flow-work

Gitmaxd's avatarfrom Gitmaxd

Execute a plan file or Beads epic systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan, working through a spec, following documented steps, or executing a Beads issue ID (e.g., bd-123, gno-45, app-12).

⭐0stars🔀0forks📁View on GitHub🕐Updated Dec 31, 2025
[Project Management]

When & Why to Use This Skill

The flow-work skill is a high-performance execution agent designed to systematically implement development plans and Beads epics. It automates the software delivery lifecycle by managing git environments, tracking tasks via TodoWrite, and enforcing quality checks. By maintaining state through a progress tracking system, it ensures high fidelity to specifications and rigorous testing standards, making it an essential tool for structured technical project execution.

Use Cases

  • Executing complex feature implementations by following structured markdown plan files with automated progress tracking and state management.
  • Systematically resolving project management issues and epics (e.g., Beads IDs) with integrated git workflow and branch isolation.
  • Streamlining the development-to-review pipeline by chaining plan execution with automated code reviews and iterative bug fixing.
  • Resuming interrupted development sessions using the flow-progress tracking system to ensure no tasks are left half-done.
nameflow-work
descriptionExecute a plan file or Beads epic systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan, working through a spec, following documented steps, or executing a Beads issue ID (e.g., bd-123, gno-45, app-12).

Flow work

Execute a plan systematically. Focus on finishing.

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

Input

Full request: #$ARGUMENTS

Accepts:

  • Plan file: plans/<slug>.md
  • Beads ID(s) or title(s) directly
  • Chained instructions like "then review with /flow:impl-review"

Examples:

  • /flow:work plans/oauth.md
  • /flow:work gno-40i
  • /flow:work gno-40i then review via /flow:impl-review and fix issues

If no plan/ID provided, ask for it.

FIRST: Setup Questions (REQUIRED)

Before doing anything else, output these questions as text:

Check if rp-cli available: which rp-cli >/dev/null 2>&1

If rp-cli available, ask both:

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) Yes  b) No

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

If rp-cli NOT available, ask only branch:

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

(Reply: "a", "current", or just tell me)

Wait for response. Parse naturally — user may reply terse or ramble via voice. Do NOT read files or write code until user responds.

Workflow

After setup questions answered:

  1. Create flow-progress.txt at repo root to track session state (enables /flow:resume)
  2. Create TodoWrite list from plan tasks (use Factory.ai's TodoWrite tool for visibility)
  3. Read phases.md and execute each phase in order
  4. Update flow-progress.txt and TodoWrite after each task completion
  5. If user chose review: run /flow:impl-review after Phase 6, fix issues until it passes

Factory.ai Integration

  • Use TodoWrite tool to track tasks visibly in the UI
  • Parallelize independent tool calls when possible (e.g., multiple git commands)
  • Use Task tool with subagent_type for research agents

Guardrails

  • Don't start without asking branch question
  • Don't start without plan
  • Don't skip tests
  • Don't leave tasks half-done