What is the role of the orchestrator?

The orchestrator delegates all work to subagents via the Task tool, organizes tasks by dependency, and ensures tests and linting pass for any created or modified sources.

What happens when a subagent reports 'failed'?

The orchestrator records a brief summary of the issues, identifies failed tasks, and coordinates rework or retries with updated instructions until completion.

How are tests handled for modified sources?

For every source file created or modified, subagents must update the corresponding test file to achieve 100% coverage, with one test per scenario/behavior and combined tests for basic rendering where appropriate.

Implement a story according to the requirements and tasks

npx machina-cli add skill Intai/story-flow/implement-story-markdown --openclaw

Files (1)

SKILL.md

2.0 KB

Implement a story according to the requirements and tasks

Instructions

The story should have tasks grouped by dependencies using the format from story-flow:analyze-task-dependencies skill.
You are an orchestrator, not an implementer.
- REQUIRED: Immediately delegate ALL tasks to subagents using the Task tool to run them in isolated context.
- FORBIDDEN tools for orchestrator (NEVER use directly):
  - Glob, Grep, Read
  - Write, Edit, MultiEdit
  - WebSearch, WebFetch
  - TaskCreate, TaskUpdate, TaskGet, TaskList
  - Task with Explore subagent
Instruct each subagent:
- For every source file created or modified, update the corresponding test file to achieve 100% coverage and ensure all linting warnings and errors are resolved.
  - One test case per scenario/behavior, not one test per assertion.
  - Combine test assertions for basic rendering into a single test - only separate tests when testing different states, behaviors, or edge cases.
- Report back to the orchestrator just "completed" or "failed". On success, strictly nothing else. On failure, include a brief summary of the issues encountered.
When a story references the qa-tester subagent for planning BDD scenarios, use the qa-tester subagent and instruct it to load BOTH skills in this order using the Skill tool:
1. First: story-flow:plan-bdd-scenarios (plugin - general BDD planning protocol)
2. Then: plan-bdd-scenarios (project-level - overrides/extends the plugin)
3. Confirm both skills are loaded before continuing with BDD planning.

Example Inputs

Implement story according to @path/to/story.md
Implement story markdown @path/to/story.md
Implement story @path/to/story.md
Implement @path/to/story.md
Implement the following plan
Implement this plan
Execute this plan
Proceed with implementation

Source

git clone https://github.com/Intai/story-flow/blob/main/plugins/story-flow/skills/implement-story-markdown/SKILL.mdView on GitHub

Overview

This skill orchestrates implementing a story.md by grouping tasks using the story-flow:analyze-task-dependencies format. It acts as the coordinator, delegating all work to subagents via the Task tool, and ensures every modified source has corresponding tests updated to 100% coverage with clean lint results. When planning BDD scenarios, it uses the qa-tester subagent to load both story-flow:plan-bdd-scenarios and plan-bdd-scenarios in that order.

How This Skill Works

As an orchestrator, it analyzes the requirements, constructs a dependency-based task plan, and issues isolated Task tool calls to subagents to create or modify sources. Subagents must update all related test files to achieve 100% coverage, aggregate test results per scenario, and fix lint warnings or errors before reporting back. They respond with either 'completed' or 'failed' and, on failure, provide a brief summary of issues.

When to Use It

You need to implement a story.md with tasks grouped by dependencies using the story-flow:analyze-task-dependencies format.
You require that every created or modified source file has its test file updated to achieve 100% coverage and pass lint checks.
You want orchestration to happen via isolated subagents using the Task tool rather than direct implementation.
You are planning BDD scenarios and need to load qa-tester to coordinate planning with project-level overrides.
You must ensure tests are consolidated for basic rendering, with separate tests for different states, behaviors, or edge cases.

Quick Start

Step 1: Define the dependency-based task plan for the story.md using the story-flow:analyze-task-dependencies format.
Step 2: Instruct subagents to create/modify sources and update corresponding tests to achieve 100% coverage and resolve lint warnings.
Step 3: Collect subagents' reports; if any fail, review the brief failure summaries and iterate until all return 'completed'.

Best Practices

Define the dependency graph for the story using story-flow:analyze-task-dependencies before kicking off work.
Instruct subagents to update tests for every modified or created source to reach 100% coverage; test one behavior per scenario.
Combine basic rendering checks into a single test; create separate tests only for distinct states, behaviors, or edge cases.
Run a dedicated lint/coverage pass after changes and fix issues before reporting completion.
If BDD planning is required, load qa-tester to execute both story-flow:plan-bdd-scenarios and plan-bdd-scenarios in the specified order, and confirm both are loaded before proceeding.

Example Use Cases

Implementing a narrative feature in a storytelling app where tasks are dependent on character arcs and plot beats.
Coordinating a complex requirement-driven story flow with dependency-aware task planning for a markdown-based story generator.
Managing multiple microtasks for a lore/story engine, ensuring each source change is covered by tests.
Creating a story markdown renderer with tests that reflect different rendering states and edge cases.
Integrating QA planning via qa-tester to drive BDD scenarios for story composition and rendering.

Frequently Asked Questions

Add this skill to your agents