Agent skill

Skill Creator

by pretend1111 in pretend1111/claude-desktop-app

Walks through creating a new Claude skill from scratch or improving an existing one, asking what it should do, when it should trigger, and in what format.

Apache-2.0Auto-check passedAgent Workflows

Install Skill Creator

skills CLI
$ npx skills add pretend1111/claude-desktop-app --skill skill-creator -a claude-code

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

GitHub CLI
$ gh skill install pretend1111/claude-desktop-app 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/pretend1111/claude-desktop-app.git skills-src && mkdir -p .claude/skills && cp -r skills-src/electron/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
494
Used in
1 other repo
Token cost
~591 tokens
SKILL.md length
287 words
Files
18 (incl. scripts, references, assets)
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Walks through creating a new Claude skill from scratch or improving an existing one, asking what it should do, when it should trigger, and in what format.

  • Works in 3 steps: Understand intent → Write the SKILL.md → Confirm
  • Creating a new skill from scratch
  • SKILL.md covers When first invoked, greet the…, Creating a skill, Skill Writing Tips and Editing an Existing Skill
  • Runs Python scripts from its folder

What it does

On first use the agent greets the user and offers to create a new skill, edit an existing one, or optimize a description so the skill triggers reliably. For a new skill it asks, one question at a time, what the skill should enable, what phrases or contexts should trigger it, and what output format is expected, then writes a SKILL.md with a name and description to a skills folder, telling the user where it was saved and that it will be available in the next conversation.

Writing tips emphasize that the description is the primary trigger mechanism and should name both what the skill does and specific contexts it applies to, written slightly assertively to avoid under-triggering, with instructions kept under 200 lines, written in imperative form, explaining the reasoning behind a rule rather than just stating it, and including example input and output where helpful. Editing an existing skill follows the same pattern: read the current file, discuss the change, make a targeted edit and save it.

When your agent uses it

  • Creating a new skill from scratch
  • Editing or improving an existing skill's instructions
  • Rewriting a skill's description so it triggers more reliably

Example prompts

  • “Help me create a new skill for formatting CSV exports into clean tables.”
  • “This skill isn't triggering when I mention invoices. Fix its description.”
  • “Edit my existing meeting-notes skill to also extract action items.”

Workflow steps

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

  1. Understand intent
  2. Write the SKILL.md
  3. Confirm

What it can do on your machine

Read from SKILL.md and the folder at commit 8cbd7b7. 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 7 files in scripts/ (Python, from the files we listed), which the agent can run.

    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 591 tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 37 tokens; SKILL.md has 287 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~591
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

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 pretend1111/claude-desktop-app at commit 8cbd7b7, republished under its Apache-2.0 licence (© pretend1111). 287 words, ~591 tokens.

Download SKILL.mdSave it as .claude/skills/skill-creator/SKILL.md (or your agent's skills folder). This skill also uses 17 other files; get the full folder from GitHub.
name
skill-creator
description
Create new skills, modify and improve existing skills. Use when users want to create a skill from scratch or edit an existing skill.

Skill Creator

You are the Skill Creator. Help users create, edit, and improve skills (reusable instruction sets).

When first invoked, greet the user:

Welcome! I'm ready to help you create, improve, or evaluate a skill. Here's what I can help with:

  • Create a new skill from scratch — I'll guide you through defining what it does, writing the instructions, and testing it
  • Edit or improve an existing skill — refine its instructions or optimize how reliably it triggers
  • Optimize the description so the skill triggers reliably

What are you looking to do? Do you have something specific in mind, or are you starting fresh?

Creating a skill

Step 1: Understand intent

Ask the user (one question at a time, conversational tone):

  1. What should this skill enable Claude to do?
  2. When should this skill trigger? (what user phrases/contexts)
  3. What's the expected output format?
Step 2: Write the SKILL.md

Save to: ~/.claude/skills/<skill-name>/SKILL.md

markdown
---
name: skill-name
description: One-line description of what it does and when to use it. Be specific about trigger conditions. Make descriptions slightly "pushy" to avoid under-triggering.
---

Instructions for the skill go here.
Step 3: Confirm

Tell the user:

  • The skill has been created at ~/.claude/skills/<skill-name>/
  • It will be available in the next conversation
  • They can edit or improve it anytime

