| name | omcustomcodex:improve-report |
| description | Read-only report of improvement suggestions from eval-core analysis engine |
| scope | harness |
| user-invocable | true |
Improve Report
Display improvement suggestions from eval-core analysis engine as read-only report. No file modifications, no GitHub mutations.
Purpose
Surface actionable improvement suggestions gathered by the eval-core analysis engine. Reads from eval-core's local database and renders insights as structured markdown. Useful for understanding routing quality, skill effectiveness, and agent usage patterns.
Usage
/omcustomcodex:improve-report
Workflow
Step 1: Check eval-core availability
command -v eval-core 2>/dev/null || ls node_modules/.bin/eval-core 2>/dev/null
If not found โ skip to Step 4 (fallback).
Step 2: Run analysis
eval-core analyze --format markdown
Step 3: Data sufficiency check
Count sessions recorded from the output metadata:
| Sessions recorded | Confidence | Behavior |
|---|
| < 5 | [confidence: low] | Show results with message: "์ต์ 5์ธ์
์ด์์ ๋ฐ์ดํฐ๊ฐ ํ์ํฉ๋๋ค. ํ์ฌ ๋ฐ์ดํฐ๋ก๋ ์ด๊ธฐ ๋ถ์์ ๊ฐ๋ฅํ์ง๋ง, ์ ํ๋๋ ์ ํ์ ์
๋๋ค." |
| 5โ20 | [confidence: medium] | Show results with medium confidence note |
| > 20 | [confidence: high] | Show results normally |
Step 4: Display
If output contains data โ display as structured markdown with confidence annotation prepended.
If command not found OR output is empty:
[omcodex:improve-report] ๋ฐ์ดํฐ ์์
eval-core๊ฐ ์ค์น๋์ด ์์ง ์๊ฑฐ๋ ์์ง ์ถฉ๋ถํ ์ธ์
๋ฐ์ดํฐ๊ฐ ์์ง๋์ง ์์์ต๋๋ค.
eval-core๋ฅผ ์ค์นํ๊ฑฐ๋ ๋ ๋ง์ ์ธ์
์ ์งํํ ํ ๋ค์ ์คํํ์ธ์.
Notes
- Read-only: No file modifications, no GitHub issue creation, no external mutations
- R010 compliant: Only executes Bash for read-only analysis โ no write operations delegated
- Graceful fallback: Falls back silently if eval-core or its DB doesn't exist
- Confidence-aware: Reports data sufficiency alongside results per R011 conventions