leakage-check
www-zaq-ai/zaqScans the edited files of the current branch (or a given diff/PR) for cross-boundary concern leakage — channel/adapter logic leaking into Engine modules,…
Scores out of 100 · grade B+
2026-08-13Works
40% of the score100/100
- Loads cleanly: valid frontmatter, required fields present, no dangling references.
Maintained
25% of the score100/100
- no commits in the last 12 weeks
Adopted
20% of the score25/100
- 66 stars on the source repo.
Documented
15% of the score73/100
- 1,704 words with worked examples.
Install
npx skills add www-zaq-ai/zaq/leakage-checkWhat it says it does
Scans the edited files of the current branch (or a given diff/PR) for cross-boundary concern leakage — channel/adapter logic leaking into Engine modules, channel-specific knowledge (email, Mattermost) in generic modules, direct Bridge/adapter calls outside the channel layer, subset-only callbacks on global behaviours, BO web code bypassing NodeRouter, test-only affordances in production code, circular layer seams (A→B→A), and modules reading keys out of values contracted as opaque. Follows every seam touching an edited file to its far end (even into unedited files) and reconciles findings against unresolved PR reviewer threads. Identifies the exact file:line of every leak and drafts an implementation plan to fix them in docs/exec-plans/active/. Use whenever the user asks to check for leakage, boundary violations, separation-of-concerns problems, or "concerns leaking" into a module, or before requesting re-review on a PR that previously had leakage findings. Detection and planning only — never implements the fixes.
Also in www-zaq-ai/zaq
| Artifact | Score | What the check found | Type | Reach | Last commit |
|---|---|---|---|---|---|
| ux-designwww-zaq-ai/zaq | clean | Skill | 65 stars | today | |
| prototypewww-zaq-ai/zaq | clean | Skill | 66 stars | today | |
| create-workflowwww-zaq-ai/zaq | clean | Skill | 66 stars | today | |
| security-scannerwww-zaq-ai/zaq | clean | Subagent | 66 stars | today | |
| pr-review-agentwww-zaq-ai/zaq | clean | Skill | 66 stars | today | |
| replacewww-zaq-ai/zaq | clean | Skill | 66 stars | today |
Other code review skills
Browse all| Artifact | Score | What the check found | Category | Reach | Last commit |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowers | clean | Code review | 173,412 installs | 2 days ago | |
| scaffold-exercisesmattpocock/skills | clean | Code review | 241,781 installs | today | |
| financial-statementsanthropics/knowledge-work-plugins | clean | Code review | 3,719 installs | today | |
| review-contractanthropics/knowledge-work-plugins | clean | Code review | 3,017 installs | today | |
| backport-prvercel/next.js | clean | Code review | 142k stars | today | |
| create-prvercel/next.js | clean | Code review | 142k stars | today |
Put this measurement in your README
A badge carrying how many listings this index holds from the repository and how many pass every static structural check. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://skillworks.kynth.studio/?q=www-zaq-ai%2Fzaq)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.
