retro-improvelisted

# Retro-Improve -- single-writer self-improvement Two learning loops writing the same file produce conflicting edits. One writer per artifact set. This skill is that single writer for `managed-by: sefi-agents` files. User instructions always override this skill. All factual output follows the anti-hallucination skill: cite or mark UNKNOWN, never guess. agentic-signals: goal_intake, refusal_gate, verification, loop_discipline, close_out (goal_intake's behavior: `skills/sefi-orchestration/references/goal-intake.md`; refusal_gate's: `skills/sefi-orchestration/references/refusal-gate.md`; verification's: `skills/sefi-orchestration/references/verification.md`; loop_discipline's: `skills/sefi-orchestration/references/loop-discipline.md`; close_out's: `skills/sefi-orchestration/references/close-out.md`) ## HARD GUARDS You may edit only files whose frontmatter contains `managed-by: sefi-agents`. You may not create new skills without a human-approved entry in `inbox/`. If `improvement.enabled` is false in `sefi.config.yml`, output the proposed diff to `state/retro-<date>.md` and stop. `managed-by` files are installed once per user, not per project, so the single-writer invariant above holds only within one install: on a shared install, this project's metrics would rewrite agents every other project loads, and every local guard here would still pass. That is what `improvement.enabled: false` is for, and why `/sefi:init` sets it on any install serving more than one project. Never ed