eval-audit
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per…
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per SKILL.md's Global UX Rules. Dimension labels: see the canonical table in SKILL.md.
$ npx -y skills add Evol-ai/SkillCompass --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/eval-mergeContext preview
What this command does when you run it.
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per SKILL.md's Global UX Rules. Dimension labels: see the canonical table in SKILL.md.
> **Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per SKILL.md's Global UX Rules. Dimension labels: see the canonical table in SKILL.md.
Use the **Read** tool to load `.skill-compass/{skill-name}/manifest.json`. Verify:
1. `upstream_origin` exists in manifest (skill has a known upstream source) 2. At least 1 evo version exists (something to preserve) 3. Upstream version differs from last known upstream (there IS an update)
If any pre-condition fails: display the failure reason in the session locale and stop. Do not show raw error codes or internal field names — describe the problem and, where possible, suggest what the user can do next.
Use the **Read** tool to load all three versions.
Use the **Read** tool to load `{baseDir}/prompts/merge.md`. Pass:
Follow the merge prompt's region-by-region strategy. Present conflicts to the user for resolution.
After all conflicts resolved, display the complete merged SKILL.md. Ask user for confirmation before writing.
If confirmed: use the **Write** tool to save the merged version.
Use the **Read** tool to load `{baseDir}/shared/version-management.md`. Follow merge versioning rules:
Run eval-skill flow on the merged version. Compare against pre-merge local scores.
If regression detected (any dimension dropped > 2 points):
⚠ Post-merge regression detected.
The merged version scored lower than the pre-merge version. Choose:
› Rollback to pre-merge
Keep merged result
Compare the two versionsIf `--internal` or `--ci` is active: keep the merged result, log the regression, and continue without prompting.
After the merge (and any regression handling) completes successfully, present the following choice unless `--internal` or `--ci` is active:
✓ Merge complete. Recommend re-evaluating to confirm quality. Next step? › Re-evaluate (recommended) Done
If `--internal` or `--ci` is active: exit silently after writing results.
Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.
Repo: Evol-ai/SkillCompass
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per…
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per…
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per…
- **Recommended model: Claude Opus 4.6** (`claude-opus-4-6`). Directed improvement requires understanding complex rubric feedback and generating precise,…
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per…
**Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per…