Skill Writing Tips

  • Description is critical — this is the primary trigger mechanism. Include BOTH what the skill does AND specific contexts. Example: instead of "Format data" write "Format tabular data into clean markdown tables. Use whenever the user mentions tables, CSV formatting, data organization, or wants to display structured data."
  • Keep instructions under 200 lines
  • Use imperative form ("Do X", not "You should do X")
  • Explain the WHY behind instructions — models work better with reasoning
  • Include examples of expected input/output when helpful

Editing an Existing Skill

  1. Read the existing ~/.claude/skills/<skill-name>/SKILL.md
  2. Discuss with the user what to change
  3. Make targeted improvements
  4. Save the updated file

© pretend1111, 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 17 other files (scripts, references, assets) in electron/skills/skill-creator of pretend1111/claude-desktop-app.

  • SKILL.md
  • LICENSE.txt
  • agents/analyzer.md
  • agents/comparator.md
  • agents/grader.md
  • assets/eval_review.html
  • eval-viewer/generate_review.py
  • eval-viewer/viewer.html
  • references/schemas.md
  • scripts/__init__.py
  • scripts/aggregate_benchmark.py
  • scripts/generate_report.py
  • scripts/improve_description.py
  • scripts/package_skill.py
  • scripts/quick_validate.py
  • scripts/run_eval.py
  • … and 2 more

Open the folder on GitHubat commit 8cbd7b7

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in pretend1111/claude-desktop-app, which our catalogue first saw on October 7, 2026.

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 skillpretend1111/claude-desktop-app4941 repos~591Automated safety check: PassApache-2.0
Skill CreatorAzure/azqr79589 repos~8.2kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k11 repos~3.5kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Claude Code Command Developmentanthropics/claude-plugins-official38k10 repos~4.8kAutomated safety check: PassApache-2.0
Claude Code Plugin Structureanthropics/claude-plugins-official38k10 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.

    795 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 11 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.

    38k 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.

    38k 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.

    66k GitHub stars~1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from pretend1111/claude-desktop-app

  • Thorough Code Review

    pretend1111/claude-desktop-app

    Reviews code or recent changes for bugs, security issues, performance problems and maintainability, reporting findings by severity with the reason and a fix.

    494 GitHub starsUsed in 1 repo~502 tokens
    Auto-check passed
  • Project Scaffolder

    pretend1111/claude-desktop-app

    Scaffolds a complete, runnable project from scratch, covering web, Python and Node.js projects, with a working entry point and no placeholder code.

    494 GitHub starsUsed in 1 repo~498 tokens
    Auto-check passed
  • Frontend Design Principles

    pretend1111/claude-desktop-app

    Gives practical design rules for polished HTML, CSS and JavaScript interfaces and browser games, covering spacing, type, color, components, motion and responsive breakpoints.

    494 GitHub starsUsed in 1 repo~824 tokens
    Auto-check passed
  • Doc Writer

    pretend1111/claude-desktop-app

    Generate README, API docs, or user guides for code and projects.

    494 GitHub starsUsed in 1 repo~375 tokens
    Auto-check passed

Categories

Questions about Skill Creator

What does Skill Creator do?

Walks through creating a new Claude skill from scratch or improving an existing one, asking what it should do, when it should trigger, and in what format. On first use the agent greets the user and offers to create a new skill, edit an existing one, or optimize a description so the skill triggers reliably.md with a name and description to a skills folder, telling the user where it was saved and that it will be available in the next conversation.

When should I use Skill Creator?

Skill Creator fits situations like: creating a new skill from scratch; editing or improving an existing skill's instructions; rewriting a skill's description so it triggers more reliably.

How do I install Skill Creator in Claude Code?

Run `npx skills add pretend1111/claude-desktop-app --skill skill-creator -a claude-code`. Or copy the skill folder (electron/skills/skill-creator in pretend1111/claude-desktop-app) 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 pretend1111/claude-desktop-app --skill skill-creator -a codex`. Or copy the skill folder (electron/skills/skill-creator in pretend1111/claude-desktop-app) 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 pretend1111/claude-desktop-app --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.

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 591 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.

What are the alternatives to Skill Creator?

Skills that share tags, products or a category with Skill Creator: Skill Creator (Azure/azqr, 795 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, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Creator?

pretend1111 (a GitHub user) maintains it in pretend1111/claude-desktop-app, which has 494 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on April 22, 2026.

Source: pretend1111/claude-desktop-app on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.