skill-creator · dkyazzentwatwa — Claude Code skill: building and validating skills
skill-creator — a skill for creating skills: generates folder structure, SKILL.md, agent metadata, and validates everything before packaging.
Apache-2.0 167 installs ★ 136 updated 2026-04-08
npx skills add dkyazzentwatwa/chatgpt-skills --skill skill-creator -a claude-codeWhat skill-creator does
It ships with four Python scripts: init_skill.py scaffolds a new skill with references/ and scripts/ folders, generate_openai_yaml.py builds agents/openai.yaml from explicit interface parameters, quick_validate.py checks frontmatter, name matching, and script dependencies, package_skill.py validates and zips the skill.
The author recommends keeping SKILL.md short and moving detailed content into references/. Frontmatter should contain only name and description; description acts as the trigger — it must state what the skill does and when to use it. The folder name must match the name field exactly.
The workflow is built around skill creation: first define the user requests that should activate the skill, write a minimal instruction, add only the resources that make execution more reliable, generate metadata, and validate before publishing.
What it helps with
- scaffold a new skill with folders and boilerplate
- generate
agents/openai.yamlfrom interface parameters - validate frontmatter, names and dependencies before publishing
- package a skill into a zip after validation
- move detail from
SKILL.mdintoreferences/
Example prompts for the agent
- Create a new skill called
pdf-builderwith script and reference folders - Generate
agents/openai.yamlfor theapi-testerskill with short description “Tests REST APIs” - Validate the
data-parserskill and package it into./dist
How to install skill-creator
1Skills CLI (Vercel)
npx skills add dkyazzentwatwa/chatgpt-skills --skill skill-creator -a claude-code2Manually: put the files in place
~/.claude/skills/skill-creator/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/skill-creator/
1Skills CLI (Vercel)
npx skills add dkyazzentwatwa/chatgpt-skills --skill skill-creator -a codex2Manually: put the files in place
.agents/skills/skill-creator/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add dkyazzentwatwa/chatgpt-skills --skill skill-creator -a cursor2Manually: put the files in place
.cursor/skills/skill-creator/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install dkyazzentwatwa/chatgpt-skills skill-creator2Manually: put the files in place
.github/skills/skill-creator/SKILL.md1Skills CLI (Vercel)
npx skills add dkyazzentwatwa/chatgpt-skills --skill skill-creator -a gemini-cli2Platform CLI
gemini skills install https://github.com/dkyazzentwatwa/chatgpt-skills --path skill-creatorManually: put the files in place
.devin/skills/skill-creator/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add dkyazzentwatwa/chatgpt-skills --skill skill-creator -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about skill-creator
How to install skill-creator in Claude Code?
Run npx skills add dkyazzentwatwa/chatgpt-skills --skill skill-creator -a claude-code; the skill lands in ~/.claude/skills/skill-creator/SKILL.md.
What does skill-creator do?
It scaffolds a new skill structure, generates agent metadata, validates frontmatter and dependencies, and packages the skill into a zip.
Which scripts are included in skill-creator?
init_skill.py creates folder structure, generate_openai_yaml.py builds agent metadata, quick_validate.py checks compliance, package_skill.py validates and packages.
Source text
SKILL.md · Apache-2.0
--- name: skill-creator description: Create or update agent skills with concise SKILL.md instructions, bundled resources, agent metadata, validation, and packaging. Use when building or refactoring skills. --- # Skill Creator Design or refactor skills so they are small, triggerable, and mechanically valid. ## Workflow 1. Define the exact user requests that should trigger the skill. 2. Keep `SKILL.md` short and put deep detail in `references/`. 3. Add only the scripts, assets, or references that make execution materially more reliable. 4. Generate `agents/openai.yaml` and validate before packaging. ## Scripts - `scripts/init_skill.py` initializes a new skill with optional resource folders and `agents/openai.yaml`. - `scripts/generate_openai_yaml.py` writes `agents/openai.yaml` from explicit interface values. - `scripts/quick_validate.py` enforces strict frontmatter, directory naming, agent metadata, and script dependency rules. - `scripts/package_skill.py` validates first, then zips the skill for distribution. ## Rules - Keep frontmatter to `name` and `description` only. - Make `description` do the trigger work: what the skill does and when to use it. - Match the folder name exactly to `name`. - Prefer one focused workflow over a kitchen-sink skill. - Remove placeholder files and generic boilerplate before publishing. ## Typical Commands ```bash python3 skill-creator/scripts/init_skill.py my-skill --path . python3 skill-creator/scripts/generate_openai_yaml.py my-skill \ --interface display_name="My Skill" \ --interface short_description="One-line summary" \ --interface default_prompt="Help me use this skill." python3 skill-creator/scripts/quick_validate.py my-skill python3 skill-creator/scripts/package_skill.py my-skill ./dist ```
© dkyazzentwatwa · Apache-2.0 · dkyazzentwatwa/chatgpt-skills
Similar skills
All skills for Agent setup: memory, context, orchestration →skill-creator by other authors comes first.