Skip to content
mcp/skillhub

Agent Skill

Skill Creator skill

skill-creatorCherryHQ/cherry-studioresources/skills/skill-creator/SKILL.md

Create, edit, evaluate, and optimize skills, including benchmarking and description tuning for better triggering.

53kAGPL-3.0

always on

23 tokname + description

once used

7,591 tokSKILL.md body

bundled files

1710 scripts

repo stars

53kGitHub

Install the Skill Creator skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/CherryHQ/cherry-studio --skill skill-creator

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git /tmp/cherry-studio
mkdir -p ~/.claude/skills
cp -R /tmp/cherry-studio/resources/skills/skill-creator ~/.claude/skills/skill-creator

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description23 tok
When the agent uses itThe SKILL.md instructions7,591 tok
Only if opened17 bundled files (187 KB)varies

Until it is used, skill-creator costs about 59× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 40 skills from CherryHQ/cherry-studio would load 1,676 tokens of descriptions. Skills vs MCP study

Checks

  • Ships scripts the agent can run. Read them before installing.
  • The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.
  • The instructions are over 500 lines; the specification suggests moving detail into reference files.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Cherry Studio workflow (READ FIRST — overrides packaging / install steps below)
  • Skill Creator
  • Communicating with the user
  • Creating a skill
  • Capture Intent
  • Interview and Research
  • Write the SKILL.md
  • Skill Writing Guide
  • Writing Style
  • Test Cases
  • Running and evaluating test cases
  • Step 1: Spawn all runs (with-skill AND baseline) in the same turn
  • Step 2: While runs are in progress, draft assertions
  • Step 3: As runs complete, capture timing data
  • Step 4: Grade, aggregate, and launch the viewer
  • What the user sees in the viewer
  • Step 5: Read the feedback
  • Improving the skill
  • How to think about improvements
  • The iteration loop
  • Advanced: Blind comparison
  • Description Optimization
  • Step 1: Generate trigger eval queries
  • Step 2: Review with user

More skills from CherryHQ/cherry-studio

All skills in this repo
  1. agent-notesCherryHQ/cherry-studio

    Use when deciding whether a Cherry Studio change needs an Agent Note, authoring or reviewing a Spec, recording a durable bug-fix decision, moving a note between proposed/implemented/rejected, or checking supersession and stacked Spec approval.

    53k51 tok idle · 865 in use
  2. cherry-assistant-guideCherryHQ/cherry-studio

    从当前安装包查询 Cherry Studio 产品信息并排查运行问题。当用户询问功能、路由、快捷键、Provider、语言、Agent、频道、定时任务、Code CLI、当前版本，或报告运行错误、连接失败、配置异常并需要诊断时触发。

    53k68 tok idle · 795 in use
  3. cherry-browserCherryHQ/cherry-studio

    Control the user's visible Agent browser: navigate, click, type, screenshot, debug. Needs the Browser setting.

    53k26 tok idle · 1,038 in use
  4. cherry-computerCherryHQ/cherry-studio

    Drive native apps via Computer Use: open, inspect, type, click, screenshot. Needs OS permissions; respect user stop.

    53k30 tok idle · 769 in use
  5. cherry-electron-devCherryHQ/cherry-studio

    Develop, fix, profile, and test PRs in a tracked Cherry Studio Electron instance. Use for implementation, UI and interaction work, runtime debugging, DevTools inspection, performance analysis, and interactive PR verification with a test report. Reuse a verified workspace instance and manage its lifetime according to the selected workflow.

    53k68 tok idle · 589 in use
  6. cherry-regression-testCherryHQ/cherry-studio

    Run Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for full regression, release acceptance, development-branch system validation, or a named cherry-regression-test task on GitHub-hosted macOS and Windows runners.

    53k58 tok idle · 992 in use
  7. cherry-skill-marketplaceCherryHQ/cherry-studio

    用户要求搜索、安装、查看或卸载 Skill，或内置能力不足时使用：先 search_skills，再 install_skill；无结果用 skill-creator 创建。

    53k43 tok idle · 1,008 in use
  8. cherry-studio-feedbackCherryHQ/cherry-studio

    Use when Cherry Studio 用户希望报告、提交或整理 BUG、UI/UX 问题或功能建议，但未明确要求创建 GitHub Issue。

    53k37 tok idle · 478 in use