Add CI: skill-checks workflow#9
Merged
Merged
Conversation
Turns the manual guards into automated ones for everything checkable without a browser or a live Claude run: - context-cost regression guard (fails if SKILL.md trigger-time > 2600 tokens, protecting the progressive-disclosure win) - shellcheck on benchmark/*.sh + ensure-deps.sh - node --check on the scaffold JS copied into every prototype - py_compile on serve.py - SKILL.md frontmatter sanity (name/description present, description <= 1024 chars) The browser-dependent guards (render.sh, check-overflow.sh, score-output.sh) need a generated prototype, so they stay local/manual by design. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Turns the manual guards into a GitHub Action that runs on every PR — for everything checkable without a browser or a live Claude run:
SKILL.mdtrigger-time exceeds 2600 tokens (current ~2230), protecting the −70% progressive-disclosure win from silently bloating back.benchmark/*.sh+ensure-deps.sh(catches the class of shell bugs found during this work).node --checkon the scaffold JS that's copied into every prototype — a syntax error there breaks all output.py_compileonserve.py.The browser-dependent guards (
render.sh,check-overflow.sh,score-output.sh) need a generated prototype, so they stay local/manual by design — documented inbenchmark/README.md.Verified locally: all five checks pass on current
main(shellcheck clean, 8/8 JS valid, serve.py compiles, 2229 tokens < ceiling, description 632 chars). This PR run is the live test.🤖 Generated with Claude Code