/skill-creator

name: skill-creator
description: 'Create, edit, evaluate, and optimize skills, including benchmarking and description tuning for better triggering.'
version: 1.0.0

Cherry Studio workflow (READ FIRST — overrides packaging / install steps below)

You are running inside Cherry Studio. Skills live in a managed registry that Cherry keeps in sync with the filesystem automatically — there is **no** install or register tool to call, and you should **ignore** any `package_skill.py` / `.skill` packaging steps mentioned later in this file (they apply to Claude Code / Claude.ai, not here).

**To create a new skill, write it straight into Cherry's managed skills directory:**

1. Resolve the directory once by running `echo "$CHERRY_STUDIO_SKILLS_DIR"` in Bash. That folder is Cherry's managed skill library. 2. Create `$CHERRY_STUDIO_SKILLS_DIR/<skill-folder-name>/` and write `SKILL.md` plus any supporting files (`scripts/`, `references/`, `assets/`) into it with your normal file tools. 3. That's it. Cherry's skill sync detects the new directory, registers it in the catalog, and lists it in the app — no register step. You can re-edit the files in place at any time and the changes are picked up on the next sync.

Use a lowercase, hyphenated `<skill-folder-name>` (e.g. `my-cool-skill`). The `name:` field inside your `SKILL.md` frontmatter must match the folder name and use only lowercase letters, numbers, and hyphens (e.g. `name: my-cool-skill` with folder `my-cool-skill`), per the Agent Skills spec — it is not a free-form display name.

Eval / test workspaces (`<skill-name>-workspace/`, `iteration-*/`, etc.) from the evaluation loop described below must be created **outside** that skills directory — e.g. as a sibling under the user's workspace — so they don't get bundled into the skill. The evaluation loop itself still applies; only the packaging and install mechanics change.

---

Skill Creator

A skill for creating new skills and iteratively improving them.

At a high level, the process of creating a skill goes like this:

• Decide what you want the skill to do and roughly how it should do it
• Write a draft of the skill
• Create a few test prompts and run claude-with-access-to-the-skill on them
• Help the user evaluate the results both qualitatively and quantitatively
• While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
• Use the `eval-viewer/generate_review.py` script to show the user the results for them to look at, and also let them look at the quantitative metrics
• Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
• Repeat until you're satisfied
• Expand the test set and try again at larger scale

Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.

On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.

Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead.

Then after the skill is done (but again, the order is flexible), you can also run the skill description improver, which we have a whole separate script for, to optimize the triggering of the skill.

Cool? Cool.

Communicating with the user

The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. If you haven't heard (and how could you, it's only very recently that it started), there's a trend now where the power of Claude is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.

So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea:

• "evaluation" and "benchmark" are borderline, but OK
• for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them

It's OK to briefly explain terms if you're in doubt, and feel free to clarify terms with a short definition if you're unsure if the user will get it.

---

Creating a skill

Capture Intent

Start by understanding the user's intent. The current conversation might already contain a workflow the user wants to capture (e.g., they say "turn this into a skill"). If so, extract answers from the conversation history first — the tools used, the sequence of steps, corrections the user made, input/output formats observed. The user may need to fill the gaps, and should confirm before proceeding to the next step.

1. What should this skill enable Claude to do? 2. When should this skill trigger? (what user phrases/contexts) 3. What's the expected output format? 4. Should we set up test cases to verify the skill works? Skills with objectively verifiable outputs (file transforms, data extraction, code generation, fixed workflow steps) benefit from test cases. Skills with subjective outputs (writing style, art) often don't need them. Suggest the appropriate default based on the skill type, but let the user decide.

Interview and Research

Proactively ask questions about edge cases, input/output formats, example files, success criteria, and dependencies. Wait to write test prompts until you'