chameleon-pr-review

Solid

Use when the user explicitly invokes /chameleon-pr-review to review a PR or branch diff against the repo's chameleon conventions, principles, and task requirements. Reports convention violations + logic gaps.

Code & Development 9 stars 3 forks Updated today MIT

Install

View on GitHub

Quality Score: 79/100

Stars 20%
33
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# PR Review with Chameleon Context Review code changes against this codebase's actual conventions, principles, and (optionally) the task spec. Combines convention compliance with logic review. ## Reviewer discipline This review follows the same discipline a senior reviewer applies (the superpowers `requesting-code-review` skill's `code-reviewer` template): be specific (always `file:line`); explain WHY each finding matters, not just what; never say "looks good" without checking; don't mark a nitpick as BLOCK; never give feedback on code you didn't actually read; and always give a clear verdict with its reasoning. The output leads with the verdict line (Step 4 format) and the one-sentence Verdict Reasoning that carries the superpowers "Ready to merge?" assessment, then the strengths, then the findings — a verdict-first order for the reader who needs the decision immediately, not the template's verdict-last order. Every finding is grounded in chameleon data or a removed hunk line — see the grounding loop below. ## Input formats ``` /chameleon-pr-review → convention-only review of current branch vs main /chameleon-pr-review PROJ-1234 → full review (conventions + Jira logic check) /chameleon-pr-review <PR-URL> → full review (conventions + linked Jira) /chameleon-pr-review <PR-URL> PROJ-1234 → full review (explicit PR + ticket) ``` ## The six-phase discipline Every review runs the pipeline the chameleon engine runs at turn end, p...

Details

Author
crisnahine
Repository
crisnahine/chameleon
Created
2 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category