learn

Extract patterns and decisions from completed campaign artifacts.

820|78|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/SethGammon/Citadel --skill learn-sethgammon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learn
Source: https://github.com/SethGammon/Citadel/tree/main/skills/learn
Command: npx skills add https://github.com/SethGammon/Citadel --skill learn-sethgammon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Post-campaign learning extractor reads a completed campaign file, its postmortem, and telemetry audit log to extract successful patterns, failed patterns, key decisions, and quality rule candidates. It writes findings to the knowledge base and optionally appends quality rules to harness.json to enable faster, repeatable improvements across future campaigns.

Core Features & Use Cases

  • Pattern extraction: reads campaign artifacts to identify successful and failed patterns with concrete evidence.
  • Decision capture: aggregates key decisions and rationales to guide future engineering and QA efforts.
  • Knowledge write-back: writes results to .planning/knowledge/ and can auto-update harness.json with quality-rule candidates.
  • Use case: after a completed campaign, run /learn to surface lessons and enforce repeatable improvements.

Quick Start

Trigger the learning pass by invoking /learn after a campaign completes to generate and persist pattern insights.

Frequently Asked Questions about learn

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract patterns from completed engineering campaigns?

Extract patterns from completed engineering campaigns by reading campaign artifacts, postmortems, and telemetry logs to identify successful and failed patterns with concrete evidence. The learning pass automatically writes these findings to the knowledge base.

What is the best way to capture key decisions and rationales after a campaign postmortem?

Capture key decisions and rationales after a campaign postmortem by aggregating them from telemetry audit logs and campaign files to guide future engineering and QA efforts. This ensures decisions are preserved with concrete evidence.

Can I auto-update harness.json with quality rules from past campaign telemetry?

You can auto-update harness.json with quality rule candidates generated from past campaign telemetry. The learning pass optionally appends these rules to enable faster, repeatable improvements across future campaigns.

How does pattern extraction work when a campaign postmortem is missing?

Pattern extraction gracefully handles missing postmortems by processing available campaign artifacts and telemetry logs. It extracts successful and failed patterns from existing data without failing when postmortem files are absent.

When do I need to run a knowledge write-back for software engineering campaigns?

Run a knowledge write-back after any completed software engineering campaign to surface lessons learned. It writes extracted pattern insights and key decisions to .planning/knowledge/ to enforce repeatable improvements.

Does the learning pass process empty campaigns or skip them entirely?

The learning pass gracefully handles empty campaigns by processing available artifacts without failing. It reads whatever campaign data exists, including telemetry logs, to extract any available patterns and decisions.