trove-workflow

Plugin trove-workflow from marketplace trove in bravew/trove. Commands read from the repo's manifest — yesterday.

Skills (24)

• trove-arena

  Spawn N parallel candidate attempts at one hard, novel artifact, pick the strongest base, graft the best ideas from the losers into it, then verify. A heavyweight technique — most work routes to trove-architect instead. Use only for a genuinely novel, hard-to-reverse design decision with no preceden

• trove-autoplan

  Front-door planning workflow. Take an idea and produce implementation-ready output by composing the Trove product skills (spec → user stories → release-note preview). Defers all detail to the leaf skills it calls.

• trove-brainstorm

  Feature and design brainstorming gate. Use before implementing a new feature, UI, refactor, or product change when no approved design exists.

• trove-debug

  Systematic debugging workflow. Use for bug reports, failing tests, broken behavior, red CI, regressions, or unexplained production symptoms.

• trove-dispatch

  Parallel-agent dispatch workflow. Use when a request contains multiple independent tasks that can be safely delegated.

• trove-execute-plan

  Execute an approved implementation plan one checkpoint at a time with verification before advancing.

• trove-plan

  Implementation planning workflow. Use after brainstorm approval or for multi-step work that needs verifiable checkpoints.

• trove-principle-data-shape

  Foundational Thinking — get the data shape right before writing logic. Choose core types and structures first; a late data-structure change is a rewrite, early it is a one-line diff. Use before writing logic, choosing core types, or sequencing scaffold-vs-feature work.

• trove-principle-encode-in-structure

  Encode Lessons in Structure — when you catch yourself writing the same instruction a second time, encode it as a lint, rubric, metadata flag, runtime check, or script instead of more prose. The repeated instruction is the symptom. Use when a correction recurs, or when tempted to add another \"rememb

• trove-principle-idempotency

  Make Operations Idempotent — design commands, lifecycle steps, and processing loops to converge to the same end state regardless of how many times they run or where a previous run stopped. Use when designing operations that run amid crashes, restarts, and retries (jobs, deploys, lifecycle steps, que

• trove-principle-laziness

  Laziness Protocol — aim for the most result with the least code and complexity; bias toward deletion and the smallest change that solves the problem. Use when refactoring, weighing diff size, or tempted to add abstractions, layers, or signal threading.

• trove-principle-migrate-then-delete

  Migrate Callers Then Delete Legacy APIs — when introducing a new internal API while old callers exist, migrate every caller and delete the old API in the same refactor wave instead of leaving a compatibility layer. Use when replacing an internal API, function, or module that has no external dependen

• trove-principle-type-discipline

  Type System Discipline — treat the type checker as a proof assistant: make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, don't lie to the compiler. Applies to any statically typed language. Use when designing types or a signature in T

• trove-receive-review

  Review-feedback handling workflow. Use when the user provides PR comments, code review feedback, or requested changes.

• trove-refactor

  Behavior-preserving change to structure: rename, extract, inline, dedupe, move, or migrate an internal API. Pin behavior first, migrate callers and delete the legacy API in one wave, prove behavior unchanged on the real artifact. Use for refactors and internal-API migrations.

• trove-reflect

  Mine the current session for durable learnings and route each into a concrete edit — a skill change or a learnings entry — never auto-applied. Use when the user says \"reflect\", or after a session that surfaced a recurring correction or a non-obvious project quirk.

• trove-ship

  Front-door ship workflow. Prepare a change for landing by composing the review and commit skills, surfacing a final Decision Gate before any destructive action. Thin orchestrator — defers detail to leaf skills.

• trove-show-work

  Keep a reviewable decision trail for long-running or unattended work: an append-only TSV log with one row per decision (what, why, evidence, result). Use for autonomous or multi-phase runs, or work a human reviews after stepping away.

• 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.

• trove-verify

  Completion verification workflow. Use before claiming done, fixed, complete, ready, or shipped.

• 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 fo

• trove-worktree

  Git worktree workflow for spikes, risky experiments, and broad refactors that should not disturb the user's current branch.

• trove-write-skill

  Skill authoring workflow. Use when creating or updating a Codex or Trove skill, including rubrics, tasks, metadata, and validation.

• 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.

Hooks (1)

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh

Similar plugins