Agent skill

Skill Creator

by qzzqzzb in qzzqzzb/OpenClaudeScience

Create or update InternAgent skills. An agent skill from qzzqzzb/OpenClaudeScience.

MITAuto-check passedAgent Workflows

Install Skill Creator

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

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

GitHub CLI
$ gh skill install qzzqzzb/OpenClaudeScience 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/qzzqzzb/OpenClaudeScience.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
106
Token cost
~1.1k tokens
SKILL.md length
476 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Create or update InternAgent skills. An agent skill from qzzqzzb/OpenClaudeScience.

  • Works in 5 steps: Understand the user's intent before… → Choose the skill shape. → Pick a stable skill name. → …
  • The user wants InternAgent to create a reusable skill
  • SKILL.md covers Creation Workflow, Writing Guidance, Safety And Maintainability and InternAgent Placement
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Creator is an agent skill from qzzqzzb/OpenClaudeScience. Create or update InternAgent skills. Use this skill when the user wants InternAgent to create a reusable skill, turn a repeated workflow into a SKILL.md package, improve an existing skill, or decide what scripts, references, assets, and triggering description a skill should include.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: Bringing the Claude Science experience to the open-source world. The licence is MIT.

When your agent uses it

  • The user wants InternAgent to create a reusable skill
  • Turn a repeated workflow into a SKILL.md package
  • Improve an existing skill
  • Decide what scripts

Example prompts

  • “/skill-creator”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Understand the user's intent before writing files.
  2. Choose the skill shape.
  3. Pick a stable skill name.
  4. Write SKILL.md.
  5. Validate the result.

What it can do on your machine

Read from SKILL.md and the folder at commit 4a5f2ab. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    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 1.1k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 476 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from qzzqzzb/OpenClaudeScience at commit 4a5f2ab, republished under its MIT licence (© qzzqzzb). 476 words, ~1,051 tokens.

Download SKILL.mdSave it as .claude/skills/skill-creator/SKILL.md (or your agent's skills folder).
name
skill-creator
description
Create or update InternAgent skills. Use this skill when the user wants InternAgent to create a reusable skill, turn a repeated workflow into a SKILL.md package, improve an existing skill, or decide what scripts, references, assets, and triggering description a skill should include.

Skill Creator

Use this skill to create, improve, or review InternAgent skills.

InternAgent skills are reusable instruction packages. A skill is a directory that contains a required SKILL.md file and optional supporting resources:

text
skill-name/
+-- SKILL.md
+-- scripts/
+-- references/
`-- assets/

Creation Workflow

  1. Understand the user's intent before writing files.

    • What recurring task should the skill help with?
    • When should InternAgent use this skill?
    • What inputs, outputs, tools, credentials, or external services are involved?
    • Are there examples, edge cases, or success criteria?
  2. Choose the skill shape.

    • Use only SKILL.md for instruction-only workflows.
    • Add scripts/ when repeated code, deterministic parsing, file conversion, or API calls would otherwise be rewritten each time.
    • Add references/ for detailed documentation, schemas, policies, API notes, or long examples that should be loaded only when needed.
    • Add assets/ for templates, sample files, images, or other files used to produce outputs.
  3. Pick a stable skill name.

    • Use lowercase letters, digits, and hyphens only.
    • Keep the name short and specific.
    • Make the directory name match the name frontmatter value.
  4. Write SKILL.md.

    • Include YAML frontmatter with name and description.
    • Put trigger guidance in description, because InternAgent uses it before loading the body.
    • Keep the body focused on procedures, constraints, examples, and how to use bundled resources.
    • Prefer clear, general guidance over one-off details copied from the current conversation.
  5. Validate the result.

    • Confirm SKILL.md exists and frontmatter parses.
    • Confirm required fields are non-empty.
    • Confirm referenced files actually exist.
    • Run or syntax-check scripts when the skill includes them.
    • Test with at least one realistic user prompt when practical.
Show full SKILL.md (223 more words)Show less

Writing Guidance

Write skill descriptions that include both what the skill does and when it should trigger. A good description is specific enough to avoid accidental use, but explicit enough to trigger when the user phrases the request differently.

