audit

Audit Skill

Pre-flight

1. Check .claude/autoimprove/config.md exists. If not, stop: "Run /autoimprove:setup first."
2. Check git is available and working tree is clean.

Step 1: Run Measurement Suite

Run the measure skill to get the composite score and per-metric breakdown. Capture both the scores AND the raw command output for each metric.

For each metric defined in the config:

• Run the command (e.g., tsc --noEmit 2>&1, pnpm test 2>&1, pnpm lint 2>&1)
• Record the score (using the measure skill's scoring logic)
• Also capture the raw output for deficiency counting

Step 2: Count Individual Deficiencies

Parse the raw output from each command to count specific issues:

• Type errors: Count lines matching error patterns (e.g., error TS for TypeScript, error: for Rust). Group by file.
• Build: Pass/fail only — no granular count. If build fails, it becomes top priority.
• Tests: Count passing vs total from test runner output. Identify failing test names if any.
• Lint: Count warning/error lines from linter output. Group by rule if possible.

Step 3: Calculate Efficiency

For each metric with a gap (score < max):

1. Point gap = max_weight - current_score
2. Estimated iterations = ceil(issue_count / issues_per_iteration) using these heuristics:
   • Type errors: ~3 per iteration (clustered in files)
   • Lint warnings: ~2.5 per iteration
   • Tests (new): ~1 per iteration
   • Build fix: ~1-2 iterations
   • These are initial estimates — actual results will vary
3. Efficiency = point_gap / estimated_iterations
4. Estimated tokens = estimated_iterations × 22000 (rough average per iteration)

Read weights dynamically from .claude/autoimprove/config.md. If a metric is not applicable, skip it and redistribute weight as the measure skill already handles.

Sort areas by efficiency (highest pts/iteration first).

Step 4: Display Report

Print the audit report:

━━━ Codebase Audit ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 Current Score: XX/100

  [Metric 1]:  XX/WW  [progress bar]  (gap pts to max) or ✓ maxed
  [Metric 2]:  XX/WW  [progress bar]  (gap pts to max) or ✓ maxed
  [Metric 3]:  XX/WW  [progress bar]  (gap pts to max) or ✓ maxed
  [Metric 4]:  XX/WW  [progress bar]  (gap pts to max) or ✓ maxed

━━━ Fastest Path to 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

  #  Area          Gap    Issues  Est. iterations  Efficiency
  1  [best area]   Xpts   N items  M iterations    X.X pts/iter ← best
  2  [next area]   Xpts   N items  M iterations    X.X pts/iter
  ...

  Total: ~N iterations to reach 100/100
  ⚡ Estimated token usage: ~XXXK tokens (rough estimate, actual usage varies)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━