Skip to content

fix: tighten review skill early-exit and add blind spots#184

Merged
SimplyLiz merged 1 commit into
developfrom
fix/review-skill-refinements
Mar 24, 2026
Merged

fix: tighten review skill early-exit and add blind spots#184
SimplyLiz merged 1 commit into
developfrom
fix/review-skill-refinements

Conversation

@SimplyLiz

Copy link
Copy Markdown
Owner

Summary

  • Tightens early-exit from score≥80 to score≥90 + zero warns + <100 lines + no new files (per-check caps hide warnings at 80)
  • Adds "CKB's blind spots" section: logic errors, business logic, race conditions, incomplete refactoring, domain edge cases
  • Expands Phase 2 checklist: race conditions, incomplete refactoring, secrets beyond CKB's 26 patterns
  • Adds anti-patterns: trusting score≥80, skipping new files
  • All three copies synced: ~/.claude/commands/ckb-review.md, .claude/commands/review.md, embedded constant in setup.go

Test plan

  • go build ./cmd/ckb/... passes
  • go test ./cmd/ckb/... passes
  • Local skill, repo skill, and embedded constant are identical

🤖 Generated with Claude Code

…tion

Syncs local skill refinements to repo and embedded constant:

- Early exit now requires score>=90 + zero warns + <100 lines + no new
  files (score>=80 was unsafe due to per-check caps hiding warnings)
- Added "CKB's blind spots" section listing what the LLM must catch
  (logic errors, business logic, race conditions, etc.)
- Expanded Phase 2 checklist: race conditions, incomplete refactoring,
  secrets beyond CKB's 26 patterns
- Added anti-patterns: trusting score>=80, skipping new files

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@SimplyLiz SimplyLiz merged commit bf28787 into develop Mar 24, 2026
@SimplyLiz SimplyLiz deleted the fix/review-skill-refinements branch March 24, 2026 13:34
@github-actions

Copy link
Copy Markdown

🟢 Change Impact Analysis

Metric Value
Risk Level LOW 🟢
Files Changed 0
Symbols Changed 0
Directly Affected 0
Transitively Affected 0

Blast Radius: 0 modules, 0 files, 0 unique callers


Generated by CKB

@github-actions

Copy link
Copy Markdown

CKB Analysis

Risk Files +0 -0 Modules

📊 1 complex · 📚 156 stale

Risk factors: Small, focused change

Metric Value
Impact Analysis 0 symbols → 0 affected 🟢
Doc Coverage 8.333333333333332% ⚠️
Complexity 1 violations ⚠️
Coupling 0 gaps
Blast Radius 0 modules, 0 files
Index indexed (0s) 🆕
📊 Complexity · 1 violations
File Cyclomatic Cognitive
cmd/ckb/setup.go ⚠️ 31 ⚠️ 58
💡 Quick wins · 10 suggestions
📚 Stale docs · 156 broken references

Generated by CKB · Run details

SimplyLiz added a commit that referenced this pull request Mar 24, 2026
…tion (#184)

Syncs local skill refinements to repo and embedded constant:

- Early exit now requires score>=90 + zero warns + <100 lines + no new
  files (score>=80 was unsafe due to per-check caps hiding warnings)
- Added "CKB's blind spots" section listing what the LLM must catch
  (logic errors, business logic, race conditions, etc.)
- Expanded Phase 2 checklist: race conditions, incomplete refactoring,
  secrets beyond CKB's 26 patterns
- Added anti-patterns: trusting score>=80, skipping new files

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@github-actions

Copy link
Copy Markdown

CKB review failed to generate output.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant