Create new Agent Skills or improve existing ones in an agent-agnostic way.

MITAuto-check passedAgent Workflows

Install Skill Creator

skills CLI
$ npx skills add micronaut-projects/micronaut-openapi --skill skill-creator -a claude-code

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

GitHub CLI
$ gh skill install micronaut-projects/micronaut-openapi 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/micronaut-projects/micronaut-openapi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/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
114
Token cost
~1.2k tokens
SKILL.md length
567 words
Files
4 (incl. references)
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Create new Agent Skills or improve existing ones in an agent-agnostic way.

  • Works in 7 steps: Identify intent and scope → Gather concrete examples → Design the skill anatomy → …
  • Users ask to build
  • SKILL.md covers Objectives, Workflow, Agent-Agnostic Rules and Safety and integrity, plus 2 more sections
  • Calls npx

What it does

Skill Creator is an agent skill from micronaut-projects/micronaut-openapi. Create new Agent Skills or improve existing ones in an agent-agnostic way. Use when users ask to build, refactor, validate, or package skills compatible with the Agent Skills specification and the skills CLI ecosystem.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/research-synthesis.md`, `references/spec-checklist.md` and `references/templates.md`). Compatibility notes: Compatible with Agent Skills spec and skill directories such as .agents/skills or equivalent agent-specific skill paths.

It sits in Agent Workflows, covering Skill authoring and OpenAPI specifications. It works with OpenAPI. The repository describes itself as: Generates OpenAPI / Swagger Documentation for Micronaut projects. The licence is MIT.

When your agent uses it

  • Users ask to build
  • Package skills compatible with the Agent Skills specification and the skills CLI ecosystem

Example prompts

  • “/skill-creator”

Requirements

  • Node.js
  • Compatibility (from SKILL.md): Compatible with Agent Skills spec and skill directories such as .agents/skills or equivalent agent-specific skill paths.

Workflow steps

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

  1. Identify intent and scope
  2. Gather concrete examples
  3. Design the skill anatomy
  4. Author SKILL.md frontmatter
  5. Author SKILL.md body
  6. Apply progressive disclosure
  7. Validate and harden

What it can do on your machine

Read from SKILL.md and the folder at commit 4877fd7. 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:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    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.

  • Compatibility

    Compatible with Agent Skills spec and skill directories such as .agents/skills or equivalent agent-specific skill paths.

    From compatibility in the SKILL.md frontmatter.

Context cost

Skill Creator loads about 1.2k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 567 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

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 micronaut-projects/micronaut-openapi at commit 4877fd7, republished under its MIT licence (© micronaut-projects). 567 words, ~1,214 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
Create new Agent Skills or improve existing ones in an agent-agnostic way. Use when users ask to build, refactor, validate, or package skills compatible with the Agent Skills specification and the skills CLI ecosystem.
compatibility
Compatible with Agent Skills spec and skill directories such as .agents/skills or equivalent agent-specific skill paths.
license
MIT
metadata.author
local
metadata.version
1.0.0

Skill Creator

Create and refine skills that work across agents implementing the Agent Skills specification.

Use imperative instructions. Keep the process deterministic where possible. Keep the skill output portable.

Objectives

  1. Produce a valid skill with a correct SKILL.md frontmatter and useful body instructions.
  2. Keep the skill agent-agnostic unless the user explicitly requests agent-specific behavior.
  3. Apply progressive disclosure so only essential content stays in SKILL.md.
  4. Validate structure and naming before declaring completion.

Workflow

1) Identify intent and scope

Determine whether the user wants one of these outcomes:

  • New skill from scratch
  • Update an existing skill
  • Improve trigger quality (description tuning)
  • Add reusable resources (scripts/, references/, assets/)

Extract known constraints from conversation context first. Only ask for missing details that materially change implementation.

2) Gather concrete examples

Collect at least 2 realistic user prompts that should trigger the target skill. Also collect at least 2 near-miss prompts that should not trigger it.

