AgentSkillsCN

flow-next-work

借助 Git 配置、任务跟踪、质量检查以及提交工作流，系统化地执行一个 Flow 巨型任务或子任务。无论是落实项目计划，还是逐条核对规范内容，此流程都能高效赋能。当 /flow-next:work 触发时，系统会根据 Flow ID（如 fn-1-abc、fn-1-abc.2，或沿用的 fn-1、fn-1.2）自动启动相关任务。

SKILL.md
--- frontmatter
name: flow-next-work
description: Execute a Flow epic or task systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan or working through a spec. Triggers on /flow-next:work with Flow IDs (fn-1-abc, fn-1-abc.2, or legacy fn-1, fn-1.2).

Flow work

Execute a plan systematically. Focus on finishing.

Follow this skill and linked workflows exactly. Deviations cause drift, bad gates, retries, and user frustration.

IMPORTANT: This plugin uses .flow/ for ALL task tracking. Do NOT use markdown TODOs, plan files, TodoWrite, or other tracking methods. All task state must be read and written via flowctl.

CRITICAL: flowctl is BUNDLED — NOT installed globally. which flowctl will fail (expected). Always use:

bash
FLOWCTL="${CLAUDE_PLUGIN_ROOT}/scripts/flowctl"
$FLOWCTL <command>

Hard requirements (non-negotiable):

  • •You MUST run flowctl done for each completed task and verify the task status is done.
  • •You MUST stage with git add -A (never list files). This ensures .flow/ and scripts/ralph/ (if present) are included.
  • •Do NOT claim completion until flowctl show <task> reports status: done.
  • •Do NOT invoke /flow-next:impl-review until tests/Quick commands are green.

Role: execution lead, plan fidelity first. Goal: complete every task in order with tests.

Ralph Mode Rules (always follow)

If REVIEW_RECEIPT_PATH is set or FLOW_RALPH=1:

  • •Must use flowctl done and verify task status is done before committing.
  • •Must stage with git add -A (never list files).
  • •Do NOT use TodoWrite for tracking.

Input

Full request: $ARGUMENTS

Accepts:

  • •Flow epic ID fn-N-xxx (e.g., fn-1-abc) or legacy fn-N to work through all tasks
  • •Flow task ID fn-N-xxx.M (e.g., fn-1-abc.2) or legacy fn-N.M to work on single task
  • •Markdown spec file path (creates epic from file, then executes)
  • •Idea text (creates minimal epic + single task, then executes)
  • •Chained instructions like "then review with /flow-next:impl-review"

Examples:

  • •/flow-next:work fn-1-abc
  • •/flow-next:work fn-1-abc.3
  • •/flow-next:work fn-1 (legacy format still supported)
  • •/flow-next:work docs/my-feature-spec.md
  • •/flow-next:work Add rate limiting
  • •/flow-next:work fn-1-abc then review via /flow-next:impl-review

If no input provided, ask for it.

FIRST: Parse Options or Ask Questions

Check configured backend:

bash
REVIEW_BACKEND=$($FLOWCTL review-backend)

Returns: ASK (not configured), or rp/codex/none (configured).

Option Parsing (skip questions if found in arguments)

Parse the arguments for these patterns. If found, use them and skip corresponding questions:

Branch mode:

  • •--branch=current or --current or "current branch" or "stay on this branch" → current branch
  • •--branch=new or --new-branch or "new branch" or "create branch" → new branch
  • •--branch=worktree or --worktree or "isolated worktree" or "worktree" → isolated worktree

Review mode:

  • •--review=codex or "review with codex" or "codex review" or "use codex" → Codex CLI (GPT 5.2 High)
  • •--review=rp or "review with rp" or "rp chat" or "repoprompt review" → RepoPrompt chat (via flowctl rp chat-send)
  • •--review=export or "export review" or "external llm" → export for external LLM
  • •--review=none or --no-review or "no review" or "skip review" → no review

If options NOT found in arguments

If REVIEW_BACKEND is rp, codex, or none (already configured): Only ask branch question. Show override hint:

code
Quick setup: Where to work?
a) Current branch  b) New branch  c) Isolated worktree

(Reply: "a", "current", or just tell me)
(Tip: --review=rp|codex|export|none overrides configured backend)

If REVIEW_BACKEND is ASK (not configured): Ask both branch AND review questions:

code
Quick setup before starting:

1. **Branch** — Where to work?
   a) Current branch
   b) New branch
   c) Isolated worktree

2. **Review** — Run Carmack-level review after?
   a) Codex CLI
   b) RepoPrompt
   c) Export for external LLM
   d) None (configure later with --review flag)

(Reply: "1a 2a", "current branch, codex", or just tell me naturally)

Wait for response. Parse naturally — user may reply terse or ramble via voice.

Defaults when empty/ambiguous:

  • •Branch = new
  • •Review = configured backend if set, else none (no auto-detect fallback)

Do NOT read files or write code until user responds.

Workflow

After setup questions answered, read phases.md and execute each phase in order.

Worker subagent model: Each task is implemented by a worker subagent with fresh context. This prevents context bleed between tasks and keeps re-anchor info with the implementation. The main conversation handles task selection and looping; worker handles implementation, commits, and reviews.

If user chose review, pass the review mode to the worker. The worker invokes /flow-next:impl-review after implementation and loops until SHIP.

Guardrails

  • •Don't start without asking branch question
  • •Don't start without plan/epic
  • •Don't skip tests
  • •Don't leave tasks half-done
  • •Never use TodoWrite for task tracking
  • •Never create plan files outside .flow/