@groupby/ai-dev 0.5.11 → 0.5.12

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@groupby/ai-dev",
3
- "version": "0.5.11",
3
+ "version": "0.5.12",
4
4
  "description": "Interactive installer for Rezolve Ai development content",
5
5
  "type": "module",
6
6
  "bin": {
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: team-code-review
3
3
  description: >-
4
- Review current changes against the repository's AI routing docs, working agreement, architecture, code-review checklist, and changed files. Use for phase reviews, final branch reviews, PR readiness checks, or focused reviews where findings should be prioritized before summary.
4
+ Review current changes against the repository's AI routing docs, working agreement, architecture, code-review checklist, and changed files. Scores the change across review axes (correctness, readability, architecture, security, performance) and tags each finding with a severity label so blockers are obvious. Use for phase reviews, final branch reviews, PR readiness checks, or focused reviews where findings should be prioritized before summary.
5
5
  ---
6
6
 
7
7
  # Team Code Review
@@ -28,39 +28,59 @@ Use this skill for read-first review work. The project docs define the review st
28
28
  - architecture or task-specific docs named by the router
29
29
  4. Inspect changed files and nearby code before writing findings.
30
30
 
31
- ## Review Standards
31
+ ## Review Axes
32
32
 
33
- Prioritize defects and regressions over style. Check:
33
+ Review the change across these axes and score each one. Scoring forces a deliberate pass over every axis instead of stopping at the first issue found.
34
34
 
35
- - correctness and user-visible behavior
36
- - architecture and documented conventions
37
- - security, permissions, and sensitive data handling
38
- - error handling and failure states
39
- - performance and lifecycle cleanup
40
- - accessibility for UI work
41
- - test coverage and validation gaps
42
- - docs drift caused by the change
35
+ - **Correctness** user-visible behavior, edge cases, error handling and failure states, test coverage and validation gaps.
36
+ - **Readability** — clarity, naming, and complexity. Could another engineer follow this without explanation?
37
+ - **Architecture** — documented conventions, module boundaries, and docs drift caused by the change.
38
+ - **Security** input validation, permissions, auth, and sensitive data handling.
39
+ - **Performance** — inefficient or expensive code, and lifecycle cleanup.
43
40
 
44
- If the code contradicts project docs, treat that as a finding unless the change deliberately updates the documented target state.
41
+ For UI work, also review accessibility (semantic markup, keyboard navigation, focus management) under Readability and Correctness.
42
+
43
+ Prioritize defects and regressions over style. If the code contradicts project docs, treat that as a finding unless the change deliberately updates the documented target state.
44
+
45
+ ## Severity Labels
46
+
47
+ Tag every finding so the reader instantly knows what blocks merge versus what is optional:
48
+
49
+ | Label | Meaning |
50
+ |---|---|
51
+ | `Critical:` | Blocks merge — security hole, data loss, broken or wrong behavior. |
52
+ | `Required:` | Must change before merge, but not merge-breaking on its own. |
53
+ | `Consider:` | Worth evaluating. A suggestion, not a blocker. |
54
+ | `Nit:` | Optional minor or style feedback. |
55
+ | `FYI:` | Informational only, no action needed. |
45
56
 
46
57
  ## Output
47
58
 
48
- Lead with findings ordered by severity. Include tight file and line references when possible.
59
+ Group findings by axis, and prefix each with its severity label. Include tight file and line references when possible. Lead with the axes that have the most severe findings.
49
60
 
50
61
  Use this shape:
51
62
 
52
63
  ```markdown
53
64
  ## Findings
54
- - [P1/P2/P3] file:line - Issue and impact.
65
+
66
+ ### Correctness
67
+ - Critical: file:line - Issue and impact.
68
+ - Consider: file:line - Issue and impact.
69
+
70
+ ### Security
71
+ - Critical: file:line - Issue and impact.
72
+
73
+ ### Readability
74
+ - Nit: file:line - Issue and impact.
55
75
 
56
76
  ## Open Questions
57
77
  - [Question]
58
78
 
59
79
  ## Summary
60
- [Brief assessment]
80
+ [Brief assessment, with a per-axis read and the total count by severity, e.g. "2 critical, 1 consider, 1 nit. Blocks merge until criticals are fixed."]
61
81
 
62
82
  ## Validation Gaps
63
83
  - [Gap]
64
84
  ```
65
85
 
66
- If the project workflow requires a review artifact, write it to the documented scratch location, commonly `tmp/review-phase-XX.md` or `tmp/review-final.md`.
86
+ Only include axes that have findings. If the project workflow requires a review artifact, write it to the documented scratch location, commonly `tmp/review-phase-XX.md` or `tmp/review-final.md`.