Use these examples to decide:

  • Required workflow steps
  • Output format expectations
  • Edge cases to handle
  • Whether deterministic scripts are needed
3) Design the skill anatomy

Create a minimal structure first:

text
<skill-name>/
└── SKILL.md

Add optional directories only when justified:

  • scripts/ for deterministic or repeated operations
  • references/ for detailed docs, schemas, and long procedures
  • assets/ for templates and static resources used in outputs
4) Author SKILL.md frontmatter

Set required fields:

  • name: lowercase, digits, hyphens; matches folder name
  • description: what the skill does and when to use it

Common optional fields include license, compatibility, metadata, and allowed-tools. Additional frontmatter keys (for example, MCP or tooling configuration) are allowed when supported by the Agent Skills spec/validator, and may be nested under metadata when appropriate.

Description guidance:

  • Include both capability and trigger cues
  • Avoid vague phrases like "helps with X"
  • Prefer concrete contexts and user-language synonyms
5) Author SKILL.md body

Structure the body for execution, not marketing:

  1. Goal and success criteria
  2. Step-by-step operating procedure
  3. Input/output expectations
  4. Error handling and edge cases
  5. Examples
  6. Validation checklist

Write in imperative style. Explain why non-obvious constraints matter.

Show full SKILL.md (231 more words)Show less
6) Apply progressive disclosure

Keep SKILL.md concise. Move large or specialized content into references/ and link to it from SKILL.md.

If the skill spans multiple variants, separate variant details into dedicated reference files and keep variant-selection logic in SKILL.md.

7) Validate and harden

Run a final compatibility pass:

  • Frontmatter parses as valid YAML
  • name complies with spec constraints and folder match
  • description is explicit about trigger contexts
  • Relative file references resolve
  • Optional scripts are executable and documented
  • Language is agent-neutral and avoids vendor lock-in

If skills-ref is available, run:

bash
skills-ref validate ./<skill-name>

If the skills CLI is available, verify discovery from the repo root:

bash
npx skills list

Agent-Agnostic Rules

  • Do not require a specific model vendor or proprietary UI affordance.
  • Do not rely on agent-only file paths when portable paths exist.
  • Do not reference unavailable tools as mandatory.
  • Prefer open, portable commands and plain Markdown guidance.

Safety and integrity

  • Refuse to create skills intended for malware, exploitation, data exfiltration, or unauthorized access.
  • Keep behavior aligned with user intent; avoid hidden actions.

Completion criteria

A skill-creation task is complete only when all are true:

  1. Skill folder exists in the requested location.
  2. SKILL.md is valid and complete.
  3. Optional resources are present only if needed.
  4. Validation checks pass or limitations are explicitly reported.

References

  • See references/spec-checklist.md for implementation rules distilled from the spec.
  • See references/templates.md for copy-ready scaffolds.
  • See references/research-synthesis.md for design rationale from cross-source research.

© micronaut-projects, 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 .agents/skills/skill-creator of micronaut-projects/micronaut-openapi.

  • SKILL.md
  • references/research-synthesis.md
  • references/spec-checklist.md
  • references/templates.md

Open the folder on GitHubat commit 4877fd7

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in micronaut-projects/micronaut-openapi, 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 skillmicronaut-projects/micronaut-openapi114—~1.2kAutomated safety check: PassMIT
Api2clialexknowshtml/api2cli455—~2.9kAutomated safety check: PassMIT
Tasksgenkovich/sdd171—~4.8kAutomated safety check: PassMIT
MCP Server Builderalirezarezvani/claude-skills28k—~985Automated safety check: PassMIT
CLI MCP DocsChatbotXIO/ChatbotX879—~1.3kAutomated safety check: PassCustom licence
MCP Server Builderborghei/Claude-Skills881—~1.9kAutomated safety check: PassMIT

Similar skills

  • Api2cli

    alexknowshtml/api2cli

    Generate a working CLI from any API, then wrap it in a Claude Code skill.

