5 Commits

Author SHA1 Message Date
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
Hawthorn
f65ab491be fix(docs): clarify Stop event matcher is optional, not disallowed
Validator (scripts/ci/validate-hooks.js line 182-184) only errors when
matcher is missing for non-EVENTS_WITHOUT_MATCHER events. For Stop (in
EVENTS_WITHOUT_MATCHER), matcher is optional — presence is allowed and
validated for type correctness, absence is also accepted.
2026-06-10 18:21:12 +05:30
Hawthorn
7c0a0049a8 fix: address second-round review comments
- Replace httpx.Retry references with correct httpx API usage across all files
  (httpx has no built-in Retry class; use HTTPTransport/Limits instead)
- Fix _check_summary to check first 100 words (not 100 characters)
- Fix template to only show → improvement arrow for non-5 scores
- Clarify hook documentation: hook echoes reminder, does not run evaluator
- Add return type annotation to main()
- Make required parameter keyword-only in _read_file_or_text
2026-06-10 17:59:25 +05:30
Hawthorn
2ea4d779a3 fix: address self-evaluation review comments
- Clarify that agent-evaluator reads skills/agent-self-evaluation/SKILL.md directly
- Standardize on Conciseness terminology, including helper names
- Remove invalid Stop hook matcher and avoid unsupported command-expression matcher examples
- Add explicit hook-integration reference path in SKILL.md
- Add summary and self-check fields to evaluate.py output, template, and agent spec
- Refactor evaluate.py clarity and input parsing helpers
- Remove unused task parameter from check_completeness

Validation:
- python3 -m py_compile skills/agent-self-evaluation/scripts/evaluate.py
- evaluate.py high/low example smoke tests
- node scripts/ci/validate-agents.js
- node scripts/ci/validate-skills.js
- node scripts/ci/validate-hooks.js
- node scripts/ci/validate-no-personal-paths.js
2026-06-10 17:25:24 +05:30
Hawthorn
bd45947941 feat(skills,agents): add agent-self-evaluation skill and agent-evaluator persona
Add structured 5-axis self-evaluation framework for agent output quality:
- Accuracy, Completeness, Clarity, Actionability, Conciseness
- Evidence-based scoring with concrete improvement suggestions
- Standalone Python evaluator script with keyword heuristics
- Detailed scoring anchors reference guide
- High-score and low-score annotated examples
- Reusable evaluation report template
- Optional hook integration for session-stop evaluation

Agent persona (agent-evaluator) provides a dedicated subagent
for applying the rubric to agent output with tool-backed verification.

All files tested: Python script runs, examples score correctly
(high 4.2, low 3.4), frontmatter parses clean, 183 lines (under 500).
2026-06-10 16:56:18 +05:30