← ClaudeAtlas

mission-reviselisted

Revises an existing `project/mission.md` per the canonical-language file under spec/project/mission/. Invoke when the user says "revise the mission", "update project/mission.md", "flip mvp_status", "the MVP is achieved", "the stabilisation gate is satisfied", or equivalent German-language requests. Supports three operations: (1) revise statement, audiences, verifying-feature pointer, or time_bound; (2) flip `mvp_status` along the legal lifecycle (`defining→in_progress→achieved→stabilised`, plus regression path); (3) revise after stabilisation with the mandatory rationale. Verifies the stabilisation-gate conditions by reading `project/roadmap.md` and `project/sprints/` before allowing a flip to `stabilised`. Supports resume on re-invocation per `spec/claude/resumable-work/`.
nolte/claude-shared · ★ 0 · AI & Automation · score 76
Install: claude install-skill nolte/claude-shared
# Mission Revise Edits an existing `project/mission.md` against `spec/project/mission/<canonical_language>.md` (canonical language: English). The spec is the authority for legal lifecycle transitions and the stabilisation gate; this skill enforces them mechanically and writes the resulting diff with explicit user confirmation. ## German trigger phrases This skill also triggers on equivalent German-language requests, including: - "Mission überarbeiten" - "mvp_status umstellen" - "die Mission ist stabilisiert" ## Why this is a skill, not an agent - **Persistent on-disk artefact** — every revision mutates a versioned markdown file consuming skills (`mission-define` for first-write, future audits, the roadmap's `mvp` semantics) read; an agent would lose the persistent-state contract. - **Per-step user gating drives the lifecycle** — `mvp_status` flips are explicit operator decisions per the spec, never silently inferred from satisfying the conditions; the spec mandates that the operator confirm the flip after the skill has shown the satisfied conditions, so an agent's structured-report shape can't carry the gate. - **Output flows back into the main conversation** — the stabilisation-gate verification (which roadmap items are still open, which sprint closed last, whether a subsequent sprint has held) is itself useful conversational context; isolating it behind an agent boundary would obscure the operator decision the skill exists to support. - Counter-dimension considered: a