Agent Skill (SKILL.md) generator
Turn a workflow description into a SKILL.md in the Agent Skills format — frontmatter, trigger description, procedure, rules and references.
Your key stays in your browser.It goes straight to the provider, never to our servers, and we neither log nor keep it. Use a dedicated key with a spending cap, and delete it in the provider's dashboard when you are done.
Input
Result
The result will appear here.Agent Skills are the way to teach an AI agent a repeatable job: a folder with a SKILL.md whose frontmatter tells the agent when to load it and whose body tells it exactly what to do, plus optional reference files and scripts. Claude Code, Claude.ai, Codex, Cursor and OpenHands all load the same format from anthropics/skills and the agentskills.io specification. The hard part is not the YAML — it is writing a description that triggers at the right moment and a procedure precise enough that the agent does not improvise. Describe the workflow and this generator writes the skill the way the reference skills are written: imperative, concrete, with the checks to run and the mistakes to avoid.
How it works
- The frontmatter description carries the trigger phrases a user would say, because it is the only text the agent reads before deciding to load the skill.
- The body is a numbered procedure with the commands, the rules that each prevent a specific mistake, and the expected deliverable — not general advice the model already knows.
- Choose the full layout to also get the references/ and scripts/ files the body points to, each under a heading with its path, ready to save as a folder.
Where your data goes
With your own key, what you type and the key go from your browser straight to the provider you choose; neither passes through Hysen Labs. In hosted mode, your text goes through our server to our provider (DeepSeek) and is billed in credits; we keep the token counts and cost of each run for billing, never the text itself or the answer. How the provider handles the text is governed by its own privacy policy.
This tool handles keys and credentials, so nothing about a run is saved, not even to your own history.
About your API key
We do not collect, store or leak your key: it lives only in this page's memory (unless you tick “remember in this tab”) and is gone when you close it. Still, treat any key you have pasted into a web page with care — create a dedicated key with a spending cap for use here, and delete or rotate it in your provider's dashboard when you are done.
What it costs
This tool is free, with no sign-in and no points.
Common questions
- What goes in SKILL.md and what goes in references/?
- SKILL.md holds what the agent needs on every run — purpose, steps, rules, output — and should stay under a few hundred lines. Long material consulted occasionally (a style guide, an API reference, a checklist of edge cases) belongs in references/ with a sentence in the body saying when to read it, so it costs context only when needed.
- Where do I install the result?
- Claude Code reads skills from .claude/skills/<name>/SKILL.md in a project or ~/.claude/skills for all projects; Codex reads .codex/skills; Claude.ai takes the folder as an upload under Settings → Capabilities. The folder name must equal the name field in the frontmatter.
- Can a skill include secrets or credentials?
- It should not — skills are plain text committed to repositories and shared. The generator names environment variables instead and tells the agent to read them, which is also what the official skills do.
The open-source behind it
This tool's prompt is adapted from anthropics/skills (Apache-2.0) and runs on the model you choose. To use the same capability from the command line or inside your own program, start with that project.
anthropics/skillsAlso known as
- skill.md generator
- agent skills format
- claude code skill generator
- create custom skill claude
- agentskills.io spec
- codex skill file