Skill

task_breakdown

Decomposes feature descriptions or GitHub issues into ordered subtasks with file-level scope, acceptance criteria, and optional gh issue create. Use when asked to "break down task", "decompose feature", "create subtasks", "plan implementation", "break this into tasks", "task list", or "implementation plan".

From task-breakdown

Install

Run in your terminal

npx claudepluginhub shouenlee/ghcp-dev-plugin --plugin task-breakdown

Tool Access

This skill uses the workspace's default tool permissions.

Skill Content

Task Breakdown

Decompose feature descriptions or GitHub issues into ordered implementation subtasks with file-level scope, acceptance criteria, and dependency ordering.

When to Use

You have a feature description or GitHub issue that needs to be broken into actionable subtasks
You want to plan an implementation with clear ordering and dependencies
You need to create GitHub issues for each subtask in a larger feature
You want to estimate complexity and scope before starting work

Prerequisites

A feature description, GitHub issue number, or branch/PR to analyze
gh CLI installed and authenticated (required only for fetching issues and creating subtasks as issues)

Workflow

Gather the feature or task to decompose:
- If the user provides a GitHub issue number, fetch it:
```
gh issue view <number> --json title,body,labels,comments
```
- If the user provides a description, use it directly
- If the user provides a branch name or PR, analyze the scope from the diff or description
Analyze the codebase to understand:
- Which files and modules will need changes
- Dependencies between components
- Existing patterns for similar features
- Test infrastructure and conventions
Break down into ordered subtasks, each including:
- Title: Clear, imperative-mood description (e.g., "Add User model with email and password fields")
- Files: Specific files to create or modify
- Acceptance criteria: Measurable conditions for "done"
- Dependencies: Which other subtasks must complete first
- Estimated complexity: Small / Medium / Large
Order subtasks by dependency (foundation first, integration last):
- Data models and schemas first
- Business logic and services next
- API endpoints / views
- Tests alongside or after implementation
- Documentation and cleanup last
Present the breakdown as a numbered list for the user to review.
Offer to create GitHub issues for each subtask:
```
gh issue create --title "<title>" --body "<body with acceptance criteria>"
```
- Add labels if specified
- Set up issue references between dependent tasks
Optionally create a tracking issue that links to all subtasks so progress can be monitored from a single place.

Troubleshooting

Problem	Cause	Solution
Issue not found	The issue number does not exist or `gh` is not authenticated	Verify the issue number and run `gh auth status` to check authentication
Scope too vague	The feature description lacks enough detail to identify files	Ask the user clarifying questions about expected behavior, affected components, and constraints
Circular dependencies	Two subtasks depend on each other	Merge the coupled subtasks into one or extract the shared concern into a separate subtask that both depend on

Similar Skills

cache-components

Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.

138.5k

algorithmic-art

3 files

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

103.7k

brand-guidelines

1 file

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

103.7k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitMar 5, 2026

Actions

View Source View Plugin View on GitHub View README