New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Cook

by avibebuilder in avibebuilder/claude-prime

Implement, build, create, or add any feature, endpoint, page, component, or functionality.

MITAuto-check passedBackend & APIs

Install Cook

skills CLI
$ npx skills add avibebuilder/claude-prime --skill cook -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install avibebuilder/claude-prime cook --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/avibebuilder/claude-prime.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/cook .claude/skills/cook && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cook
GitHub stars
120
Token cost
~970 tokens
SKILL.md length
421 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
MIT

At a glance

Implement, build, create, or add any feature, endpoint, page, component, or functionality.

  • Works in 4 steps: Break into tasks only when it helps → Implement → Verify → Review → Next → Review the whole change set → …
  • The user asks you to write new code
  • SKILL.md covers How cook works, Before you start, The loop and Request
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cook is an agent skill from avibebuilder/claude-prime. Implement, build, create, or add any feature, endpoint, page, component, or functionality. Use this skill whenever the user asks you to write new code or make code changes — whether it's adding an API endpoint, building a UI page, creating an export feature, wiring up a webhook, implementing a search/filter, or any other hands-on coding task. This is the default skill for all 'build this', 'add this', 'create this', 'wire up', 'implement' requests. Covers the full cycle: clarify requirements, plan if needed…

Its SKILL.md is about 970 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Requirements gathering, REST APIs and Webhooks. The repository describes itself as: You've heard Claude Code can do amazing things. Skills, hooks, agents, memory systems — but who has time to figure all that out? Claude Prime sets it up for you in one command. The licence is MIT.

When your agent uses it

  • The user asks you to write new code
  • Make code changes — whether its adding an API endpoint
  • Building a UI page
  • Creating an export feature

Example prompts

  • “build this”
  • “add this”
  • “create this”
  • “/cook”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Break into tasks only when it helps
  2. Implement → Verify → Review → Next
  3. Review the whole change set
  4. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 80bcfa4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cook loads about 970 tokens when it runs. Until then it costs about 168 tokens; SKILL.md has 421 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~168
When it runs · the whole SKILL.md, loaded when a task matches
~970

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from avibebuilder/claude-prime at commit 80bcfa4, republished under its MIT licence (© avibebuilder). 421 words, ~970 tokens.

Download SKILL.mdSave it as .claude/skills/cook/SKILL.md (or your agent's skills folder).
name
cook
description
Implement, build, create, or add any feature, endpoint, page, component, or functionality. Use this skill whenever the user asks you to write new code or make code changes — whether it's adding an API endpoint, building a UI page, creating an export feature, wiring up a webhook, implementing a search/filter, or any other hands-on coding task. This is the default skill for all 'build this', 'add this', 'create this', 'wire up', 'implement' requests. Covers the full cycle: clarify requirements, plan if needed, write code, verify, and review. Do NOT use for pure research, debugging, documentation, or explanation — only when the user wants working code delivered.
argument-hint
what-to-implement

ultrathink.

How cook works

Cook is an incremental loop: break work into tasks, implement one, verify it works, move to the next. The key discipline is that nothing is "done" until there's evidence it works — but how you verify adapts to the situation.

Before you start

If the request is clear, start. If it's ambiguous or multi-faceted, ask clarifying questions. If the work is large or multi-path, plan first (/give-plan). Otherwise, just start.

The loop

1. Break into tasks only when it helps

For a small single-concern request, just implement, verify, and continue.

For multi-step work or collaboration, use .claude/scripts/tasks.py to track concrete outcomes. Task files persist in .tasks/, so a fresh context can pick up where the last one left off.

Every task requires three fields: title, desc, expected. Read the authoring rubric before writing tasks — bad tasks are worse than no tasks:

  • .claude/scripts/tasks.py --help for the short-form rubric and examples
  • .claude/scripts/tasks-authoring.md for the full guide
.claude/scripts/tasks.py --task-file <slug> add "<title>" "<desc>" "<expected>"
.claude/scripts/tasks.py --task-file <slug> list
.claude/scripts/tasks.py --task-file <slug> verify <id> "<evidence>"
.claude/scripts/tasks.py --task-file <slug> done <id>
2. Implement → Verify → Review → Next

Pick the next unblocked task, make the change, then hand off to a tester and (for risky work) a reviewer — isolated teammates that judge the change independently. See .claude/skills/test/teammate.md and .claude/skills/review-code/teammate.md for how to spawn them.

/cook owns implementation. The tester owns verification. Give the tester:

  • the user-visible claim or acceptance criteria
  • the files or behavior you changed
  • the most likely regression surface
  • any constraints that matter

You can still add durable tests, fixtures, or stable selectors when they belong to the product change itself. Do not stuff temporary verification tactics into /cook just to get through one run.

Show full SKILL.md (160 more words)Show less

Before invoking verification, confirm the edits actually landed on disk. If the change you expect is missing from the diff, fix that first; a passing check against unchanged code is worthless evidence.

Do not mark a task done on confidence alone. The tester proves the behavior. The reviewer checks that the implementation is correct, scoped, and aligned with the repo. For risky or non-trivial work, spawn a reviewer before marking the task complete.

Update task status as you go so the execution trail stays trustworthy.

3. Review the whole change set

After the task list is complete, review the combined diff before declaring success. Cross-task issues often appear only in the final aggregate: mismatched assumptions, naming drift, incomplete ripple updates, or verification that was too narrow. Spawn a reviewer for this final pass.

4. Report

When done, summarize:

  • what changed
  • how each claim was verified
  • decisions that materially shaped the implementation
  • any follow-up the user should know about

Request

<request>$ARGUMENTS</request>

© avibebuilder, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/cook of avibebuilder/claude-prime.

