comprehensive-learning-wrapper
Discoverable skill wrapper for the comprehensive-learning nightly pipeline. Provides session-invocable commands to trigger learning extraction, check pipeline status, and review recent learning reports. Bridges the cron-based pipeline to the skills tree.
Best use case
comprehensive-learning-wrapper is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Discoverable skill wrapper for the comprehensive-learning nightly pipeline. Provides session-invocable commands to trigger learning extraction, check pipeline status, and review recent learning reports. Bridges the cron-based pipeline to the skills tree.
Teams using comprehensive-learning-wrapper should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/comprehensive-learning-wrapper/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How comprehensive-learning-wrapper Compares
| Feature / Agent | comprehensive-learning-wrapper | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Discoverable skill wrapper for the comprehensive-learning nightly pipeline. Provides session-invocable commands to trigger learning extraction, check pipeline status, and review recent learning reports. Bridges the cron-based pipeline to the skills tree.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Comprehensive Learning — Skill Wrapper Discoverable entry point for the comprehensive-learning nightly pipeline. The pipeline itself runs via cron (`scripts/cron/comprehensive-learning-nightly.sh`) and is invisible to skill discovery without this wrapper. ## Why This Exists The learning extraction pipeline is the largest automated process in the ecosystem: - 10+ phases running nightly at 22:00 on dev-primary - Processes session signals, drift detection, knowledge harvesting - Produces learning reports, WRK items, memory updates But it was invisible to `/skills` discovery and could not be invoked on-demand. This wrapper makes it accessible via `/learn-extended` or similar commands. ## Canonical Pipeline The full pipeline lives at: - **Skill definition**: `.Codex/skills/workspace-hub/comprehensive-learning/` - **Cron wrapper**: `scripts/cron/comprehensive-learning-nightly.sh` - **Pipeline script**: `scripts/learning/comprehensive-learning.sh` - **Phase specs**: `.Codex/skills/workspace-hub/comprehensive-learning/references/pipeline-detail.md` ## On-Demand Commands ### Check Pipeline Health ```bash REPO_ROOT="$(git rev-parse --show-toplevel)" REPORT_DIR="$REPO_ROOT/.Codex/state/learning-reports" CRON_LOG="$REPORT_DIR/cron.log" echo "=== Pipeline health ===" # Last run time if [[ -f "$CRON_LOG" ]]; then LAST_RUN=$(tail -1 "$CRON_LOG" 2>/dev/null) echo " Last cron log entry: $LAST_RUN" else echo " WARNING: No cron log found at $CRON_LOG" fi # Most recent report LATEST_REPORT=$(ls -t "$REPORT_DIR"/*.md 2>/dev/null | head -1) if [[ -n "$LATEST_REPORT" ]]; then echo " Latest report: $(basename "$LATEST_REPORT")" echo " Report age: $(( ($(date +%s) - $(stat -c %Y "$LATEST_REPORT" 2>/dev/null || echo 0)) / 3600 )) hours" else echo " WARNING: No learning reports found" fi ``` ### Review Latest Report ```bash REPO_ROOT="$(git rev-parse --show-toplevel)" REPORT_DIR="$REPO_ROOT/.Codex/state/learning-reports" LATEST=$(ls -t "$REPORT_DIR"/*.md 2>/dev/null | head -1) if [[ -n "$LATEST" ]]; then head -80 "$LATEST" else echo "No learning reports available" fi ``` ### List Recent Learning Candidates ```bash REPO_ROOT="$(git rev-parse --show-toplevel)" CANDIDATES_DIR="$REPO_ROOT/.Codex/state/candidates" echo "=== Recent learning candidates ===" if [[ -d "$CANDIDATES_DIR" ]]; then ls -lt "$CANDIDATES_DIR"/*.md 2>/dev/null | head -10 else echo " No candidates directory found" fi ``` ### Manual Pipeline Trigger (use sparingly) The pipeline is designed for nightly cron execution. Running it during an active session violates the Iron Law documented in the comprehensive-learning skill. Only trigger manually in exceptional cases: ```bash REPO_ROOT="$(git rev-parse --show-toplevel)" # DRY RUN: list what phases would execute echo "Pipeline phases:" head -30 "$REPO_ROOT/scripts/learning/comprehensive-learning.sh" 2>/dev/null || echo "Script not found" echo "" echo "WARNING: Running the pipeline mid-session violates the Iron Law." echo "Use nightly cron instead. See: .Codex/skills/workspace-hub/comprehensive-learning/" ``` ## Scheduling Reference The cron entry on dev-primary: ``` 0 22 * * * cd /path/to/workspace-hub && bash scripts/cron/comprehensive-learning-nightly.sh >> .Codex/state/learning-reports/cron.log 2>&1 ``` ## Iron Law Reminder > No learning pipeline phase shall run standalone during an active work session. > Learning is deferred to the nightly pipeline, always. This wrapper provides read-only inspection commands that are session-safe. The actual pipeline execution is reserved for cron. ## Related - Primary skill: `.Codex/skills/workspace-hub/comprehensive-learning/` - Extract to issues: `.Codex/skills/extract-learnings-to-issues/` - Session corpus audit: `.Codex/skills/coordination/session-corpus-audit/` - Cron scripts: `scripts/cron/comprehensive-learning-nightly.sh`
Related Skills
comprehensive-learning
Single fire-and-forget command that runs the full session learning pipeline: insights → reflect → knowledge → improve → action-candidates → report. All machines run local Phases 1–9 against logs/orchestrator/ and commit derived state. dev-primary additionally runs Phase 10a (cross-machine compilation) and Phase 10 (report). Safe for cron scheduling. Use when session ends, nightly cron fires, or you want to harvest learnings from recent sessions. Replaces running 4 skills manually.
extract-learnings-to-issues
Extract unstructured user reflections and learnings, distill core themes, route insights to existing GitHub issues as contextual comments rather than creating duplicates.
agent-learnings-portability
Git-track AI agent learnings so they survive machine loss — memory snapshots, corrections, patterns, insights across Codex, Hermes, Codex, and Gemini.
provider-session-learning-transfer
Refresh provider session audit, identify post-audit/unassessed sessions, extract actionable learnings, and transfer them into repo notes and GitHub issues before a follow-up implementation session.
core-context-management-learning-from-past-work
Sub-skill of core-context-management: Learning from Past Work (+2).
doc-extraction-hybrid-classification-strategy-wrk-1188-learning
Sub-skill of doc-extraction: Hybrid Classification Strategy (WRK-1188 Learning).
test-oversized-skill
A test fixture skill that exceeds 200 lines with multiple H2/H3 sections for split testing.
interactive-report-generator
Generate interactive HTML reports with Plotly visualizations from data analysis results. Supports dashboards, charts, and professional styling.
data-validation-reporter
Generate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.
claude-reflection
Self-improvement and learning skill that helps Claude learn from user interactions, corrections, and preferences
agent-os-framework
Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.
OrcaFlex Specialist Skill
```yaml