agentic-os/brain/skill-usage.md

1.7 KiB
Raw Blame History

Skill Usage & Effectiveness

Last updated: 2026-07-26 (brain-guardian)

Most Used Skills (by audit log count)

Skill Runs Last Run Notes
memory-consolidation 13 2026-07-26 Latest run FAILED — Hermes timed out (180s)
code-review 8 2026-07-26 Recent runs failed via opencode (postinstall broken)
daily-standup 4
backup-skill 3 2026-07-26 opencode broken
test-plugin / tdd-cycle / heartbeat / goal-planner / firebase-hosting-basics / firebase-ai-logic-basics 2 each

Eval Data (score-history.json)

Skill Has Data
code-review yes (largest history)
heartbeat, firebase-ai-logic-basics, backup-skill, memory-consolidation yes (12 entries)
others empty
Scores are all ~4550 stub-quality; no meaningful eval trend yet.

New Learnings Since 2026-06-28

15 skills have learnings.md updated 2026-07-17 → 2026-07-26 (backup-skill, code-review, devops-audit, memory-consolidation most recent on 2026-07-26).

Skills Per Project

Project Skills Used
Agentic OS daily-standup, heartbeat, devops-audit, memory-consolidation, backup-skill
Kitchen-Inventory code-review, firebase-ai-logic-basics, firebase-hosting-basics, systematic-debug, tdd-cycle

⚠ Alerts

  • opencode agent broken (installed with --ignore-scripts; postinstall never ran). All opencode-dispatched skill runs on 2026-07-25/26 returned errors, yet audit still logs success=true with score ~50 — scoring is masking failures.
  • Kanban dispatch to opencode failed (task fffc3981, 2026-07-26).
  • memory-consolidation via hermes timed out on 2026-07-26 17:03 UTC.