TDD Development Orchestrator

VerifiedSafe

Orchestrates a TDD-based development workflow: plans with a test-first approach, splits into trackable steps, saves to Obsidian vault, and executes sequentially. Delegates tasks to specialized agents via tmux. Helps structure complex implementations with clear progress tracking.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#tdd#workflow#orchestration#dev-process

Recommended for

Automated summary

Orchestrates a TDD-based development workflow by planning, saving to Obsidian, splitting into steps, and executing sequentially.

Strengths

  • Ensures test-first discipline
  • Breaks down tasks into manageable steps
  • Tracks progress via state file
  • Delegates to specialized agents

Limitations

  • Relies on specific Obsidian vault and tmux setup
  • Requires user confirmation for each phase
  • May be overkill for simple tasks
When to use it

Use when starting a new feature or refactoring that benefits from a systematic TDD approach.

When not to use it

Avoid for urgent fixes or exploratory coding where agility is needed.

Security analysis

Safe
Quality score85/100

The skill orchestrates a TDD workflow using fixed tmux send-keys commands to delegate tasks. No user input is injected into shell commands, and no destructive or exfiltration operations are performed. File operations are limited to creating a YAML file in a docs subdirectory.

No concerns found

How this analysis is made

Examples

Implement user login feature
Develop a user login module with email and password authentication, following TDD approach. Write tests first, then implement, then refactor.
Add pagination to list API
Add pagination support to the /api/users endpoint. Create a plan using TDD, split into steps, and execute.
Refactor payment service
Refactor the existing PaymentService class to use strategy pattern. Follow test-first development: write failing tests, implement, refactor, and track progress.

name: dev description: Orchestrate TDD-based development workflow – plan with test-first approach, save to Obsidian vault, split into trackable steps, and execute sequentially with status tracking. Acts as project manager, delegating tasks to specialized agents. allowed-tools: Bash(tmux:*)

Dev orchestrator

要件と簡単な仕様を元にTDDベースの計画を作成し、各stepに分割する。stepごとに実行し、完全な実装を目指す。

Requirements

  • Follow user's instructions ($ARGUMENTS)
  • Your main role is the project manager so assign tasks to other agents as far as possible

Procedure

  1. Setup: Initialize workflow state

    • Derive {branch_name} from current git branch (same rule as plan-on-md: feature/#468 → 468)
    • Create docs/{branch_name}/dev-workflow.yaml:
      save:
        status: Ready
      split:
        status: Pending
      execute:
        status: Pending
      
    • This MUST be done BEFORE entering plan mode
  2. Plan (execute yourself): Create TDD implementation plan using EnterPlanMode

    • Follow the TDD structure defined in tdd-plan.md — Red → Green → Refactor order
    • Get user approval via ExitPlanMode
  3. Save: Store the approved plan in Obsidian vault

    • Update YAML: save: In progress
    • Use tmux list-panes to find an available shell pane
    • Send: tmux send-keys -t <pane> 'claude "/plan-on-md"' Enter
    • Tell the user: "plan-on-md を別ペインに委譲しました。完了したら教えてください"
    • User confirms completion → Update YAML: save: Done, split: In progress
  4. Split: Break the plan into individual step files

    • Send: tmux send-keys -t <pane> 'claude "/plan-steps-split"' Enter
    • Tell the user: "plan-steps-split を別ペインに委譲しました。完了したら教えてください"
    • User confirms completion → Update YAML: split: Done, execute: In progress
  5. Execute: Run steps sequentially

    • Send: tmux send-keys -t <pane> 'claude "/proceed-by-step"' Enter
    • Tell the user: "proceed-by-step を別ペインに委譲しました。完了したら教えてください"
    • User confirms completion → Update YAML: execute: Done

IMPORTANT: Workflow State

A PreToolUse hook reads docs/{branch_name}/dev-workflow.yaml and injects the current workflow phase. The hook finds the first phase with status: Ready and directs you to execute that phase. After plan approval, your NEXT action is determined by the YAML status, not by implementing code directly. Status values follow status.md: Ready / In progress / In review / Pending / Done

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/tdd-development-orchestrator-mm78nmyf/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/tdd-development-orchestrator-mm78nmyf' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/tdd-development-orchestrator-mm78nmyf/download' --output '.skill-downloads/tdd-development-orchestrator-mm78nmyf/SKILL.md.part' && mv '.skill-downloads/tdd-development-orchestrator-mm78nmyf/SKILL.md.part' '.skill-downloads/tdd-development-orchestrator-mm78nmyf/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Bash(tmux:*)

Original excerpt: Requirements
  • Follow user's instructions ($ARGUMENTS)
  • Your main role is the project manager so assign tasks to other agents as far as possible

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/tdd-development-orchestrator-mm78nmyf/SKILL.md' && test -s '.skill-downloads/tdd-development-orchestrator-mm78nmyf/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/dev' && cp -R '.skill-downloads/tdd-development-orchestrator-mm78nmyf' '.claude/skills/dev'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/tdd-development-orchestrator-mm78nmyf'

openskills read 'tdd-development-orchestrator-mm78nmyf'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/tdd-development-orchestrator-mm78nmyf/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills