From silver-bullet
Writes SB phase plans with dependencies, assumptions, waves, TDD policy, acceptance criteria, and verification steps. Invoked via /silver:plan.
How this skill is triggered — by the user, by Claude, or both
Slash command
/silver-bullet:silver-plan <phase or change description><phase or change description>The summary Claude sees in its skill listing — used to decide when to auto-load this skill
SB-owned planning creates clear tasks, small waves, assumptions, dependencies,
SB-owned planning creates clear tasks, small waves, assumptions, dependencies, verification criteria, and explicit handoff to execution.
Do not delegate core planning to an external lifecycle plugin. The PLAN.md artifact is SB-owned.
Write or update .planning/phases/<phase>/PLAN.md. If no phase folder exists,
create the smallest sensible phase folder under .planning/phases/.
| Mode | When to use | How waves are organized |
|---|---|---|
| Standard (default) | Most phases | Horizontal layers: shared infrastructure, then service/API, then UI/presentation |
MVP vertical-slice (--mvp) | Phase 1 of a new project OR when the user asks for "walking skeleton" / "vertical slice" / "end-to-end from UI to DB" | Feature slices: each wave delivers a thin vertical cut (UI + API + DB) for one user-facing scenario. Prefer 2–3 slices per wave. Produces an optional SKELETON.md for phase 1 of a new project with no prior phases. |
Use --mvp when the user says "MVP", "vertical slice", "feature slice", "end-to-end first", or "walking skeleton". Default to standard otherwise.
SILVER BULLET > PLAN.**Mode:** mvp annotation).tdd before code edits;silver:verify can execute without inventing
criteria later.SKELETON.md when this is phase 1 of a new project with
no prior SUMMARY.md files. SKELETON.md describes the walking skeleton:
the minimal end-to-end path from UI to data store that proves the system
hangs together.The plan is complete only when:
npx claudepluginhub alo-exp/silver-bullet --plugin silver-bulletGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.