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.
npx skills add tranfu-labs/tranfu-skills --skill generate-product-logogit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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.
[](https://agentmods.dev/skills/tranfu-labs/tranfu-skills/generate-product-logo)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/generate-product-logo"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/generate-product-logo/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.
<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/generate-product-logo"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/generate-product-logo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00131 | $0.01513 |
| Opus 5 | $0.00066 | $0.00757 |
| Sonnet 5 | $0.00026 | $0.00303 |
| Haiku 4.5 | $0.00013 | $0.00151 |
Grade A, and why
generate-product-logo 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Product Logo
Create product-specific logo design rules first, then generate logo or icon concepts that follow those rules. This skill owns the process for turning product context into a reusable visual style direction; it does not own one fixed aesthetic.
Before generating, read references/style-and-workflow.md. If the user provides brand assets or reference images, inspect them and use them as inputs to the style direction.
Product Gate
CRITICAL: MUST NOT generate any logo until the product gate is satisfied; if any required field is missing, ask one product-gate question and STOP.
Minimum required product information:
- product name or working name;
- product category and core function;
- target user or buyer;
- main product motion, such as upload, download, relay, routing, sync, growth, protection, automation, review, or management;
- intended logo usage, such as app icon, browser icon, website header, social preview, product badge, or all of these.
If any of the above is missing, ask one concise question that collects the missing pieces. Do not ask for visual style first; derive the style direction from product context unless the user provides explicit visual constraints. Example:
先补一下产品信息：产品叫什么、做什么、给谁用、核心动作是什么（比如路由/同步/上传/下载/管理），以及 Logo 主要用在浏览器图标、官网还是社交预览？
Optional inputs to respect when provided:
- brand colors;
- existing logo or reference image;
- must-avoid symbols;
- required product metaphor, symbol family, or style direction;
- desired number of concepts;
- whether the result should continue into favicon, app icon, social preview, or page head assets.
Workflow
CREATE A TODO LIST FOR THE TASKS BELOW (one TODO per step):
- Confirm the product gate is satisfied. If it is not satisfied, follow the Product Gate question rule and STOP before image generation.
- Derive a short logo design specification: audience fit, brand personality, symbol logic, shape language, color/material direction, composition rules, and must-avoid choices.
- Translate the design specification into 3-4 distinct logo directions.
- Generate square 1:1 image concepts with image generation, unless the user explicitly asks for a text-only style guide.
- Save project-bound outputs into a durable workspace path, usually
outputs/logos/<product-slug>/<round-name>/. - Verify every generated candidate is a real image and square.
- MUST create a comparison contact sheet and a 32px nearest-neighbor preview for generated image concepts.
- Recommend the strongest candidate based on product fit, style-spec alignment, and small-size recognition.
- Wait for selection before producing final browser icons, social-preview images, page-head assets, or implementation changes.
What ships with it
6 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.
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.
- 12d ago First seen · 121 lines · 131 tokens per session scan A 8e6e42a7d1d3
generate-product-logo is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 131 tokens to every session and 1,513 once invoked, about $0.0007 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.