/skill-creator

name: skill-creator
description: Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

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.

---

DeerFlow Environment (⚠️ READ THIS FIRST)

If you are running inside a **DeerFlow** sandboxed agent environment (you have access to the `skill_manage` tool), you MUST follow these rules for all skill file operations. These override the generic file-writing and packaging instructions below.

Why this matters

In DeerFlow, the sandbox filesystem is isolated. Files written with `write_file` land in `/mnt/user-data/outputs/`, which is a **per-thread output directory** — new chats cannot see files there. Skills must be persisted through the dedicated `skill_manage` tool so they are stored in the per-user skill directory and immediately visible to all future chats.

Use `skill_manage` for all skill file operations

| Operation | skill_manage action | Example | |-----------|---------------------|---------| | Create a new skill | `action="create"` | `skill_manage(action="create", name="my-skill", content="---\nname: my-skill\n---\n...")` | | Replace entire SKILL.md | `action="edit"` | `skill_manage(action="edit", name="my-skill", content="updated SKILL.md")` | | Partial edit (find & replace) | `action="patch"` | `skill_manage(action="patch", name="my-skill", find="old text", replace="new text")` | | Delete a skill | `action="delete"` | `skill_manage(action="delete", name="my-skill")` | | Add a supporting file | `action="write_file"` | `skill_manage(action="write_file", name="my-skill", path="scripts/helper.py", content="...")` | | Remove a supporting file | `action="remove_file"` | `skill_manage(action="remove_file", name="my-skill", path="scripts/helper.py")` |

Key rules

1. **NEVER use sandbox `write_file` to create or modify skill files** (SKILL.md, scripts/, references/, assets/). These would land in `/mnt/user-data/outputs/` and be invisible to future chats. Always use `skill_manage` instead.

2. **Skip the `package_skill.py` step**. In DeerFlow, `skill_manage` already persists the skill to the correct per-user directory. No `.skill` packaging or manual install is needed. The skill is immediately available in all new chats.

3. **Skip the `present_files` step for skills**. Skills are NOT deliverables — they are persisted via `skill_manage` and auto-loaded by the skill system. Only use `present_files` for non-skill outputs (eval reports, benchmarks, etc.).

4. **Eval workspace files are OK in sandbox**. Test prompts, benchmark data, eval viewer HTML, grading results, etc. are NOT skill files — you can write these to `/mnt/user-data/outputs/` or `/mnt/user-data/workspace/` using sandbox `write_file` as usual.

5. **To read an existing skill's SKILL.md**, use `read_file("/mnt/skills/custom/<name>/SKILL.md")` in the sandbox (it maps to the per-user skill directory).

6. **Updating an existing skill**: use `skill_manage(action="edit")` or `skill_manage(action="patch")`. Do NOT copy to `/tmp/` first — `skill_manage` handles the per-user storage directly.

Workflow in DeerFlow

The core loop is the same, but the persistence mechanism changes:

1. Capture intent → interview → draft SKILL.md content 2. **Call `skill_manage(action="create", name=<name>, content=<SKILL.md>)`** to persist the skill 3. Run test cases (eval workspace files use sandbox `write_file`) 4. Evaluate results, gather feedback 5. **Call `skill_manage(action="edit")` or `skill_manage(action="patch")`** to improve the skill 6. Repeat until satisfied 7. **Done — no packaging needed.** The skill is already persisted and visible to all future chats.

---

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 ho