grill-me-jewel

grill-me-jewel is a skill for Codex from yuyou-dev/GrillMeJewel. It costs 105 tokens per session (987 once invoked), scanned A, original, Apache-2.0.

A four-stage interview skill for turning an unclear jewelry idea into a confirmed design brief and real jewelry images made with gpt-image-2.

In plain words
What is it for?
It helps discover a jewelry concept, define its meaning and visual style, choose variations and delivery details, confirm the brief, and generate design images.
Why use it?
It gives beginners a structured way to decide what they want before images are generated, preserving their answers through confirmation.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit It helps discover a jewelry concept, define its meaning and visual style, choose variations and delivery details, confirm the brief, and generate design images.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yuyou-dev/grillmejewel/grill-me-jewel
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 yuyou-dev/GrillMeJewel --skill grill-me-jewel
Clone the repo
git clone --depth 1 https://github.com/yuyou-dev/GrillMeJewel

Made for: Codex.

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 grill-me-jewel

README.md
[![agentmods](https://agentmods.dev/badge/skills/yuyou-dev/grillmejewel/grill-me-jewel/github.svg)](https://agentmods.dev/skills/yuyou-dev/grillmejewel/grill-me-jewel)
Your own site
<a href="https://agentmods.dev/skills/yuyou-dev/grillmejewel/grill-me-jewel"><img src="https://agentmods.dev/badge/skills/yuyou-dev/grillmejewel/grill-me-jewel/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 grill-me-jewel

Your own site · 80×15
<a href="https://agentmods.dev/skills/yuyou-dev/grillmejewel/grill-me-jewel"><img src="https://agentmods.dev/badge/skills/yuyou-dev/grillmejewel/grill-me-jewel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 987 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 $0.00105 $0.00987
Opus 5 $0.00053 $0.00494
Sonnet 5 $0.00021 $0.00197
Haiku 4.5 $0.00011 $0.00099

Measured 11d ago against content hash d8593fa692bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

grill-me-jewel 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/grill-me-jewel/skills/grill-me-jewel/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill Me Jewel

Purpose

Help a beginner discover and articulate what jewelry they want to design. Complete four purposeful discovery rounds plus a separate confirmation round, preserve every answer, then use Codex gpt-image-2 to generate the requested real design images.

Interview

  1. Read references/design-frontier.md. Reuse facts from the conversation and attachments, then complete foundation, meaning, design language, and variation/delivery as four submitted Apps UI rounds. A known fact moves its stage to a deeper decision; it does not remove the stage.
  2. For every round, call ask_grill_me_questions as the primary interaction surface with the exact stage and sequential round. Ask one to four currently answerable fields. Discover that exact tool name before falling back to prose. Use concise chat questions only after real tool discovery fails or the call errors.
  3. Use stable lowercase field and option ids. Offer an other option when a useful answer may fall outside the list. In foundation, ask delivery_count unless the user already supplied a count; offer count_1, count_2, count_4, count_8, and a custom value. Never ask for providers, concurrency, internal job ids, API keys, or cost.
  4. After submission, summarize only the newly established facts and preserve all earlier answers. Continue with the next stage; never answer the user's side of the interview.
  5. In variation/delivery, split locked facts from flexible axes. For multiple outputs, define named candidate branches that each change at least three visible design axes while preserving product identity, wearing logic, and the central story.
  6. After four discovery rounds, present the assembled brief through one final ask_grill_me_questions confirmation round with stage: confirmation and round 5 or greater. Ask whether to confirm it or revise it, with a text field for corrections when needed.
  7. After confirmation, read references/image2-generation.md, compile one production prompt per requested design, and invoke Codex $imagegen / gpt-image-2. The confirmed brief is the source of truth; do not resume interviewing during generation.
  8. Return the final brief in Markdown under: Objective, Product, Design Direction, Materials and Craft, Source Assets, Output Intent, Locked Facts, Flexible Details. Present every real generated image inline. Never claim an image exists unless the tool returned it.

Read the full file on GitHub · 69 lines

Files

What ships with it

3 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 · 69 lines · 105 tokens per session scan A d8593fa692bf

Subscribe to this mod's changes

grill-me-jewel is a skill published in the GitHub repository yuyou-dev/GrillMeJewel (0 stars, last pushed 24d ago), licensed Apache-2.0. It adds 105 tokens to every session and 987 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

web-design-engineer

Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.…

ConardLi/garden-skills · 96 tokens

asset-set

Generate a complete, style-consistent set of image assets for a web or app project in one pass — favicons, app icons, OG/social cards, hero images, empty-state illustrations, or a matching icon family. Use when the user asks for "icons for", "assets for", "favicon", "og image", "app icon", "a set of illustrations", or…

Sateezg/codex-bridge · 85 tokens

claude-design-skill

Claude Code-based design skill for hi-fi prototyping and Figma MCP-driven precision design work. Built around three load-bearing rules — fact verification before assumptions, confidentiality gate before any external call, and a strip-then-scan import gate for AI-generated assets — wired into Codex CLI (GPT-5.5…

0xmhha/claude-design-skill · 184 tokens

brand-icon-banner

A skill for turning platform observations, policy explanations, or product judgments into wide banners featuring a 3D brand app icon.

FANzR-arch/Phil-design-skills · 190 tokens

engineering-blueprint-sheet

A prompt-writing guide for engineering-drawing visuals, such as blueprints, orthographic views, exploded diagrams, and cross-sections, with technical labels and drafting marks.

FANzR-arch/Phil-design-skills · 266 tokens

quiet-paper-specimen

A prompt-writing guide for turning a theme, feeling, object, or short text into a quiet minimalist cover with aged paper, one subject, handwritten Chinese lettering, and a single bright color detail.

FANzR-arch/Phil-design-skills · 198 tokens