trove-plan
Implementation planning workflow. Use after brainstorm approval or for multi-step work that needs verifiable checkpoints.
- License 许可
- MIT
- 所属仓库
- bravew/trove
- 最近更新
- 2026-11-12
- Stars
- ★ 10
- Forks
- 1
01 前言 Front Matter
- name
- trove-plan
- metadata
- { "trove-category": "engineering", "trove-category-label": "Engineering" }
- description
- Implementation planning workflow. Use after brainstorm approval or for multi-step work that needs verifiable checkpoints.
- when_to_use
- write a plan; implementation plan; break this down; multi-step change
- user-invocable
- true
03 SKILL.md 正文
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --> <!-- Regenerate: bun run build:skills -->
Session Init
This skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.
If a sibling skill in this plugin matches the request more directly, defer to it. See AGENTS.md (or docs/routing.md in the marketplace) for the per-plugin routing index.
trove-plan
A plan is a sequence of verifiable checkpoints, not a wish list.
Throughput checkpoint
Before sequencing, answer four questions so the plan parallelizes safely and doesn't serialize work that's actually independent:
- Blocking first steps — what must land before anything else can start?
- Independent workstreams — what can proceed in parallel (disjoint files/subsystems)?
- Shared mutable state — what would two parallel workstreams both write? Eliminate the sharing or serialize that part.
- Smallest safe decomposition — the fewest checkpoints that each verify independently.
Keep an n/a answer in the list with a one-line reason rather than dropping it. Prefer several small checkpoints over a few large ones, staying within the seven-checkpoint cap below; each must be independently verifiable (static + runtime).
Plan Shape
Create at most seven checkpoints. Each checkpoint must include:
- The files or subsystem likely touched.
- The observable result after the checkpoint.
- The verification command or inspection needed before moving on.
Decision Gate: plan readiness
Context: Execution should start only when the checkpoints are independently verifiable. Question: Is this plan concrete enough to execute one checkpoint at a time? Options:
- A. Yes - execute checkpoint 1.
- B. Revise the plan.
- C. Stop for missing information. Default: B, because vague checkpoints make verification meaningless.
Handoff
When the user approves the plan, route to trove-execute-plan. Do not execute while still drafting the plan unless the user has explicitly asked for immediate implementation and the change is narrow.
04 同仓库更多 Skills
using-trove
Skill discipline anchor for the Trove marketplace. Loaded once per session; routes the agent to the right trove-* skill before code, planning, review, or git actions.
trove-write-skill
Skill authoring workflow. Use when creating or updating a Codex or Trove skill, including rubrics, tasks, metadata, and validation.
trove-worktree
Git worktree workflow for spikes, risky experiments, and broad refactors that should not disturb the user's current branch.
trove-why
Reconstruct design rationale and decision history from evidence — source control, issue tracker (Linear), docs (Notion), chat (Slack), error tracking (Sentry) — with calibrated confidence. Use for "why does X work this way", "why did we pick Y", regressions, and postmortems. Use trove-explain for how it works now.
trove-verify
Completion verification workflow. Use before claiming done, fixed, complete, ready, or shipped.
trove-unslop
Cut AI tells from writing — PR descriptions, release notes, specs, commit bodies, and replies. Use before finalizing prose, or when the user asks to clean up, de-slop, or make text sound human.