agentleFS
claude-worldclaude-world/director-mode-lite/skills/workflow/SKILL.md

workflow

Skill80 starsChanged 8 months agoMITView on GitHub

Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 54 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before dispatch, preserve the bounded exploration request and expected result.

    line 41
  2. Very specific:

    If Claude's Agent tool is unavailable or withheld, or Codex's spawn_agent interface is unavailable or withheld, the maximum depth is …

    line 42
  3. Distinctive:

    Goal: Ensure minimal viable implementation (YAGNI principle).

    line 66
  4. Distinctive:

    Goal: Ensure code is understandable.

    line 108

“Common” is measured: kept by at least 6 in 10 of the 54 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Development Workflow

A structured approach to software development that emphasizes understanding, minimal implementation, testing, documentation, and clean commits.


Overview

Step 1: Focus Problem    → Understand before coding
Step 2: Prevent Overdev  → Only build what's needed (YAGNI)
Step 3: Test First       → Red-Green-Refactor
Step 4: Document         → Keep it clear and current
Step 5: Smart Commit     → Conventional Commits

Step 1: Focus Problem (/focus-problem)

Goal: Thoroughly understand the problem before writing code.

Checklist

  • What is the user need? (Who / What / Why)
  • What defines success? (How to verify completion?)
  • What are the boundaries? (What NOT to do?)
  • What files/modules are affected?
  • Is there existing similar functionality?

Use Explore Agent

(Use the active provider's native dispatcher; Claude pseudo-code is shown below.)

Before dispatch, preserve the bounded exploration request and expected result. If Claude's Agent tool is unavailable or withheld, or Codex's spawn_agent interface is unavailable or withheld, the maximum depth is reached, or a concurrency limit rejects the call, do not retry or substitute assumptions. Return an incomplete dispatch_request and do not advance the workflow.

Choose exactly one provider-native form:

  • Claude Code: Agent(subagent_type="Explore", model="haiku", prompt="<bounded prompt>")
  • Codex CLI: spawn_agent(agent_type="explorer", task_name="workflow_explore", message="<bounded prompt>")
Agent(subagent_type="Explore", model="haiku", prompt="""
Explore the codebase for: [feature name] (thoroughness: medium)
Find related files, similar implementations, and test patterns.
""")

In Codex, send the same exploration request through spawn_agent(...); do not invoke the Claude example as a second dispatch.


Step 2: Prevent Overdev

Goal: Ensure minimal viable implementation (YAGNI principle).

Red Flags

"We might need this later..." → Don't build it now
"Just in case..." → YAGNI
"Let's make it generic..." → Solve current problem only
"We should create a framework..." → Write concrete implementation

Checklist

  • Is there immediate need for this?
  • Is this over-abstracted?
  • Can this be simpler?
  • Are we adding unnecessary dependencies?

Step 3: Test First (/test-first)

Goal: Strict TDD (Red-Green-Refactor).

Red Phase (Write Failing Test)

  • Write a test for expected behavior
  • Run test, confirm it fails
  • Failure message clearly indicates the issue

Green Phase (Minimal Implementation)

  • Write minimum code to pass test
  • Don't optimize yet
  • Run test, confirm it passes

Refactor Phase

  • Clean up code (keep tests passing)
  • Remove duplication
  • Improve naming
  • Simplify logic

Step 4: Document

Goal: Ensure code is understandable.

Checklist

  • README describes purpose and usage
  • Public APIs have docstrings
  • Complex logic has comments explaining "why"
  • No obvious-comment clutter

Step 5: Smart Commit (/smart-commit)

Goal: Clean version history with Conventional Commits.

Format

<type>(<scope>): <description>

Types

  • feat - New feature
  • fix - Bug fix
  • docs - Documentation
  • test - Tests
  • refactor - Code restructure

Quick Start

# Run full workflow
/workflow

# Or individual steps
/focus-problem "implement user login"
/test-first
/smart-commit

Related Skills

SkillPurpose
/focus-problemStep 1: Problem analysis
/test-firstStep 3: TDD cycle
/smart-commitStep 5: Create commit
/planBreak down complex tasks

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.