Good pattern:

yaml
---
name: report-builder
description: Create structured research or experiment reports from notes, data files, logs, or previous chat context. Use when the user asks InternAgent to produce a reusable report, summarize experiment outcomes, compare runs, or turn raw project material into a polished document.
---

Avoid putting "when to use this skill" only in the body. If the trigger condition is not in description, InternAgent may not load the skill.

Keep SKILL.md concise. Move long API documentation, schemas, policies, or examples into references/ and link them from the main file with clear instructions about when to read them.

Safety And Maintainability

  • Do not create skills that hide behavior from the user, exfiltrate data, capture credentials, or bypass authorization.
  • Do not store secrets in a skill. Describe the required environment variable or configuration instead.
  • Do not add unnecessary README, changelog, or installation guide files unless the user explicitly asks for them.
  • Prefer updating an existing relevant skill over creating near-duplicates.
  • If a skill is generated from a one-time workflow, generalize it so it remains useful outside the current thread.

InternAgent Placement

For project-provided skills, place the skill as a first-level directory under skills/, for example:

text
skills/my-skill/SKILL.md

For user-imported or generated runtime skills, prefer .internagents/imported-skills/my-skill/ so generated content does not accidentally become repository source.

When a skill should be active by default, add its relative path to skills.selected in deepagent.config.json.

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

Files

Just SKILL.md in skills/skill-creator of qzzqzzb/OpenClaudeScience.

Open the folder on GitHubat commit 4a5f2ab

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 skillqzzqzzb/OpenClaudeScience106—~1.1kAutomated safety check: PassMIT
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 today
    Agent WorkflowsAuto-check passed

More from qzzqzzb/OpenClaudeScience

  • Local Release Test

    qzzqzzb/OpenClaudeScience

    Use the repository-local GitHub Actions release workflow to publish prerelease test builds from development branches without touching the official InternScience/InternAgents release repository.

    106 GitHub stars~1.9k tokensUpdated 2 mo ago
    Auto-check: notes
  • Patent Disclosure Skill

    qzzqzzb/OpenClaudeScience

    通用中国专利挖掘发现与交底书生成全流程:扫描项目文档挖掘专利点、讨论融合、基于脱敏模版生成技术交底书、联网查新、生成后自检含逻辑闭环与公式参数一致性。| Patent mining, disclosure drafting, prior-art search, and consistency self-check.

    106 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check: notes

Categories

Questions about Skill Creator

What does Skill Creator do?

Create or update InternAgent skills. An agent skill from qzzqzzb/OpenClaudeScience. Skill Creator is an agent skill from qzzqzzb/OpenClaudeScience. Create or update InternAgent skills.

When should I use Skill Creator?

Skill Creator fits situations like: the user wants InternAgent to create a reusable skill; turn a repeated workflow into a SKILL.md package; improve an existing skill; decide what scripts.

How do I install Skill Creator in Claude Code?

Run `npx skills add qzzqzzb/OpenClaudeScience --skill skill-creator -a claude-code`. Or copy the skill folder (skills/skill-creator in qzzqzzb/OpenClaudeScience) 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 qzzqzzb/OpenClaudeScience --skill skill-creator -a codex`. Or copy the skill folder (skills/skill-creator in qzzqzzb/OpenClaudeScience) 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 qzzqzzb/OpenClaudeScience --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?

SKILL.md names no scripts, command-line tools or credentials: Skill Creator is instructions for the agent only.

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. Review the folder before installing.

What licence does Skill Creator use?

Skill Creator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Creator use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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, 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?

qzzqzzb (a GitHub user) maintains it in qzzqzzb/OpenClaudeScience, which has 106 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on July 13, 2026.

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