Skill Model Gap
Find why a skill works worse on one model than another, and fix it without hurting the others. Give it the skill and the models to compare.
Install
/plugin marketplace add nicobailon/skill-dietThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add nicobailon/skill-diet --skill skill-model-gapgit clone --depth 1 https://github.com/nicobailon/skill-diet.git /tmp/skill-diet
mkdir -p ~/.claude/skills
cp -r /tmp/skill-diet/skills/skill-model-gap ~/.claude/skills/skill-model-gapPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Skill model gap A skill tested on one model (the **reference**) often passes fewer tasks on another (the **target**). Find where and why, fix it with text every model reads, and prove the target gains while no model drops. This runs skill-diet's eval: tasks and scoring per [eval.md](../skill-diet/references/eval.md), the adapter per [adapter.md](../skill-diet/references/adapter.md), commands as `node ../skill-diet/scripts/eval.mjs …`. Edits follow skill-diet's [Editing a skill](../skill-diet/SKILL.md#editing-a-skill). ## Set up - **One adapter, one host** for every model, so only the model differs. Pass `--model` to every `run` and `score`. - **Tasks** per eval.md, each labeled with the case it covers. Split them blind and at random: about a third, at least one per case, go to a **held-back** folder whose `adapter` and `sk/` link to the tuning folder's. Held-back tasks get no runs until the end. - **Versions:** `base` (the skill as it is), `none`, and one folder per candidate fix. - **Models:** the reference has the best `base` pass rate (on a tie, the one that reads the skill most); every other model with a gap is a target. Add at least one more model as a harm check. - **Paid quota:** before each step, give the user sessions × cost per run and stay within the budget they set. Two tasks first measure the cost. ## 1. Measure the gap
Details
- Skill name
skill-model-gap- Repository
- nicobailon/skill-diet
- Path
skills/skill-model-gap/SKILL.md- License
- MIT
- Repo updated
- 6 November 2026
FAQ
What does the Skill Model Gap skill do?
Find why a skill works worse on one model than another, and fix it without hurting the others. Give it the skill and the models to compare.
How do I install the Skill Model Gap skill?
Claude Code plugin: /plugin marketplace add nicobailon/skill-diet. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Skill Model Gap popular?
It lives in nicobailon/skill-diet, which has 260 GitHub stars and 10 forks.
Related skills
Skill Diet
260nicobailon/skill-diet
Keep agent skills lean and correct. Use before editing an existing skill, such as adding a lesson; when a code change touches names or behavior a skill describes; and to put a skill on a full diet when it is large, loads detail most tasks never use, or has drifted from the tool it teaches.
Agent Manager Skill
514Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
Geo Optimizer
241liangdabiao/GEO-Content-Optimizer-Skill
GEO (Generative Engine Optimization) 全流程优化工具。帮助品牌内容被 ChatGPT、Perplexity、Gemini 等 AI 搜索引擎引用。 包含 5 大模块:结构化数据生成 (JSON-LD Schema)、内容 AI 可读性检测、内容集群架构规划、AI 可见度监控与季度报告、内容差距分析。 当用户提到 "GEO"、"AI搜索优化"、"AI 引用优化"、"Schema 标记"、"JSON-LD"、"FAQ Schema"、"E-E-A-T"、 "内容被 AI 抓取"、"Pillar Page"、"内容集群"、"AI 可见度"、"Generative Engine Optimization" 时触发。 也适用于用户要求:"帮我生成 Schema"、"检测内容 AI 友好度"、"优化让 AI 引用我的内容"、"测试品牌在 AI 搜索中的曝光"。
Code Review AI AI Review
514Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C
Geo
241liangdabiao/GEO-Content-Optimizer-Skill
完整的 GEO(生成式引擎优化)服务流水线:给一个产品官网 URL 和介绍材料, 做站点诊断与 AI 答案采样、生成带验收标准的执行工单、产出可直接部署的资产 (llms.txt / JSON-LD / 定义块 / FAQ / 内容大纲与初稿)、自动验收工单是否闭环、 并打包成可直接发给客户的交付物。可按周期复跑,做长期 GEO 运营与月报。 国内和海外双市场并行:国内覆盖 智谱GLM/豆包/DeepSeek/Kimi/MiniMax/纳米AI/百度AI, 海外覆盖 Gemini/ChatGPT/Claude/Grok/Perplexity,问题库与指标按市场分开算。 当用户说「做 GEO」「生成式引擎优化」「让 AI 推荐我的产品」「AI 搜索里搜不到我们」 「GEO 方案/诊断/监测/月报/交付」「给客户做 GEO 服务」,或给一个产品网址要做 AI 可见性优化时使用。GEO 指生成式引擎优化,不是地理信息; 不用于传统 SEO 关键词排名、竞价投放或建站。
Pcb
188daishuge/pcb-skill
Design a manufacturable PCB end to end — concept, schematic, layout, routing, verification, and a staged purchase — driven from Claude Code or Codex on the desktop, with EasyEDA Pro over MCP and JLC/LCSC/Taobao in a logged-in browser. Optimises for cost-effectiveness, hand-assembly, and a free prototype board.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.