weft-check
SkillDev toolsRuns the weft compiler over your project, fixes every error it reports, and rebuilds until validation is clean.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the weft-check skill
About this capability
COMMAND, not reference: Validate and build the weft program, fix diagnostics until clean. Run this when the user asks for this step by name. The sixteen `weft-` reference skills beside it are things you read; this is a procedure you carry out.
What this skill tells your AI
The instructions your AI receives, as published by weavemindai/weft in tangle/cline/.cline/skills/weft-check/SKILL.md and read by ahel’s review.
Run the compiler over this project and fix what it names, without running anything.
- Read the
weft-languageskill if you have not this session, and themetadata.jsonof any node type you are about to edit. Then:weft validate --file src/main.weft < src/main.weft. - Parse the diagnostics. Errors are
line:column messagewith a stable slug; the message names the fix. Fix every Error, then re-validate until the list is empty. Never route around a diagnostic, and never weaken the program to silence one: if a fix feels wrong, stop and say what the compiler is asking for instead. Alevel-too-largewarning is not an error, but answer it the same way: [the level rule] is a law, and the fix is a group, never a wider level. - Then
weft build. If it fails, read the error, fix, rebuild. - Report, in plain words: what was wrong, what you changed, and the current state (clean validate, clean build). No summary of the diff.
Signals
- GitHub stars
- 2k
- Forks
- 221
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
weft-check- Source
- github.com/weavemindai/weft