Meta-skill that generates new Claude Code skills. An agent skill from idoforgod/Dissertation-Simulator-AgenticWorkflow.

MITAuto-check passedAgent Workflows

Install Skill Creator

skills CLI
$ npx skills add idoforgod/Dissertation-Simulator-AgenticWorkflow --skill skill-creator -a claude-code

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

GitHub CLI
$ gh skill install idoforgod/Dissertation-Simulator-AgenticWorkflow 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/idoforgod/Dissertation-Simulator-AgenticWorkflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/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
108
Token cost
~1.6k tokens
SKILL.md length
610 words
Files
4 (incl. references)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Meta-skill that generates new Claude Code skills. An agent skill from idoforgod/Dissertation-Simulator-AgenticWorkflow.

  • Works in 6 steps: Domain Analysis → Skill Architecture Design → Generate SKILL.md → …
  • Asked to create a skill
  • SKILL.md covers When to Use, Inherited DNA, Generation Protocol and Language Rules, plus 1 more section
  • Calls python3

What it does

Skill Creator is an agent skill from idoforgod/Dissertation-Simulator-AgenticWorkflow. Meta-skill that generates new Claude Code skills. Given a domain description, it creates a complete SKILL.md + references/ structure following AgenticWorkflow conventions. Use when asked to "create a skill", "make a new skill", or "generate skill for X".

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/ccp-contextualization-guide.md`, `references/quality-gates-guide.md` and `references/skill-template-guide.md`).

It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: AI 에이전트 58개가 협업하는 211-step 박사 논문 연구 시뮬레이션 시스템. AgenticWorkflow 프레임워크에서 태어난 자식 시스템. The licence is MIT.

When your agent uses it

  • Asked to create a skill
  • Make a new skill
  • Generate skill for X

Example prompts

  • “create a skill”
  • “make a new skill”
  • “generate skill for X”
  • “/skill-creator”

Requirements

  • Python 3

Workflow steps

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

  1. Domain Analysis
  2. Skill Architecture Design
  3. Generate SKILL.md
  4. Generate Reference Files
  5. Validate Generated Skill
  6. Register Skill

What it can do on your machine

Read from SKILL.md and the folder at commit f2205f5. 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

    Shell commands in SKILL.md call:

    • python3

    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 1.6k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 610 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.9k

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 idoforgod/Dissertation-Simulator-AgenticWorkflow at commit f2205f5, republished under its MIT licence (© idoforgod). 610 words, ~1,556 tokens.

Download SKILL.mdSave it as .claude/skills/skill-creator/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
skill-creator
description
Meta-skill that generates new Claude Code skills. Given a domain description, it creates a complete SKILL.md + references/ structure following AgenticWorkflow conventions. Use when asked to "create a skill", "make a new skill", or "generate skill for X".

Skill Creator — Meta-Skill for Generating Claude Code Skills

A meta-skill that produces new skill packages. It analyzes the target domain, designs the skill structure, and generates all required files following AgenticWorkflow's DNA inheritance patterns.

When to Use

  • User asks to create a new skill for a specific domain
  • User wants to automate a repeatable workflow as a skill
  • System needs to generate skills for thesis workflow agents

Inherited DNA

This meta-skill inherits the AgenticWorkflow genome. As a skill that generates other skills, it must itself embody the DNA it enforces.

DNA ComponentExpression in skill-creator
Absolute Criteria 1 (Quality)Generated skills are evaluated solely on output quality, not speed or token cost
Absolute Criteria 2 (SOT)Generated skills must define their SOT pattern; skill-creator validates this
Absolute Criteria 3 (CCP)Generated skills include CCP contextualization; CAP-1~4 anchored to domain
English-FirstAll generated skill instructions are in English; user-facing triggers may be bilingual
P1 ComplianceGenerated skills must include deterministic validation scripts
Quality GatesGenerated skills reference L0-L2 quality layers appropriate to their domain

Generation Protocol

Step 1: Domain Analysis

Analyze the target domain:

  1. What is the primary output of this skill?
  2. What inputs does it require?
  3. What quality criteria apply?
  4. Which tasks are deterministic (P1) vs. semantic (LLM)?

Ask the user a maximum of 4 questions (P4 rule), each with up to 3 choices. If the domain is clear enough, proceed without questions.

Step 2: Skill Architecture Design

Design the skill structure:

.claude/skills/{skill-name}/
├── SKILL.md              ← Main skill file (WHY + HOW)
└── references/           ← Supporting documents (WHAT/VERIFY)
    ├── {domain}-guide.md      ← Domain-specific guidance
    ├── {domain}-checklist.md  ← Quality checklist
    └── {domain}-examples.md   ← Before/after examples (if applicable)
Step 3: Generate SKILL.md

The generated SKILL.md must follow this template:

markdown
---
name: {skill-name}
description: {one-line description for skill matching}
# Optional — context isolation and agent type (see Selection Criteria below)
# context: fork          # omit for inline (default), add for isolated execution
# agent: general-purpose # only with context: fork — Explore | Plan | general-purpose | <custom-agent>
---

# {Skill Title}

{Brief description of what the skill does.}

## Inherited DNA
{Absolute criteria contextualized for this domain}

## Protocol
{Step-by-step execution protocol}

## Quality Gates
{Domain-specific quality criteria}

## P1 Enforcement
{List of deterministic validations, if any}
context: fork + agent Selection Criteria

These optional frontmatter fields control where and how the skill executes. Default is inline (no field needed).

