# Learning Skill

> Distill reusable decisions and lessons into project memory and improvement actions. Use at milestones, closeout, or recurring failure patterns.

- Skill: `majesteitbart/learning-skill` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add majesteitbart/learning-skill`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majesteitbart/learning-skill/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: majesteitbart (https://skillmd.com/u/majesteitbart)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/majesteitbart/learning-skill

---


# learning-skill

## Trigger context
- milestone or project closeout
- recurring failure pattern detected

## Required inputs
- project_slug
- retrospective_notes
- execution_logs

## Output schema
- updated `decisions.md`
- reusable lessons summary
- follow-up improvement items

## Quality checks
- every lesson links to observed evidence
- lessons are actionable and specific
- next-cycle improvements are prioritized

## Failure behavior
- if evidence is weak, return evidence gaps first

## Allowed side effects
- update `.project/projects/<slug>/decisions.md`
- append to project context/progress docs

## Script hooks
- `bash .agents/scripts/query-log.sh --last 200`
- `bash .agents/scripts/pm/status.sh`

## Execution assets
- `references/runbook.md`
- `templates/retrospective.md`
- `templates/improvement-backlog.md`