    455 GitHub stars~2.9k tokensUpdated 7 mo ago
    Backend & APIsAuto-check passed
  • Tasks

    genkovich/sdd

    A skill your agent uses to break a designed feature into atomic, ≤1-day tasks with a dependency graph, a per-task Definition of Done, and a machine-readable tasks.json that the implement engine…

    171 GitHub stars~4.8k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    alirezarezvani/claude-skills

    Design and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers.

    28k GitHub stars~985 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • CLI MCP Docs

    ChatbotXIO/ChatbotX

    Use after adding, renaming, or removing a public oRPC procedure, or after changing an operation's MCP visibility.

    879 GitHub stars~1.3k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    borghei/Claude-Skills

    Build MCP (Model Context Protocol) servers with tool definitions, resource providers, prompt templates, and transports.

    881 GitHub stars~1.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Kingdee MCP Dev

    WaHaiLong/KingdeeMCP

    Knowledge base for the Kingdee MCP Dev Squad. An agent skill from WaHaiLong/KingdeeMCP.

    103 GitHub stars~853 tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

More from micronaut-projects/micronaut-openapi

  • Agent Md Refactor

    micronaut-projects/micronaut-openapi

    Refactor oversized agent instruction files into a progressive-disclosure structure.

    114 GitHub stars~766 tokensUpdated today
    Auto-check passed
  • Docs

    micronaut-projects/micronaut-openapi

    Write and maintain Micronaut Framework module guides for micronaut-projects repositories.

    114 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Gradle

    micronaut-projects/micronaut-openapi

    Execute Gradle maintainer operations for Micronaut repositories using micronaut-build internals and modern Gradle best practices.

    114 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Guides

    micronaut-projects/micronaut-openapi

    Create or update standalone Micronaut Guides in micronaut-projects/micronaut-guides, including topic discovery, guide authoring, validation, PDF export, and pull request handoff.

    114 GitHub stars~1.9k tokensUpdated today
    Auto-check: notes
  • Coding

    micronaut-projects/micronaut-openapi

    Implement and review Java code changes for Micronaut framework repositories using maintainer standards, including JSpecify null-safety conventions.

    114 GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Micronaut Sourcegen

    micronaut-projects/micronaut-openapi

    Add, integrate, or review Micronaut Sourcegen usage in modules that generate Java source, Kotlin source, Groovy-compatible source, or bytecode from ObjectDef, TypeDef, MethodDef, ExpressionDef…

    114 GitHub stars~3.3k tokensUpdated today
    Auto-check passed

Works with

Questions about Skill Creator

What does Skill Creator do?

Create new Agent Skills or improve existing ones in an agent-agnostic way. Skill Creator is an agent skill from micronaut-projects/micronaut-openapi. Create new Agent Skills or improve existing ones in an agent-agnostic way.

When should I use Skill Creator?

Skill Creator fits situations like: users ask to build; package skills compatible with the Agent Skills specification and the skills CLI ecosystem.

How do I install Skill Creator in Claude Code?

Run `npx skills add micronaut-projects/micronaut-openapi --skill skill-creator -a claude-code`. Or copy the skill folder (.agents/skills/skill-creator in micronaut-projects/micronaut-openapi) 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 micronaut-projects/micronaut-openapi --skill skill-creator -a codex`. Or copy the skill folder (.agents/skills/skill-creator in micronaut-projects/micronaut-openapi) 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 micronaut-projects/micronaut-openapi --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 (npx). Our summary lists: Node.js. Compatibility (from SKILL.md): Compatible with Agent Skills spec and skill directories such as .agents/skills or equivalent agent-specific skill paths..

Does Skill Creator access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. 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 (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skill Creator use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 1.2k 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: Api2cli (alexknowshtml/api2cli, 455 stars), Tasks (genkovich/sdd, 171 stars), MCP Server Builder (alirezarezvani/claude-skills, 28k stars) and CLI MCP Docs (ChatbotXIO/ChatbotX, 879 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Creator?

micronaut-projects (a GitHub organization) maintains it in micronaut-projects/micronaut-openapi, which has 114 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 8, 2026.

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