Agent skill

Skill Creator

by wpsnote in wpsnote/wpsnote-skills

Create new skills or improve existing skills by clarifying intent, drafting SKILL.md instructions, organizing supporting resources, and doing lightweight manual review.

Apache-2.0Auto-check passedAgent Workflows

Install Skill Creator

skills CLI
$ npx skills add wpsnote/wpsnote-skills --skill skill-creator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install wpsnote/wpsnote-skills skill-creator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/wpsnote/wpsnote-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-creator .claude/skills/skill-creator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
skill-creator
GitHub stars
179
Token cost
~1.3k tokens
SKILL.md length
650 words
Files
6 (incl. scripts)
Skills in repo
37
Repo updated
First seen
Licence
Apache-2.0

At a glance

Create new skills or improve existing skills by clarifying intent, drafting SKILL.md instructions, organizing supporting resources, and doing lightweight manual review.

  • Works in 5 steps: Capture Intent → Draft the Skill → Organize Supporting Files → …
  • Users want to create a skill from scratch
  • SKILL.md covers Working Style, Workflow, Writing Guide and Deliverable
  • Runs Python scripts from its folder; calls python

What it does

Skill Creator is an agent skill from wpsnote/wpsnote-skills. Create new skills or improve existing skills by clarifying intent, drafting SKILL.md instructions, organizing supporting resources, and doing lightweight manual review. Use when users want to create a skill from scratch, revise a skill, package a skill, or improve a skill's trigger description.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `scripts/__init__.py`, `scripts/package_skill.py` and `scripts/quick_validate.py`).

It sits in Agent Workflows, covering Skill authoring. The licence is Apache-2.0.

When your agent uses it

  • Users want to create a skill from scratch
  • Package a skill
  • Improve a skills trigger description

Example prompts

  • “/skill-creator”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Capture Intent
  2. Draft the Skill
  3. Organize Supporting Files
  4. Review With Examples
  5. Validate And Package

What it can do on your machine

Read from SKILL.md and the folder at commit 2d9885d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skill Creator loads about 1.3k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 650 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from wpsnote/wpsnote-skills at commit 2d9885d, republished under its Apache-2.0 licence (© wpsnote). 650 words, ~1,292 tokens.

Download SKILL.mdSave it as .claude/skills/skill-creator/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
skill-creator
description
Create new skills or improve existing skills by clarifying intent, drafting SKILL.md instructions, organizing supporting resources, and doing lightweight manual review. Use when users want to create a skill from scratch, revise a skill, package a skill, or improve a skill's trigger description.

Skill Creator

This skill helps create and refine agent skills without assuming a heavy assessment framework. Keep the work practical: clarify what the skill should do, write the smallest useful instruction set, add supporting files only when they reduce repeated work, and validate the result with simple review prompts or real usage examples when helpful.

Working Style

  • Prefer clear skill boundaries over broad, generic behavior.
  • Keep SKILL.md readable and focused. Move long reference material into references/, reusable code into scripts/, and reusable templates or static files into assets/.
  • Do not create formal scoring harnesses by default. If the user asks for deeper validation, agree on the method first and keep it outside the published skill unless it is mature enough to maintain.
  • Use the repository's existing skill style when modifying a skill in an existing collection.
  • When in doubt, optimize for a skill that a future agent can load quickly and follow reliably.

Workflow

1. Capture Intent

Start by extracting what the user wants the skill to enable. If the current conversation already contains the workflow, derive the answer from that context before asking follow-up questions.

Clarify:

  1. What task or workflow should the skill help with?
  2. When should the skill trigger, and when should it not trigger?
  3. What inputs does the skill expect?
  4. What output or side effect should the user receive?
  5. What tools, files, apps, MCP servers, or external services are required?

Ask only for missing details that materially affect the skill design.

2. Draft the Skill

Create or update SKILL.md with:

  • YAML frontmatter containing name and description.
  • A concise overview of what the skill does.
  • Trigger boundaries and non-goals when they prevent confusion.
  • Step-by-step operating instructions.
  • Tooling notes, file locations, and safety constraints.
  • Output expectations.

