2026-05-18 Team Document Daily Review

Workspace: /Users/jack/code/010-cpt/008-zhct/zhctprompt

normal review 855 archived threads Markdown + HTML loop C/D evidence labels preserved

Scope

Date window: 2026-05-18 00:00 to 20:33, Asia/Shanghai.

Rules used: DOCUMENT_REVIEW_LEARNING_LOOP.md and team-document-review-learning-loop/SKILL.md.

Recovery archive refreshed at /Users/jack/code/099-github/notebooklm-mcp/output/codex-thread-archives/snapshots/2026-05-18/203310.

Material was sufficient. This is not a no-material review.

Main Work Clusters

Cluster Document type Review stance
Perplexity Agent Skills method intake LLM wiki, skill quality gate, review page Good candidate; external method is C-level and local adaptation remains D-level until reused.
Agent skill design quality gate Project skill and compiled method Strong structure; lightweight validation substituted because the full validator lacked yaml.
Agent Control Room upgrade Registry, specialist runbooks, task bus, templates Useful architecture upgrade; runtime automation is not proven yet.
Task index updates TSV task evidence Good traceability; keep 13-column validation.
Touched historical evidence Manual, video, API and test docs No positive learning inferred from mtime alone.

Work Style By Role

Role Observed style Learning boundary
Jack / reviewer Converts teaching and article intake into project rules with review evidence. Preserve C/D labels until local proof exists.
Skill author Moves toward eval-first, route-description-first, gotcha-driven skill design. Do not claim all existing skills are audited.
Orchestrator Adds named agents, queues, templates, and handoff contracts. Manual pilot required before automation.
Specialist agents Separate code review, PM scheduling, WeDrive knowledge, product strategy, and delivery assets. No specialist writes or approvals without the existing gates.

Accepted Pattern Candidates

  1. Skill quality should start with routing and eval examples.
  2. External method adoption should carry evidence levels and local validation status.
  3. Skill bodies should keep judgment, gotchas, and stop rules rather than generic command lists.
  4. Agent control room should map skills to named roles and queues.
  5. File-based task bus is a low-risk bridge before runtime automation.
  6. Result templates should force validation, risk notes, and next actions.

Anti-Patterns And Quality Gates

External method as local law

Keep Perplexity as C-level and local adaptation as D-level until repeated local use validates it.

Premature automation

Do not claim L4 maturity before a manual task-bus pilot succeeds and is archived.

Casual description changes

Add positive, negative, adjacent-domain, and forbidden-load examples before changing skill descriptions.

Mtime-only learning

Only promote files with explicit new content, validation, review decision, or user feedback.

Next Actions

  1. Run one manual task-bus pilot before adding runtime automation.
  2. Create lightweight eval examples for agent-skill-design-quality.
  3. Add a registry validator for agent docs, queues, and referenced skill paths.
  4. Keep daily review separating accepted candidates, anti-patterns, and pending questions.