From xlfg-engineering
Internal xlfg phase skill. Use only during /xlfg runs to promote verified durable lessons into knowledge without copying the entire run into memory.
npx claudepluginhub flrngel/xlfg --plugin xlfg-engineeringThis skill is limited to using the following tools:
Use only during `/xlfg` orchestration.
Captures lessons from completed phases into .shipyard/LESSONS.md: successes, surprises, pitfalls, improvements. Use after shipping, retrospectives, or reflection triggers.
Extracts 1-3 key learnings (insights, playbooks, corrections, patterns) from completed knowledge work sessions and saves to docs/knowledge/ after approval, duplicate, and stale checks. Use after plans, analysis, or strategy.
Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.
Share bugs, ideas, or general feedback.
Use only during /xlfg orchestration.
Input: $ARGUMENTS (RUN_ID or latest)
Promote only verified, reusable lessons into durable knowledge and leave the next run a better starting point.
RUN_ID, DOCS_RUN_DIR, and DX_RUN_DIR.spec.mdmemory-recall.mdverification.mdreview-summary.md, risk.md, run-summary.mddocs/xlfg/knowledge/current-state.mddocs/xlfg/knowledge/*.mddocs/xlfg/knowledge/ledger.jsonldocs/xlfg/knowledge/.current-state.md for repo-wide durable handoff when appropriate; keep branch-local lessons in the run when they are not yet durable.ledger.jsonl.compound-summary.md and, when helpful, run-summary.md.workboard.md so compound is DONE.