New: 98,000+ 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

Grill With Vision

by udecode in udecode/kitcn

Pressure-test a kitcn product, API, architecture, or DX direction against VISION.md and source evidence before committing to a plan or PRD.

Apache-2.0Auto-check passedProduct & Project Management

Install Grill With Vision

skills CLI
$ npx skills add udecode/kitcn --skill grill-with-vision -a claude-code

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

GitHub CLI
$ gh skill install udecode/kitcn grill-with-vision --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/udecode/kitcn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/grill-with-vision .claude/skills/grill-with-vision && 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
grill-with-vision
GitHub stars
450
Token cost
~632 tokens
SKILL.md length
308 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
Apache-2.0

At a glance

Pressure-test a kitcn product, API, architecture, or DX direction against VISION.md and source evidence before committing to a plan or PRD.

  • Works in 4 steps: VISION.md. → docs/README.md and the named PRD,… → Public exports, CLI commands, runtime… → …
  • Tasks that involve PRD writing
  • SKILL.md covers Read First, Interview Loop, Domain Modeling Discipline and Durable Notes, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Grill With Vision is an agent skill from udecode/kitcn. Pressure-test a kitcn product, API, architecture, or DX direction against VISION.md and source evidence before committing to a plan or PRD.

Its SKILL.md is about 630 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 Product & Project Management, covering PRD writing. The repository describes itself as: Convex + Better Auth + tRPC + Drizzle + TanStack Query + shadcn. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve PRD writing

Example prompts

  • “/grill-with-vision”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. VISION.md.
  2. docs/README.md and the named PRD, milestone, plan, ADR, or source.
  3. Public exports, CLI commands, runtime entry points, and representative tests.
  4. Local clones of proven OSS owners when the proposal copies a familiar

What it can do on your machine

Read from SKILL.md and the folder at commit c6010f5. 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

Grill With Vision loads about 632 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 308 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~632

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 udecode/kitcn at commit c6010f5, republished under its Apache-2.0 licence (© udecode). 308 words, ~632 tokens.

Download SKILL.mdSave it as .claude/skills/grill-with-vision/SKILL.md (or your agent's skills folder).
name
grill-with-vision
description
Pressure-test a kitcn product, API, architecture, or DX direction against VISION.md and source evidence before committing to a plan or PRD.
argument-hint
<idea | source path | current plan>

Grill With Vision

Use this when the direction is important enough that polite agreement would be expensive. The output is a sharper decision, not an interview transcript.

Read First

  1. VISION.md.
  2. docs/README.md and the named PRD, milestone, plan, ADR, or source.
  3. Public exports, CLI commands, runtime entry points, and representative tests.
  4. Local clones of proven OSS owners when the proposal copies a familiar mental model.

Interview Loop

Ask one high-leverage question at a time when user input is genuinely needed. Otherwise answer it from evidence and continue. Attack:

  • the user and job being improved;
  • why this belongs in kitcn rather than application code;
  • the familiar tRPC/Drizzle/TanStack/better-auth mental model being preserved;
  • public API, type flow, auth, data flow, and bundle consequences;
  • CLI and agent DX, including deterministic/non-interactive output;
  • source/generated ownership and regeneration;
  • hard-cut and compatibility stance;
  • proof, benchmarks, fixtures, scenarios, and failure states;
  • scope that is attractive but not necessary for the outcome.

When two answers conflict, name the contradiction and force a choice. Do not paper it over with an abstraction.

Domain Modeling Discipline

For each noun and verb, identify:

  • canonical owner and identifier;
  • input, persisted state, derived state, and output;
  • authorization boundary;
  • package/runtime entry points;
  • public name and user-facing mental model;
  • lifecycle, failure, retry, and deletion behavior.

Reject a new primitive if an existing owner can express it cleanly. Reject reuse if it corrupts the existing owner's meaning.

Durable Notes

Write meaningful discoveries to docs/brainstorms/<date>-<topic>.md or the active plan. Include decisions, rejected options with reasons, source links, open pivots, and the recommended next owner (to-milestone, to-prd, major-task, task, or stop).

Local doctrine and plans own this step.

Stop Boundary

Stop when the core outcome, owner map, irreversible decisions, proof bar, and non-goals are clear enough for the next artifact. Keep grilling if a public API or package boundary still depends on an unstated assumption.

© udecode, Apache-2.0. 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 .agents/skills/grill-with-vision of udecode/kitcn.

Open the folder on GitHubat commit c6010f5

Compare with similar skills

Grill With Vision 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.

