Add claw-score agent skill#91452
Conversation
|
Codex review: needs real behavior proof before merge. Reviewed June 21, 2026, 12:26 PM ET / 16:26 UTC. Summary PR surface: Docs +1212, Other +12149. Total +13361 across 17 files. Reproducibility: yes. for the review blockers: source inspection shows the branch uses skill-local taxonomy and generated maturity-scorecard artifacts while current main uses root taxonomy.yaml and docs/maturity-scores.yaml. No runtime bug reproduction applies to this skill-promotion PR. Review metrics: 2 noteworthy metrics.
Stored data model Merge readiness Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch. Rank-up moves:
Proof guidance:
Risk before merge
Maintainer options:
Next step before merge
Security Review findings
Review detailsBest possible solution: Refresh or replace this branch on top of the current-main root scorecard model, route any renderer work through the active root-taxonomy renderer path if maintainers want it, and add redacted real-output proof before merge. Do we have a high-confidence way to reproduce the issue? Yes for the review blockers: source inspection shows the branch uses skill-local taxonomy and generated maturity-scorecard artifacts while current main uses root taxonomy.yaml and docs/maturity-scores.yaml. No runtime bug reproduction applies to this skill-promotion PR. Is this the best way to solve the issue? No; this is not the best merge shape while current main has a narrower root-source claw-score model. The safer path is to refresh onto that model or have maintainers explicitly accept the older copied renderer stack. Full review comments:
Overall correctness: patch is incorrect AGENTS.md: found and applied where relevant. Codex review notes: model internal, reasoning high; reviewed against c2ee9b0be8ae. Label changesLabel justifications:
Evidence reviewedPR surface: Docs +1212, Other +12149. Total +13361 across 17 files. View PR surface stats
What I checked:
Likely related people:
What the crustacean ranks mean
Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics. How this review workflow works
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e4487735ac
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| Treat `docs/kevinslin/maturity-scorecard/` as an artifact root maintained by | ||
| this skill. That includes: | ||
|
|
||
| - `docs/kevinslin/maturity-scorecard/README.md` | ||
| - `docs/kevinslin/maturity-scorecard/taxonomy.md` | ||
| - `docs/kevinslin/maturity-scorecard/taxonomy-outline.md` | ||
| - `docs/kevinslin/maturity-scorecard/maturity-scorecard.md` | ||
| - `docs/kevinslin/maturity-scorecard/inventory/**` |
There was a problem hiding this comment.
This skill declares docs/kevinslin/maturity-scorecard/ as the maintained artifact root, and later workflows require README.md, taxonomy.md, maturity-scorecard.md, inventory reports, and LTS.md; however the reviewed tree contains no docs/kevinslin/maturity-scorecard/** files at all. As a result, a user invoking the new skill’s default verification/scoring commands immediately hits missing-file failures instead of a usable scorecard workflow. Either commit the initial artifact root or change the skill/scripts so the documented defaults are generated before they are required.
Useful? React with 👍 / 👎.
| dependencies: | ||
| - mem |
There was a problem hiding this comment.
The new workflow commands run these Python scripts directly, and they import yaml/PyYAML, but the skill metadata only declares mem and the repo dependency I found is the Node yaml package, not Python PyYAML. In a fresh checkout without global PyYAML, the scoring/render/validation commands exit before doing any work, so agents cannot use the skill as documented unless the dependency is declared, bootstrapped, or removed.
Useful? React with 👍 / 👎.
clawsweeper
Bot
added
rating: 🧂 unranked krab
|
Closing as superseded by #94263, merged in |
2 participants
Summary
claw-scoreagent skill fromclaw/maintainersbranchdev/kevinlin/claw-score-discrawl-scopeinto.agents/skills/claw-score.agents/skills/claw-score/**in.gitignoreso the repo-owned skill can be trackedreferences/completeness/*.mdnote set for now and makecompleteness_instructionsoptional in the skill docs and render/validation scriptsmemdependency from the copied skill frontmatterVerification
git diff --check origin/main...HEAD -- .gitignore .agents/skills/claw-scorepython3 .agents/skills/claw-score/scripts/render_scorecard_from_taxonomy.py --validate-onlypython3 .agents/skills/claw-score/scripts/render_taxonomy_from_taxonomy.py --taxonomy-doc /tmp/claw-score-taxonomy.md --taxonomy-outline-doc /tmp/claw-score-taxonomy-outline.md