Stats
Actions
Tags
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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/xlfg-engineering:xlfg-compound-phaseThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use only during `/xlfg` orchestration.
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.npx claudepluginhub flrngel/xlfg --plugin xlfg-engineeringCaptures 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.
Compiles patterns, decisions, and anti-patterns from completed campaigns and evolve cycles into structured wiki pages that integrate with existing knowledge. Runs a flush→compile→lint pipeline.