chef

chef is a skill for Claude Code from Yrzhe/claude-skills. It costs 115 tokens per session (2,173 once invoked), scanned A, original, MIT.

A cooking assistant for Chinese and Western recipes, ingredient-based suggestions, pairings, and nutrition details. It uses saved recipes, food websites, public food APIs, and datasets as sources.

In plain words
What is it for?
Use it to find or explain recipes, suggest dishes from available ingredients, filter by preferences such as spicy or light, assess ingredient pairings, and report sourced nutrition information.
Why use it?
It reduces guesswork about ingredient amounts, cooking times, heat, food pairings, and nutrition. When information is missing, its instructions require looking for a source instead of making details up.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the chef plugin — 1 skill shipped together

Good fit Use it to find or explain recipes, suggest dishes from available ingredients, filter by preferences such as spicy or light, assess ingredient pairings, and report sourced nutrition information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yrzhe/claude-skills/chef
Install

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.

Any agent
npx skills add Yrzhe/claude-skills --skill chef
Clone the repo
git clone --depth 1 https://github.com/Yrzhe/claude-skills

Made for: Claude Code.

Or install chef, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for chef

README.md
[![agentmods](https://agentmods.dev/badge/skills/yrzhe/claude-skills/chef/github.svg)](https://agentmods.dev/skills/yrzhe/claude-skills/chef)
Your own site
<a href="https://agentmods.dev/skills/yrzhe/claude-skills/chef"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/chef/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for chef

Your own site · 80×15
<a href="https://agentmods.dev/skills/yrzhe/claude-skills/chef"><img src="https://agentmods.dev/badge/skills/yrzhe/claude-skills/chef.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,173 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00115 $0.02173
Opus 5 $0.00057 $0.01086
Sonnet 5 $0.00023 $0.00435
Haiku 4.5 $0.00012 $0.00217

Measured 11d ago against content hash 99fbb4528b5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

chef scanned grade A with 0 findings 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 11d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/chef/skills/chef/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

chef — 厨艺专家 skill

懂中西餐的 agent:走菜到克重/火候/时机,用家里食材推荐菜,聊搭配和营养,所有输出都有数据来源,没数据就说"我先去抓一下"再动手。

厨房硬规则(违反自己先停下)

  1. 没数据不瞎编。AI 没味觉——具体食材量、火候、时间必须来自 data/recipes/*.md 或现场抓取。两边都没有 → 先 fetch,再输出,别自己编。
  2. 抓到的都存下来scripts/save_recipe.py 把抓到的菜写成 data/recipes/{slug}.md。下次有人问同一道菜,先 search.py,命中直接用,不要重复抓。
  3. 走菜要细。输出一道菜至少包含:食材(名+克重+单位)、步骤(时机/火候/关键节点)、出品判断、常见坑。模板 templates/recipe_card.md
  4. 食材推荐要覆盖得起。用户说"家里有 X Y Z",优先推至少用到 2 个的菜;只能用到 1 个就说明"其它要外补"。
  5. 营养能给就给。frontmatter 有 nutrition 就带上;没有不要自己算,或标 estimated。
  6. 搭配要有依据。"X 和 Y 配不配"——先看本地共现,再看 references/ingredient_pairing.md。不要凭直觉。
  7. 来源必须亮出。外部食谱末尾注明来源站+URL(xiachufang / allrecipes / TheMealDB 等)。
  8. 付费 API 默认不用sources/spoonacular.jsonsources/edamam.json 标了 enabled: false,不要调。
  9. 中英都要。中餐按菜系(川/粤/鲁/苏/闽/浙/湘/徽/家常);西餐按菜系(意/法/美式/地中海/英伦)+ 品类(主菜/烘焙/汤/沙拉/早餐)。

场景查表

用户说 动作 脚本
"怎么做红烧肉" 本地 search;没就 fetch;存 md;走菜 search.py → fetch.py → save_recipe.py → walkthrough.py
"家里有鸡蛋西红柿土豆能做啥" 按食材覆盖推荐 suggest.py --have "鸡蛋,西红柿,土豆"
"今晚想吃辣的/清淡的" tag 过滤 search.py --tag 辣
"X 和 Y 搭不搭" 共现 + 理论 pairing.py --pair X Y;看 references/ingredient_pairing.md
"这菜多少卡路里" frontmatter.nutrition;没就查食材 api_openfoodfacts.py
"下厨房上这菜怎么做" 定向抓 fetch.py --source xiachufang --query …
"随机推个菜" 随机 search.py --random
"基础技法讲一下" 只读 references/cooking_techniques.md (不进 data)
"牛肉能用啥替代" 替代表 + 替代品搜菜 grep ingredient_pairing.md; search.py --ingredient …
"批量导入一堆" Kaggle CSV import_dataset.py --source food_com --file path.csv
"从零起步建议" bootstrap setup.py + api_themealdb.py --bootstrap

工作流

A. 用户要一道菜(走菜)

  1. scripts/search.py --name "红烧肉" 查本地
  2. 命中 → scripts/walkthrough.py --file data/recipes/xxx.md 按模板输出
  3. 没命中 → 选源(中文优先 xiachufang/douguo/meishij;英文 allrecipes/bbcgoodfood/themealdb)→ scripts/fetch.py --source <id> --query ...
  4. fetch 返回结构化 → scripts/save_recipe.py --json <tmp> 写入 data/recipes/
  5. 再 walkthrough 一次
  6. 末尾亮来源

Read the full file on GitHub · 114 lines

Files

What ships with it

60 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.

Changes

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.

  1. 11d ago First seen · 114 lines · 115 tokens per session scan A 99fbb4528b5e

Subscribe to this mod's changes

chef is a skill published in the GitHub repository Yrzhe/claude-skills (33 stars, last pushed 3mo ago), licensed MIT. It adds 115 tokens to every session and 2,173 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens