24 of 24 test cases with the skill, and 14 of 24 without it.
and 9 more in the full report
10 fixed14 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
I edited `.claude-plugin/plugin.json` to update a configuration field. Should I run npm run build before restarting the application?
| Checked | Without skill | With skill |
|---|---|---|
| The response indicates that no npm run build step is required for json configuration changes. | Missed | Passed |
The instructions your model reads when the skill loads.
Always-on reminder for OMC fork development. When OMC is running in local
mode (HUD shows [OMC#X.Y.ZL] with an L suffix), Claude Code loads compiled
JavaScript from dist/ — NOT TypeScript source from src/. Edits to .ts
files are invisible to the running plugin until npm run build regenerates
dist/.
The AI should mention this reminder whenever any of these happens:
src/**/*.ts in this repo.Surface one clear sentence followed by the exact command. Don't repeat the reminder on every turn — once per "round" of TS editing is enough. Example:
Heads up: you edited
src/.... Runnpm run buildbefore restarting Claude Code —dist/won't reflect the change otherwise.
If multiple TS files were edited in a row, just remind once at the end.
.mjs / .cjs / .md / .json — those load directly
from disk, no build needed.L in the HUD).tsc --watch / npm run dev:full is already running in the background
— those rebuild automatically on save.test cases passed, vs 14 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.