Skills for Real Engineers. Straight from my .agents directory.
skill-creator
Agent skill fromMemento-Teams/Memento-Skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update 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.
How to install skill-creator
npx skills add Memento-Teams/Memento-Skills# or add only this skill to Claude Code: copy the folder
builtin/skills/skill-creator/
# into
~/.claude/skills/skill-creator/ (all projects)
.claude/skills/skill-creator/ (one project)
1<!-- SPDX-License-Identifier: Apache-2.0 -->2<!-- Modified by Memento-Skills contributors, 2026; see THIRD_PARTY_NOTICES.md. -->34# Skill Creator56A skill for creating new skills and iteratively improving them.78At a high level, the process of creating a skill goes like this:910- Decide what you want the skill to do and roughly how it should do it11- Write a draft of the skill12- Create a few test prompts and run claude-with-access-to-the-skill on them13- Help the user evaluate the results both qualitatively and quantitatively14 - 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)15 - 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 metrics16- 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)17- Repeat until you're satisfied18- Expand the test set and try again at larger scale19…
Excerpt shown under the repository's Apache-2.0 license.
More skills in Memento-Skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