Grill With Vision compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Grill With Vision this skilludecode/kitcn450—~632Automated safety check: PassApache-2.0
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Ralph Tui Create Beadssubsy/ralph-tui2.5k1 repos~2.6kAutomated safety check: PassMIT
Trellis Brainstormanjiemo/SunnyBeach1787 repos~4kAutomated safety check: PassApache-2.0
Adversarial Speczscole/adversarial-spec5561 repos~8.3kAutomated safety check: NotesMIT
Ralph Tui Create Beads Rustsubsy/ralph-tui2.5k1 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • CCPM Project Management

    automazeio/ccpm

    Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed

  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed

  • Trellis Brainstorm

    anjiemo/SunnyBeach

    Guides collaborative requirements discovery before implementation.

    178 GitHub starsUsed in 7 repos~4k tokens
    Product & Project ManagementAuto-check passed

  • Adversarial Spec

    zscole/adversarial-spec

    Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.

    556 GitHub starsUsed in 1 repo~8.3k tokens
    Product & Project ManagementAuto-check: notes

  • Ralph Tui Create Beads Rust

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).

    2.5k GitHub starsUsed in 1 repo~2.8k tokens
    Product & Project ManagementAuto-check passed

  • Ouroboros PM Interview

    Q00/ouroboros

    Runs a guided product-manager interview that classifies each question automatically and produces a Product Requirements Document.

    6.2k GitHub starsUsed in 1 repo~5.7k tokens
    Product & Project ManagementAuto-check passed

More from udecode/kitcn

All 33 skills in this repo

  • Walkthrough

    udecode/kitcn

    Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts.

    450 GitHub stars~1.6k tokensUpdated 7 days ago
    Auto-check passed

  • Avoid Feature Creep

    udecode/kitcn

    Prevent feature creep when building software, apps, and AI-powered products.

    450 GitHub stars~2.7k tokensUpdated 7 days ago
    Auto-check passed

  • Changeset Resolve

    udecode/kitcn

    Repair an unreleased .changeset/.md file so it matches the real branch delta against main.

    450 GitHub stars~922 tokensUpdated 7 days ago
    Auto-check passed

  • Convex Release Audit

    udecode/kitcn

    Audit newer Convex npm releases against kitcn. An agent skill from udecode/kitcn.

    450 GitHub stars~1.8k tokensUpdated 7 days ago
    Auto-check passed

  • Jotai X

    udecode/kitcn

    A skill your agent uses when working with Jotai X stores (createAtomStore), accessing state in components or callbacks, persisting state to cookies or localStorage

    450 GitHub stars~3.7k tokensUpdated 7 days ago
    Auto-check passed

  • Linear Backlog

    udecode/kitcn

    Run a scoped Linear backlog autonomously as a sequence of maximal safe parallel batches by composing orchestrator, autogoal, and task.

    450 GitHub stars~3.1k tokensUpdated 7 days ago
    Auto-check passed

Categories

Questions about Grill With Vision

What does Grill With Vision do?

Pressure-test a kitcn product, API, architecture, or DX direction against VISION.md and source evidence before committing to a plan or PRD. Grill With Vision is an agent skill from udecode/kitcn.md and source evidence before committing to a plan or PRD.

When should I use Grill With Vision?

Grill With Vision fits situations like: tasks that involve PRD writing.

How do I install Grill With Vision in Claude Code?

Run `npx skills add udecode/kitcn --skill grill-with-vision -a claude-code`. Or copy the skill folder (.agents/skills/grill-with-vision in udecode/kitcn) into .claude/skills/grill-with-vision in your project. Claude Code loads it when a task matches its description.

How do I install Grill With Vision in Codex?

Run `npx skills add udecode/kitcn --skill grill-with-vision -a codex`. Or copy the skill folder (.agents/skills/grill-with-vision in udecode/kitcn) into .agents/skills/grill-with-vision in your project. Codex loads it when a task matches its description.

Can I use Grill With Vision 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 udecode/kitcn --skill grill-with-vision -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/grill-with-vision, .gemini/skills/grill-with-vision, .github/skills/grill-with-vision and .opencode/skills/grill-with-vision in your project.

What does Grill With Vision need to run?

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

Does Grill With Vision 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 Grill With Vision 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 Grill With Vision use?

Grill With Vision is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Grill With Vision use?

About 632 tokens (SKILL.md is roughly 2.5k 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 Grill With Vision?

Skills that share tags, products or a category with Grill With Vision: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Adversarial Spec (zscole/adversarial-spec, 556 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Grill With Vision?

udecode (a GitHub organization) maintains it in udecode/kitcn, which has 450 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 1, 2026.

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