ECC/skills/agent-self-evaluation
Hawthorn 8d360fb466 fix: address remaining review nits
- Add top-level hooks wrapper to second JSON example (consistent with hooks.json format)
- Extract hardcoded thresholds as module-level constants (WALL_OF_TEXT_WORDS,
  SUMMARY_CHECK_WORDS, SUMMARY_CHECK_FIRST_N, TASK_OUTPUT_RATIO_HIGH/MEDIUM)

Skipped (not applicable):
- 'Scoring defaults to 5/5' — by design for heuristic fallback; SKILL.md already
  documents pairing with LLM judge for production use
- '--output silently ignored' — already fixed by _read_input refactor (checks
  args.output directly, not elif args.task and args.output)
2026-06-10 18:27:27 +05:30
..
examples fix: address second-round review comments 2026-06-10 17:59:25 +05:30
references fix: address remaining review nits 2026-06-10 18:27:27 +05:30
scripts fix: address remaining review nits 2026-06-10 18:27:27 +05:30
templates fix: address self-evaluation review comments 2026-06-10 17:25:24 +05:30
SKILL.md fix: address second-round review comments 2026-06-10 17:59:25 +05:30