sheldon/loop-loop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: tighten vague language across all prompt files

Browse Source 
- Remove blanket "write tests" instructions; tests only when
  acceptance criteria require them
- Replace arbitrary "30-50% rejection rate" with clear directive
- Replace "4/5 threshold" with "majority of claims" rule
- List concrete quality gate commands instead of "whatever project uses"
- Remove "learnings" from progress summary (too vague)
- Make error-leak pattern generic (not HTTP-specific)
- Align fix evaluator with updated test expectations
This commit is contained in:
Sheldon Finlay
2026-03-28 11:58:13 -04:00
parent f26bdce534
commit 60ce0fef54
7 changed files with 10 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
prompts/evaluator/explore.md
View File

@@ -37,7 +37,7 @@ Claims Verified:
## Grading Criteria
- **Accuracy**: How many claims are correct? (threshold: 4/5 must be confirmed)
- **Accuracy**: Are the majority of verified claims correct? If more than one claim is incorrect, reject.
- **Completeness**: Did it cover the important parts of the area?
- **Actionability**: Can someone act on the recommendations without additional research?