Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jeomon/operator-use/skill-creatornpx skills add Jeomon/Operator-Use --skill skill-creatorgit clone --depth 1 https://github.com/Jeomon/Operator-UseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jeomon/operator-use/skill-creator)<a href="https://agentmods.dev/skills/jeomon/operator-use/skill-creator"><img src="https://agentmods.dev/badge/skills/jeomon/operator-use/skill-creator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00064 | $0.05163 |
| Opus 5 | $0.00032 | $0.02582 |
| Sonnet 5 | $0.00013 | $0.01033 |
| Haiku 4.5 | $0.00006 | $0.00516 |
Grade B, and why
skill-creator scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
**Reviewing results:** If no browser display, skip browser reviewer. Present results directly in conversation. Show prompt and output. If output is a file (docx, xlsx), save it and tell user where to download it. Ask fee How it starts
The opening of the file, as written. The whole thing — 660 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
A skill for creating new skills and iteratively improving them.
Overview
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 quantitative evals
- Use the
eval-viewer/generate_review.pyscript to show results - Rewrite the skill based on feedback from evaluation
- Repeat until 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 help them progress through these stages.
How to Use This Skill
When the User is Starting Out
If they say "I want to make a skill for X":
- Help narrow down what they mean
- Write a draft
- Write test cases
- Figure out how they want to evaluate
- Run all the prompts
- Iterate based on feedback
When the User Already Has a Draft
Go straight to the eval/iterate part of the loop.
Being Flexible
If the user says "I don't need to run a bunch of evaluations, just vibe with me", that's fine too. Adjust your approach.
After the Skill is Done
Optionally run the skill description improver to optimize triggering accuracy.
Communicating with the User
The skill creator is used by people with varying familiarity with technical jargon.
Pay attention to context cues to understand how to phrase your communication:
- "evaluation" and "benchmark" are generally OK
- For "JSON" and "assertion", wait for clear signals the user knows what those are before using them without explanation
- It's OK to briefly explain terms if you're unsure
Creating a Skill
Step 1: Capture Intent
Start by understanding the user's intent. If the conversation already contains a workflow to capture (e.g., "turn this into a skill"), extract answers from the history first.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 660 lines · 64 tokens per session scan B 642d47facad8
skill-creator is a skill published in the GitHub repository Jeomon/Operator-Use (40 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 5,163 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cli-docs-guidelines
Review or write CLI documentation. Enforces progressive disclosure, logical command ordering, and plain-language explanations. Use when asked to "write CLI docs", "document commands", "review CLI reference", or "update command docs".
readme-guidelines
Review or write README content for open-source projects. Enforces progressive disclosure, jargon-free language, and single-concept code examples. Use when asked to "write README", "review README", "update README", or "check docs".
unbrowse
The action engine of the internet. Unbrowse is the open-source action layer for AI agents: it learns a site's internal API routes from real browsing, then replays them as fast, cheap, indexed routes (cache hit under 200ms) instead of re-driving a browser. Capture once, replay everywhere. The default agent flow is ONE…
unbrowse
The action engine of the internet. Unbrowse is the open-source action layer for AI agents: it learns a site's internal API routes from real browsing, then replays them as fast, cheap, indexed routes (cache hit under 200ms) instead of re-driving a browser. Capture once, replay everywhere. The default agent flow is ONE…
ai-deploy
Deploy a generated project (one process or several) to agent-sandboxes with scale-to-zero: idle sandboxes pause and auto-resume (process restarted) on the next HTTP request. Use when asked to deploy, host, or preview generated code through the sandbox platform.
e2b-sandbox
Create, manage, and use E2B sandboxes — run commands, manage files, use git, persist state, and configure networking. Use when building agent workflows that need isolated execution environments.