The description is the main trigger signal. Make it specific enough that an agent can decide when to load the skill from metadata alone.

3. Organize Supporting Files

Use bundled resources only when they are useful:

  • scripts/: deterministic helpers, validators, converters, or repeatable setup code.
  • references/: longer instructions, schemas, examples, or domain notes that do not need to be loaded every time.
  • assets/: templates, static files, sample images, or other files used by the skill.

Reference these files from SKILL.md with clear instructions on when to read or run them.

Show full SKILL.md (268 more words)Show less
4. Review With Examples

For nontrivial skills, propose 2-3 realistic example prompts and inspect whether the instructions would lead to the intended behavior. Keep this lightweight:

  • Use examples that resemble actual user requests.
  • Check trigger fit, required tools, output shape, and edge cases.
  • Revise the skill when an example exposes ambiguity or unnecessary complexity.
  • Do not add formal scoring files or long-running comparison workflows unless the user explicitly asks for them.
5. Validate And Package

When a runnable skill folder exists, use the included helpers when appropriate:

bash
python skills/skill-creator/scripts/quick_validate.py <skill-directory>
python skills/skill-creator/scripts/package_skill.py <skill-directory> [output-directory]

Validation checks the basic skill shape and frontmatter. Packaging creates a distributable skill archive.

Writing Guide

Skill Anatomy
text
skill-name/
├── SKILL.md
├── scripts/
├── references/
└── assets/

Only SKILL.md is required. Add other folders when they make the skill easier to maintain or more reliable.

Frontmatter
yaml
---
name: example-skill
description: What this skill does and when to use it.
---

Use kebab-case for name. Keep description concrete, including important trigger phrases and boundaries.

Instruction Quality
  • Explain why an instruction matters when the reason helps future agents make good tradeoffs.
  • Prefer direct workflow steps over vague principles.
  • Keep examples short and representative.
  • Avoid absolute rules unless violating the rule would clearly break the workflow.
  • Keep unrelated policy, product, and implementation details out of the skill body.
Updating Existing Skills

When improving an existing skill:

  1. Read the current SKILL.md and any directly referenced resource files.
  2. Identify what behavior should change.
  3. Preserve working conventions unless they are causing the issue.
  4. Make scoped edits.
  5. Re-read the changed file to verify the instructions are coherent.

Deliverable

Finish by summarizing:

  • Which skill was created or changed.
  • Important trigger or workflow changes.
  • Any helper files added, removed, or kept.
  • Whether quick validation or packaging was run.

© wpsnote, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts) in skills/skill-creator of wpsnote/wpsnote-skills.

  • SKILL.md
  • LICENSE.txt
  • scripts/__init__.py
  • scripts/package_skill.py
  • scripts/quick_validate.py
  • scripts/utils.py

Open the folder on GitHubat commit 2d9885d

Compare with similar skills

Skill Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skill Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Creator this skillwpsnote/wpsnote-skills179—~1.3kAutomated safety check: PassApache-2.0
Skill CreatorAzure/azqr79489 repos~8.2kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k10 repos~3.5kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Claude Code Command Developmentanthropics/claude-plugins-official37k10 repos~4.8kAutomated safety check: PassApache-2.0
Claude Code Plugin Structureanthropics/claude-plugins-official37k10 repos~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    794 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Skill Developer Guide

    diet103/claude-code-infrastructure-showcase

    A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.

    10k GitHub starsUsed in 10 repos~3.5k tokens
    Agent WorkflowsAuto-check passed
  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Command Development

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.

    37k GitHub starsUsed in 10 repos~4.8k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Plugin Structure

    anthropics/claude-plugins-official

    Official

    Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.

    37k GitHub starsUsed in 10 repos~3.4k tokens
    Agent WorkflowsAuto-check passed
  • Skill Release Gate

    rohitg00/ai-engineering-from-scratch

    Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

    65k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from wpsnote/wpsnote-skills

All 37 skills in this repo
  • Content Digest

    wpsnote/wpsnote-skills

    将任意内容提炼为结构化知识笔记,自动保存到 WPS 笔记。只要用户给出任何内容(链接、图片、本地文件、粘贴文字)并有保存笔记的意图,就应使用此 skill。常见触发词:「总结」「提炼」「做笔记」「读书笔记」「学习笔记」「整理成笔记」「帮我看看」「帮我解读」「记一下」「存下来」「整理一下」「帮我归纳」。也适用于用户直接给出…

    179 GitHub stars~1.7k tokensUpdated 4 mo ago
    Auto-check passed
  • Content Creator

    wpsnote/wpsnote-skills

    【内容创作起点】用户想要写文章/公众号/文案时的首选skill. An agent skill from wpsnote/wpsnote-skills.

