Comprehensive Learning

comprehensive-learning — Session Learning Pipeline

Single fire-and-forget skill running Phases 1–9 on all machines and Phases 10a+10 (cross-machine compilation + report) on dev-primary only.

Full phase specs: references/pipeline-detail.md — read it when you need signal sources, extraction rules, candidate formats, or state file details.

Mode-Based Routing

MACHINE=$(hostname -s 2>/dev/null || hostname | cut -d. -f1 | tr '[:upper:]' '[:lower:]')
case "$MACHINE" in
  dev-primary) CL_MODE="full" ;;
  dev-secondary) CL_MODE="contribute" ;;
  licensed-win-1|licensed-win-2) CL_MODE="contribute" ;;
  *) CL_MODE="contribute" ;;
esac
# All modes run Phases 1–9. Only 'full' runs Phase 10a (compilation) + Phase 10 (report).

Cross-Machine Data Flow

dev-primary git pull in Phase 10a picks up all machines' committed derived state.

Pipeline Summary

Run phases sequentially. Non-mandatory phases log failure and continue. Fatal failures in Phases 1 or 4 set _PIPELINE_EXIT=1. Phase 10 always runs via trap EXIT.

For phase details (signal sources, extraction rules, YAML formats): → read references/pipeline-detail.md

Session Design: Lean by Default

Sessions are pure multi-agent execution engines — all brain directed at the task. Analysis, maintenance, and learning are deferred to the nightly run.

Must NOT run standalone during sessions: /insights, /reflect, /knowledge, /improve, consume-signals.sh heavy analysis, ecosystem-health-check.sh, session-end-evaluate.sh scoring.

Stop hooks: one hook only, raw write, < 1 second. See WRK-304.

Scheduling

Crontab entry (dev-primary, 22:00 nightly):

0 22 * * * cd /mnt/local-analysis/workspace-hub && \
  bash scripts/cron/comprehensive-learning-nightly.sh \
  >> .claude/state/learning-reports/cron.log 2>&1

Script: scripts/cron/comprehensive-learning-nightly.sh — git pull is a hard gate; each rsync is independently || true.

Related

• workstations skill: machine registry and cron_variant fields
• WRK-299: implementation tracking | WRK-304: Stop hook cleanup | WRK-305: signal emitters
• WRK-303: Ensemble planning → Planning Quality Loop (in references/pipeline-detail.md)
• /insights, /reflect, /knowledge, /improve: individual pipeline stages
• scripts/planning/ — ensemble planning outputs harvested by Planning Quality Loop

Exit-Handoff Boundary

When the user asks to "document and prepare to exit," do not run the heavyweight comprehensive-learning pipeline in-session. Instead, create or update the task-specific durable handoff/report, verify commit/push/clean-state evidence, and leave deeper insights/reflect/knowledge/improve processing to the nightly pipeline. The exit response should be concise: handoff path, pushed commit(s), known dirty-state exceptions, external-action status, and remaining next steps.

For the concrete closeout checklist, use references/exit-handoff-closeout.md. Key requirements: write the handoff under docs/session-handoffs/ when no task-specific location exists, include final clean/sync proof for every touched tier-1 repo, commit and push the handoff unless blocked, inspect any hook-generated dirt before claiming clean state, and explicitly state that no external send/action was performed unless the user approved it.

For travel-planning sessions captured primarily as GitHub issues/comments rather than repo files, use references/github-issue-backed-travel-exit-closeout.md: verify issue/comment URLs live, write the control-repo handoff when the issue repo has no local checkout, stage only the handoff, and report synced-but-dirty control repo state precisely.

Iron Law

No learning pipeline phase (/insights, /reflect, /knowledge, /improve) shall run standalone during an active work session — learning is deferred to the nightly pipeline, always.

Explicit Skill-Library Update Requests

If the user explicitly asks to "review the conversation and update the skill library," do not hide behind the nightly deferral rule. Perform a targeted skill update using skill_manage against the currently loaded class-level skill or the closest existing umbrella. This is a bounded library-maintenance action, not the heavyweight comprehensive-learning pipeline. If a referenced support file is missing, create it immediately under references/ and keep SKILL.md pointing to it.

Use references/conversation-review-skill-update-mode.md as the operating checklist for this mode. Key rules: be active by default, patch loaded/governing class-level skills first, prefer support files under existing umbrellas over narrow one-session skills, and treat user corrections about style/format/workflow as first-class skill-library signals.

After targeted skill-library edits, treat the skill ledger as part of the closeout artifact set. A skill_manage patch/write can create or later append tracked ledger entries such as logs/orchestrator/hermes/skill-patches.jsonl; inspect that dirt after the primary skill commit, commit it separately if it is intentional metadata, then fetch/verify final HEAD == origin/<branch>. Do not claim a clean exit immediately after the first commit if hooks or skill tooling generated follow-up ledger dirt.

Rationalization Defense

Red Flags

These phrases signal you are about to violate the Iron Law:

• "let me quickly run /insights before we continue"
• "I should capture this learning now"
• "running /improve won't take long"
• "the session is winding down anyway"