home / skills / duc01226 / easyplatform / skill-plan

skill-plan skill

Q: How concise should the main manifest be?

Keep it under 100 lines: a short purpose statement, compact workflow steps, and read directives to references for details.

Q: Which languages are preferred for executable scripts?

Prefer Node.js or Python for portability, include tests, and respect environment variable loading order.

safe

/.claude/skills/skill-plan

This skill helps you create and optimize Claude Code skills by guiding structure, references, scripts, and packaging workflows.

npx playbooks add skill duc01226/easyplatform --skill skill-plan

Review the files below or copy the command above to add this skill to your agents.

Files (7)

SKILL.md

2.7 KB

---
name: skill-plan
description: "[Tooling & Meta] Guide for creating effective skills, adding skill references, skill scripts or optimizing existing skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, frameworks, libraries or plugins usage, or API and tool integrations."
license: Complete terms in LICENSE.txt
---

# Skill Creator

Create and optimize Claude Code skills -- modular packages providing specialized workflows, tool integrations, and domain expertise.

## Skill Structure

```
.claude/skills/skill-name/
  SKILL.md        # Required. <100 lines. Quick reference.
  references/     # Docs loaded on-demand (also <100 lines each)
  scripts/        # Executable code (Node.js/Python preferred)
  assets/         # Output files (templates, images, fonts)
```

For detailed format spec, frontmatter fields, and file organization:
**⚠️ MUST READ:** `.claude/skills/skill-plan/references/skill-structure-guide.md`

## Creation Workflow

1. **Understand** -- Gather concrete usage examples; ask clarifying questions
2. **Plan** -- Identify reusable resources (scripts, references, assets) from examples
3. **Initialize** -- Run `scripts/init_skill.py <name> --path <dir>` for scaffold
4. **Implement** -- Write SKILL.md (<100 lines), create references/scripts/assets
5. **Package** -- Run `scripts/package_skill.py <path>` to validate and zip

## Constraints

- `SKILL.md` must be **<100 lines** (frontmatter + body)
- References/ files also **<100 lines** each; split further if needed
- **Progressive disclosure**: heavy content in references/, not SKILL.md
- Combine related topics into one skill (e.g., cloudflare-* -> devops)
- Imperative writing style ("Create X" not "You should create X")
- No "Task Planning Notes" boilerplate
- Scripts: prefer Node.js/Python, include tests, respect `.env` loading order

## Writing SKILL.md

1. Purpose statement (1-2 lines)
2. Decision tree or workflow steps (concise, <5 lines per step)
3. `Read:` directives to references/ for detailed guidance
4. No inline code examples >5 lines -- move to references/

## Quality Gate

Before finalizing, validate against checklist:
**⚠️ MUST READ:** `.claude/skills/skill-plan/references/skill-quality-checklist.md`

## Iteration

After using a skill on real tasks, watch for: Claude re-discovering known info, ignoring bundled scripts, false triggers, or missed triggers. Update SKILL.md, description keywords, or references accordingly.


## IMPORTANT Task Planning Notes

- Always plan and break many small todo tasks
- Always add a final review todo task to review the works done at the end to find any fix or enhancement needed

Overview

This skill guides creation and optimization of modular Claude Code skills that extend Claude with domain knowledge, workflows, integrations, and scripts. It codifies a compact skill manifest, on-demand reference docs, executable scripts, and assets so contributors can build consistent, testable skills. The aim is fast iteration, predictable triggers, and easy packaging for deployment.

How this skill works

Inspect concrete usage examples, extract reusable components, and scaffold a new skill with a manifest, references, scripts, and assets. Validate the package with automated checks, run tests for scripts, and iterate based on real usage to fix missed triggers or redundant behavior. Emphasize progressive disclosure: keep the manifest concise and place heavy content in reference files.

When to use it

Create a new Claude extension that bundles workflows, APIs, or plugin usage
Refactor or combine several small related skills into a single coherent skill
Add executable scripts or templates that Claude can call during tasks
Optimize existing skills to reduce hallucinations and improve trigger reliability
Package and validate a skill for sharing or deployment

Best practices

Start by gathering concrete examples and ask clarifying questions before designing
Keep the primary manifest brief (<100 lines); move detailed guidance to on-demand references
Design small, testable scripts in Node.js or Python and include unit tests
Use progressive disclosure so Claude loads heavy docs only when needed
Iterate after real-world use: monitor missed triggers, ignored scripts, and update keywords

Example use cases

Add a CRM integration skill that provides contact lookup, enrichment scripts, and reference docs
Create a data-processing skill with Python scripts, test cases, and templates for outputs
Combine multiple related monitoring utilities into a single devops skill with a decision tree
Update a language-specific library skill to include new API endpoints and usage examples
Package a plugin orchestration skill that sequences tool calls and handles errors

FAQ

How concise should the main manifest be?

Keep it under 100 lines: a short purpose statement, compact workflow steps, and read directives to references for details.

Which languages are preferred for executable scripts?

Prefer Node.js or Python for portability, include tests, and respect environment variable loading order.