    179 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Doc Importer

    wpsnote/wpsnote-skills

    将本地文档批量导入到 WPS 笔记。支持扫描 Obsidian Vault、思源笔记、微信公众号存档、 下载目录或任意用户指定目录,自动识别 HTML、Markdown、PDF、DOCX、PPTX、XLSX 等格式, 转换为 WPS 笔记可读内容并保留图片和富文本格式。

    179 GitHub stars~2.7k tokensUpdated 4 mo ago
    Auto-check passed
  • Image Gen

    wpsnote/wpsnote-skills

    AI 图像生成助手,支持文生图和图生图,对接 OpenRouter / 阿里云百炼 / 火山方舟 / Google Gemini。

    179 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Literature Reader

    wpsnote/wpsnote-skills

    阅读、分析并总结学术文献(PDF论文),生成结构化的文献概要笔记。核心能力:论文元信息提取、研究问题识别、方法论梳理、实验结果分析、个人评价生成,以及多篇文献横向对比。支持中英文论文、单篇精读与批量文献综述。当用户提供 PDF 论文文件、要求阅读文献、总结论文、文献综述、论文概要、论文精读、paper summary、paper review、读论文、读…

    179 GitHub stars~793 tokensUpdated 4 mo ago
    Auto-check passed
  • Paper Researcher

    wpsnote/wpsnote-skills

    学术论文全流程助手:搜索论文、下载 PDF、存入 WPS 笔记、精读分析。当用户说"搜论文"、"找论文"、"下载论文"、"读论文"、"帮我找 paper"、"搜一下 XXX 相关的论文"、"把这篇论文存到笔记"、"分析这篇论文"、"帮我做文献调研"时触发。支持 arXiv 和 OpenAlex 两个数据源,自动完成搜索→下载→转文本→写入 WPS 笔记→分析的完整闭环。

    179 GitHub stars~970 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Skill Creator

What does Skill Creator do?

Create new skills or improve existing skills by clarifying intent, drafting SKILL.md instructions, organizing supporting resources, and doing lightweight manual review. Skill Creator is an agent skill from wpsnote/wpsnote-skills.md instructions, organizing supporting resources, and doing lightweight manual review.

When should I use Skill Creator?

Skill Creator fits situations like: users want to create a skill from scratch; package a skill; improve a skills trigger description.

How do I install Skill Creator in Claude Code?

Run `npx skills add wpsnote/wpsnote-skills --skill skill-creator -a claude-code`. Or copy the skill folder (skills/skill-creator in wpsnote/wpsnote-skills) into .claude/skills/skill-creator in your project. Claude Code loads it when a task matches its description.

How do I install Skill Creator in Codex?

Run `npx skills add wpsnote/wpsnote-skills --skill skill-creator -a codex`. Or copy the skill folder (skills/skill-creator in wpsnote/wpsnote-skills) into .agents/skills/skill-creator in your project. Codex loads it when a task matches its description.

Can I use Skill Creator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wpsnote/wpsnote-skills --skill skill-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-creator, .gemini/skills/skill-creator, .github/skills/skill-creator and .opencode/skills/skill-creator in your project.

What does Skill Creator need to run?

Going by SKILL.md and its folder, Skill Creator needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Skill Creator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skill Creator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Skill Creator use?

Skill Creator is published under the Apache-2.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Creator use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Creator?

Skills that share tags, products or a category with Skill Creator: Skill Creator (Azure/azqr, 794 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Creator?

wpsnote (a GitHub organization) maintains it in wpsnote/wpsnote-skills, which has 179 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on May 25, 2026.

Source: wpsnote/wpsnote-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.