본문으로 건너뛰기
cccskills
무료GitHub에 공개

power

Power batch-sprint helper — hosts the two behaviours that distinguish the `power` workflow track from spec-entry. (1) Per-ticket iteration: security runs once PER TICKET over workflow.json.tickets[] while the mechanical phases run once for the batch. (2) Commit split: at the commit phase, group the batch's working tree into ordered Conventional Commits via commit-split.mjs, closure last. Invoked within a `power`-track workflow; not a standalone feature. Opt-in via velocity.power_mode.enabled; requires git.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(3)

  • SKILL.md3.8 KB
  • commit-split.mjs5.5 KB
  • tests/commit-split.test.mjs2.5 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

power — batch-sprint track behaviours

The power track (in .claude/workflows.jsonl) delivers a sprint of related, spec-committed tickets in ONE cycle. It reuses the standard phase skills; this skill hosts the two behaviours that make it a batch pipeline rather than a single-ticket one. It is invoked from within a power-track workflow — never standalone.

Precondition

project.json → velocity.power_mode.enabled is true, track_id is power, the project is a git repo, and workflow.json → tickets[] lists the batch (the epic sliced-spec shape: one entry per ticket, each with its AC group + done-record). Off-flag, power is not selectable and nothing here runs.

Behaviour 1 — per-ticket judgment, amortized mechanics

The mechanical phases — spec, simplify, integrate, document, archive, and the commit-consent gate — run once for the batch. The judgment phase — security — runs once per ticket: the phase skill loops over workflow.json → tickets[], running its review for each ticket's AC group and write surface, and records a per-ticket verdict in the harness log (power_batch_reviews). This is a static DAG with in-skill iteration — there is no runtime node fan-out (the materializer cannot expand a runtime-sized list).

The amortization is mechanical-only and structurally visible — a per-ticket security review is never silently skipped. If any ticket's security raises a BLOCKER, the batch yields for it exactly as a single-ticket workflow would.

Behaviour 2 — commit split (closure last)

At the commit phase, the batch's working tree is split into a series of small, reviewable Conventional Commits so per-commit reviewability (bisect/revert) is preserved even though the cycle is large. commit-split.mjs composes on commit-planner's groupDirtyTree (single-concern grouping) and adds the power-specific ordering + closure-last rule. Feed it the dirty tree as [{path, status}] (the same shape groupDirtyTree consumes — parse it from git status --porcelain):

node .claude/skills/power/commit-split.mjs plan --json   # wraps commit-split.mjs -> planCommits

planCommits(entries) returns an ordered list of commit groups (config/build → implementation → tests → docs), each with a Conventional subject, and places the closing workflow.json + backlog stamp on the final commit — the closure-atomicity guard in git_commit_guard hard-blocks a closure split across commits, so it must land last. Source groups surface as feat; main context refines each to feat/fix at commit time. The commit phase commits each group in order under one workflow-scoped /grant-commit: one grant authorizes every commit in this workflow's landing, and only this workflow.

Constraints

  • Never amortize judgment. security is per-ticket; only mechanical ceremony is shared. Silent per-ticket skips are forbidden.
  • Reuse groupDirtyTree. commit-split.mjs imports commit-planner/inventory.mjs's groupDirtyTree; do not reimplement dirty-tree grouping.
  • Closure rides the final commit. Never split the closing workflow.json/backlog stamp across commits.
  • Requires git and the opt-in flag. Off-flag behaviour is byte-unchanged from the pre-power baseline.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

archive

무료

Phase 10.5 — move the slug's workflow artifacts (intake, scout, research, spec, approvals, swarm state, security reports, rendered diagrams) to docs/archive/<YYYY-MM-DD>/<slug>/. Runs before /commit so the committed tree is clean of work-in-flight files. workflow.json stays live and gets archived as the first step of /commit.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

friedbotstudio/baseline142026년 10월 13일 업데이트

Drift check between the baseline implementation on disk and the claims in `docs/init/seed.md` + cross-references in CLAUDE.md, README.md, and the rendered docs site. Verifies hook/agent/skill/command names + counts, settings.json wiring, project.json key presence, .mcp.json servers, vendored license files, and helper script presence. Exit 0 PASS / 1 FAIL — suitable for CI. Read-only; safe to invoke any time.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

friedbotstudio/baseline142026년 10월 13일 업데이트

PM-mode brainstorm helper. Captures the requirement via Socratic dialogue before any entry phase (`/intake`, `/spec`, `/tdd`) drafts its artifact. Stage 0 skip-check, Stage 1 gap-analysis, Stage 2 probe-loop, Stage 3 confirm-and-persist. Output lives at `docs/brief/<slug>.md`. Never proposes solutions — Stage 2 dialogue discipline is structurally enforced via `discipline.mjs`.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

friedbotstudio/baseline142026년 10월 13일 업데이트

brd

무료

Draft a Business Requirements Document (BRD) for cross-functional or stakeholder-heavy work that needs more structure than an intake. Use after `/intake` when the request spans multiple systems/teams, carries regulatory weight, or needs formal sign-off. Output lives at `docs/brd/<slug>.md`.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

friedbotstudio/baseline142026년 10월 13일 업데이트

chore

무료

Workflow track for tasks that need no TDD — documentation edits, governance count bumps, vendored-skill content updates, configuration tweaks, formatting, typo fixes, dependency bumps where no project code changes. Skips `/scenario` and `/implement` (no failing test to drive) and runs the work directly. `archive`, `memory-sync`, `/grant-commit`, and `/commit` remain mandatory. `verify`, `simplify`, `integrate`, and `document` are conditional — required when the diff hits one of the listed triggers, optional otherwise. `verify` is skipped only when the diff is pure-docs/prose AND `project.json → test.kind` is `behavior` (absent/invalid `test.kind` → `structural` → verify runs). Chore is a stripped-down pipeline, not a bypass; never silently skip a conditional phase whose triggers apply.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

friedbotstudio/baseline142026년 10월 13일 업데이트

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

friedbotstudio/baseline142026년 10월 13일 업데이트

friedbotstudio의 스킬 모두 보기

이 스킬의 문제 신고