Open the folder on GitHubat commit 80bcfa4

Compare with similar skills

Cook next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cook compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cook this skillavibebuilder/claude-prime120—~970Automated safety check: PassMIT
API Patternsdilolabs/nosia2131 repos~2.5kAutomated safety check: PassMIT
Loops APIopeninary/openinary412—~1.1kAutomated safety check: PassAGPL-3.0
Verifygregluffy/HomeLabInfo102—~424Automated safety check: PassGPL-3.0
Frappe Core APIImpertio-Studio/Frappe_Claude_Skill_Package1871 repos~3.2kAutomated safety check: PassMIT
Lemon Squeezy Integrationpockethost/pockethost1.4k—~1.1kAutomated safety check: PassMIT

Similar skills

  • API Patterns

    dilolabs/nosia

    Builds REST APIs using respondto blocks with Jbuilder templates following the 37signals same-controllers-different-formats philosophy.

    213 GitHub starsUsed in 1 repo~2.5k tokens
    Backend & APIsAuto-check passed

  • Loops API

    openinary/openinary

    A skill your agent uses whenever the user wants to integrate Loops from application code, backend services, webhook handlers, or server-side automation.

    412 GitHub stars~1.1k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed

  • Verify

    gregluffy/HomeLabInfo

    Build, run, and drive the HomeLabInfo backend to verify changes at its real surfaces (REST API, UDP DHCP listener, outgoing webhooks).

    102 GitHub stars~424 tokensUpdated 2 mo ago
    Backend & APIsAuto-check passed

  • Frappe Core API

    Impertio-Studio/Frappe_Claude_Skill_Package

    A skill your agent uses when building ERPNext/Frappe API integrations (v14/v15/v16) including REST API, RPC API, authentication, webhooks, and rate limiting.

    187 GitHub starsUsed in 1 repo~3.2k tokens
    Backend & APIsAuto-check passed

  • Lemon Squeezy Integration

    pockethost/pockethost

    Full Lemon Squeezy integration — REST API, @lemonsqueezy/lemonsqueezy.js server SDK, Lemon.js checkout overlays, webhooks, customdata, and subscriptions.

    1.4k GitHub stars~1.1k tokensUpdated 9 days ago
    Backend & APIsAuto-check passed

  • Bigcommerce API

    qdhenry/Claude-Command-Suite

    BigCommerce API expert for building integrations, apps, headless storefronts, and automations.

    1.3k GitHub stars~1.5k tokensUpdated 7 mo ago
    Backend & APIsAuto-check passed

More from avibebuilder/claude-prime

All 19 skills in this repo

  • Diagnose

    avibebuilder/claude-prime

    Investigate unexpected behavior and mysterious bugs. An agent skill from avibebuilder/claude-prime.

    120 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed

  • Frontend Design

    avibebuilder/claude-prime

    Builds distinctive, production-grade UIs that avoid generic AI aesthetics.

    120 GitHub stars~2.1k tokensUpdated 4 mo ago
    Auto-check passed

  • Media Processor

    avibebuilder/claude-prime

    Specialized visual and multimedia processing tools. An agent skill from avibebuilder/claude-prime.

    120 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check: notes

  • Skill Creator

    avibebuilder/claude-prime

    A skill your agent uses when the user wants to work on a Claude Code skill file (SKILL.md): writing one from scratch, testing whether an existing one works well, running evals or benchmarks…

    120 GitHub stars~8.2k tokensUpdated 4 mo ago
    Auto-check passed

  • Self Evolve

    avibebuilder/claude-prime

    The single config quality skill. An agent skill from avibebuilder/claude-prime.

    120 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed

  • Prime Sync

    avibebuilder/claude-prime

    Syncs Claude config between prime repo and target projects. An agent skill from avibebuilder/claude-prime.

    120 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Cook

What does Cook do?

Implement, build, create, or add any feature, endpoint, page, component, or functionality. Cook is an agent skill from avibebuilder/claude-prime. Implement, build, create, or add any feature, endpoint, page, component, or functionality.

When should I use Cook?

Cook fits situations like: the user asks you to write new code; make code changes — whether its adding an API endpoint; building a UI page; creating an export feature.

How do I install Cook in Claude Code?

Run `npx skills add avibebuilder/claude-prime --skill cook -a claude-code`. Or copy the skill folder (.claude/skills/cook in avibebuilder/claude-prime) into .claude/skills/cook in your project. Claude Code loads it when a task matches its description.

How do I install Cook in Codex?

Run `npx skills add avibebuilder/claude-prime --skill cook -a codex`. Or copy the skill folder (.claude/skills/cook in avibebuilder/claude-prime) into .agents/skills/cook in your project. Codex loads it when a task matches its description.

Can I use Cook in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add avibebuilder/claude-prime --skill cook -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cook, .gemini/skills/cook, .github/skills/cook and .opencode/skills/cook in your project.

What does Cook need to run?

SKILL.md names no scripts, command-line tools or credentials: Cook is instructions for the agent only.

Does Cook access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cook safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cook use?

Cook is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cook use?

About 970 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cook?

Skills that share tags, products or a category with Cook: API Patterns (dilolabs/nosia, 213 stars), Loops API (openinary/openinary, 412 stars), Verify (gregluffy/HomeLabInfo, 102 stars) and Frappe Core API (Impertio-Studio/Frappe_Claude_Skill_Package, 187 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cook?

avibebuilder (a GitHub organization) maintains it in avibebuilder/claude-prime, which has 120 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on May 16, 2026.

Source: avibebuilder/claude-prime on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.