skill-creator
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.pyscript 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.
More from rexleimo/rex-cli
contextdb-autopilot
Use when running tasks in Codex CLI, Claude Code, Gemini CLI, or opencode and you need automatic context persistence (init/session/event/checkpoint/context-pack) plus interactive auto-routing without manual contextdb commands.
3seed2-manga-drama
当用户要把单图或创意脚本做成AI漫剧短视频时使用。提供Seed2.0风格的四阶段流程:分镜脚本、主角设定、分镜生成、视频验收,并输出可直接投喂生成模型的结构化提示词。
3debug
Evidence-first runtime debugging for application bugs, regressions, flaky behavior, and unclear failures. Use when an agent is asked to debug an issue and should avoid speculative fixes by forming hypotheses, attaching to or starting a logging session, instrumenting code, collecting runtime logs, analyzing the recorded log file, applying only proven fixes, and verifying the result before removing instrumentation, especially for browser or frontend issues where logs should go directly to the active collector endpoint instead of app-local proxy APIs.
2find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
2xhs-ops-methods
当用户要学习或执行小红书运营方法时使用。提供可复用的“定方向-定人设-写排发互-复盘增长”流程,支持多账号协作,并强调人工审核与合规发布。
2frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
2