shorin-kiwata/miyu-agent/skill-creator

Claude Code and agent skill by shorin-kiwata/miyu-agent

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Create or safely update Miyu skills. Use when the user asks to create, author, improve or modify a reusable skill, a SKILL.md workflow or skill resources — 写技能、改技能、做一个技能。

Install

npx vskill@latest install shorin-kiwata/miyu-agent/skill-creator

SKILL.md

Skill Creator

Create focused, reusable Agent Skills that follow the Agent Skills specification.

Calling manage_skill

manage_skill is not on the always-loaded tool list: authoring a skill is a once-in-a-while action, so it lives behind this skill. Call it through the tool bridge with run_command:

bash
miyu tool-call manage_skill --stdin <<'JSON'
{"action": "create", "name": "my-skill", "description": "what it does and when to use it"}
JSON

miyu tool-call manage_skill --describe prints the full parameter contract. Everything below that says "call manage_skill" means this.

Workflow

  1. Ask what the skill should do, when it should trigger, and what it must not do when any of those points are unclear.
  2. Prefer instruction-only skills. Add scripts only when deterministic code or an external program is genuinely required.
  3. Load the development and skill authoring tools before editing.
  4. Use manage_skill with action=create for a new skill or action=update for an existing one. Use the returned absolute skill_file and skill_dir; never guess a Miyu home path.
  5. Use edit to change SKILL.md and add optional scripts/, references/, or assets/ files below the returned draft directory.
  6. Keep SKILL.md concise. Put detailed reference material in supporting files and reference those files with paths relative to the skill root.
  7. Call manage_skill with action=publish and the returned draft ID. Publishing performs structural validation and atomically installs the package.
  8. Load the published skill with load_skill to verify the final instructions and resource manifest.

Frontmatter

Every skill requires name and description. The name must match its directory and use lowercase ASCII letters, digits, and single hyphens. The description must explain both what the skill does and when it should be used.

Optional standard fields are license, compatibility, metadata, and allowed-tools. allowed-tools is compatibility metadata only and never grants Miyu permissions.

Editing Rules

  • Do not write directly into the live skills directory.
  • Do not overwrite an existing skill through action=create; use action=update.
  • Skill scripts remain resources. Do not claim that publishing automatically registers them as tools.
  • Do not add files or abstractions that the workflow does not need.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
112
Repository forks
28
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/shorin-kiwata/miyu-agent/skill-creator/badge)](https://verified-skill.com/skills/shorin-kiwata/miyu-agent/skill-creator)

Something wrong with this skill or its page? Tell us.