CriterionInline (default)Fork
User interaction needed (Q&A, HITL)✅❌
Works within ongoing conversation context✅❌
Independent analysis/transformation❌✅
Execution details would pollute main context❌✅
SOT accessDirectRead-only (file output → Orchestrator records in SOT)

Constraints — fork MUST NOT be used when:

  • Skill writes to SOT directly (violates Absolute Criteria 2 single-writer)
  • Skill requires sequential quality gate passage (L0→L1→L1.5→L2) with main context visibility
  • Skill needs Bash but the specified agent lacks Bash tool access
  • Skill is part of the main orchestration flow (router, resume, HITL gates)

agent field specifies which agent type runs the forked context. Only meaningful with context: fork:

  • Explore — read-only codebase search (haiku model)
  • Plan — architecture research, read-only
  • general-purpose — full tool access, multi-step tasks
  • {custom-agent} — any agent defined in .claude/agents/ (inherits that agent's model, tools, behavior)
Show full SKILL.md (205 more words)Show less
Step 4: Generate Reference Files

Create supporting documents in references/:

  • Domain guide: Detailed domain knowledge and best practices
  • Checklist: Verification items for quality assurance
  • Examples: Concrete examples of good/bad outputs (when applicable)
Step 5: Validate Generated Skill

Verify the generated skill:

  • SKILL.md has valid frontmatter (name, description; optional: context, agent)
  • Inherited DNA section present with all applicable genome components
  • Protocol has clear, numbered steps
  • Quality gates defined
  • References directory populated
  • No hardcoded paths (uses relative references)
  • Language: internal instructions in English, user-facing in Korean
  • Fork Safety P1 Validation (if context: fork in frontmatter): Run python3 .claude/hooks/scripts/validate_fork_safety.py --file <generated-SKILL.md> --project-dir <project-root> Must PASS all 5 rules (FS-1~FS-5). FAIL → fix violations before proceeding to Step 6.
Step 6: Register Skill

Inform the user:

  1. Skill location: .claude/skills/{skill-name}/
  2. How to trigger it (matching patterns from description)
  3. Any required setup (dependencies, configuration)

Language Rules

  • SKILL.md internal instructions: English (for AI performance)
  • SKILL.md description (frontmatter): Korean (for user-facing matching)
  • Reference files: English (domain knowledge for AI consumption)
  • Generated output for users: Korean (user-facing reports)

Quality Checklist

  • Generated skill follows AgenticWorkflow conventions
  • DNA inheritance is complete (not just referenced)
  • Steps are concrete and actionable
  • P1 tasks identified and separated from LLM tasks
  • No placeholder content — all sections are substantive

© idoforgod, MIT. 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 3 other files (references) in .claude/skills/skill-creator of idoforgod/Dissertation-Simulator-AgenticWorkflow.

  • SKILL.md
  • references/ccp-contextualization-guide.md
  • references/quality-gates-guide.md
  • references/skill-template-guide.md

Open the folder on GitHubat commit f2205f5

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 skillidoforgod/Dissertation-Simulator-AgenticWorkflow108—~1.6kAutomated 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 yesterday
    Agent WorkflowsAuto-check passed

More from idoforgod/Dissertation-Simulator-AgenticWorkflow

  • Subagent Creator

    idoforgod/Dissertation-Simulator-AgenticWorkflow

    Meta-skill that generates Claude Code agent definition files (.md).

    108 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed
  • Doctoral Writing

    idoforgod/Dissertation-Simulator-AgenticWorkflow

    박사급 학위 논문 글쓰기 스킬. An agent skill from idoforgod/Dissertation-Simulator-AgenticWorkflow.

    108 GitHub stars~2.7k tokensUpdated 4 mo ago
    Auto-check passed
  • Workflow Generator

    idoforgod/Dissertation-Simulator-AgenticWorkflow

    Automated workflow (workflow.md) generator for Claude Code. An agent skill from idoforgod/Dissertation-Simulator-AgenticWorkflow.

    108 GitHub stars~3.6k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Skill Creator

What does Skill Creator do?

Meta-skill that generates new Claude Code skills. An agent skill from idoforgod/Dissertation-Simulator-AgenticWorkflow. Skill Creator is an agent skill from idoforgod/Dissertation-Simulator-AgenticWorkflow. Meta-skill that generates new Claude Code skills.

When should I use Skill Creator?

Skill Creator fits situations like: asked to create a skill; make a new skill; generate skill for X.

How do I install Skill Creator in Claude Code?

Run `npx skills add idoforgod/Dissertation-Simulator-AgenticWorkflow --skill skill-creator -a claude-code`. Or copy the skill folder (.claude/skills/skill-creator in idoforgod/Dissertation-Simulator-AgenticWorkflow) 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 idoforgod/Dissertation-Simulator-AgenticWorkflow --skill skill-creator -a codex`. Or copy the skill folder (.claude/skills/skill-creator in idoforgod/Dissertation-Simulator-AgenticWorkflow) 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 idoforgod/Dissertation-Simulator-AgenticWorkflow --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 the command-line tools its instructions call (python3). 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. 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 1.6k tokens (SKILL.md is roughly 6.2k 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 2.4k 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?

idoforgod (a GitHub user) maintains it in idoforgod/Dissertation-Simulator-AgenticWorkflow, which has 108 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on June 4, 2026.

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