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 skill-icon-generatorgit 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/skill-icon-generator)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/skill-icon-generator"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/skill-icon-generator/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/skill-icon-generator"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/skill-icon-generator.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 | $0.00254 | $0.03089 |
| Opus 5 | $0.00127 | $0.01545 |
| Sonnet 5 | $0.00051 | $0.00618 |
| Haiku 4.5 | $0.00025 | $0.00309 |
Grade A, and why
skill-icon-generator 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 9d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
单个 Skill 图标生成器
一次只处理用户指定的一个 Skill。使用本 Skill 自带的脚本、Lucide/品牌母版、 人工映射和 Sharp 运行时;生成前完成品牌判定、语义判断、现有占用排除与感知 相似度检查。
工作流
CREATE A TODO LIST FOR THE TASKS BELOW(每个步骤一个 TODO,并随执行更新状态):
-
将用户指定路径规范化为
<target-skill-dir>,将本文件目录记为<generator-skill-dir>。 -
完整读取目标
SKILL.md。目标不存在、不是 Skill,或 YAML frontmatter 中name/description缺失时,报告原因并停止;不得选图或写文件。 -
从
name + description提炼:- 主语义:这个 Skill 的任务形态或核心能力,例如 MCP、审查、部署、写作。
- 次语义:业务对象或领域,例如 Privy、飞书、社媒、市场。
- 品牌绑定:若 Skill 的名称或核心能力直接绑定一个明确的第三方品牌、 产品或平台,且移除该品牌后任务对象会改变,则标记为品牌绑定型。
- 品牌绑定型优先表达品牌身份;其他 Skill 必须优先表达主语义,不得只命中 次语义关键词。
-
检查目标现有
assets/icon.svg/icon.png:- 已存在且用户未明确要求替换:报告现有资产并停止。
- 用户明确要求替换:后续生成命令使用
--force。
-
读取
assets/brand-registry.json、assets/curated-specs.json和--list-icons输出。若目标名称命中品牌注册表,采用注册表中唯一的品牌 Logo 与官方主色;同品牌已有映射时直接复用。非品牌候选再排除:- 已被其他 Skill 人工映射占用的相同 Lucide 或品牌母版;
- 与任一已映射图标感知相似度
> 50%的 Lucide; - 只符合次语义、不符合主语义的 Lucide。
-
目标没有人工映射时:
- 已注册品牌直接使用注册表中唯一的纯品牌母版,不叠加任务修饰符。
- 未注册的品牌绑定型先按“品牌 Logo 规则”选择和规范化品牌母版,并同步登记到
assets/brand-registry.json;不得退回无关 Lucide。 - 非品牌型内部比较至少 3 个语义候选,按以下顺序裁决:
- 主语义准确;
- 与次语义不冲突;
- 感知相似度最低;
- 48×48 下轮廓清晰。 不向用户展示未通过门禁的草稿。若内置母版没有合格候选,为公司库目标补充一个 官方 Lucide 母版并新增人工映射;不得用无关图形或稳定哈希结果凑数。
-
首次使用、依赖缺失、升级后或用户要求自检时运行:
npm install --prefix "<generator-skill-dir>" --no-package-lock node "<generator-skill-dir>/scripts/self_check.mjs"必须看到
SELF_CHECK_PASS;否则展示失败项并停止。 -
先预览最终选择:
node "<generator-skill-dir>/scripts/generate_icon.mjs" \ "<target-skill-dir>" --dry-run检查
mark_type、lucide_icon、metaphor、closest_match.similarity与品牌/主语义一致。 -
运行单目标生成器。只有步骤 4 明确允许替换时才追加
--force:node "<generator-skill-dir>/scripts/generate_icon.mjs" \ "<target-skill-dir>" -
若生成命令失败,报告错误与部分产物并停止;不得绕过相似度门禁,不得自行追加
--force重试。 -
打开实际 PNG,验证 SVG、PNG、
agents/openai.yaml和感知相似度报告。 -
输出
ICON_GENERATION_REPORT,包含目标、品牌判定、主/次语义、颜色族、mark_type、图形母版、隐喻、品牌来源(如适用)、选择来源、最相似图标及 百分比、输出路径。
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.
- .gitignore 14 B
- agents/openai.yaml 393 B
- assets/brand-registry.json 1.6 KB
- assets/curated-specs.json 6.0 KB
- assets/icon.png 703 B
- assets/icon.svg 609 B
- assets/lucide/align-left.svg 360 B
- assets/lucide/blocks.svg 444 B
- assets/lucide/book-open-check.svg 510 B
- assets/lucide/book-open-text.svg 564 B
- assets/lucide/boxes.svg 900 B
- assets/lucide/brand-coolify.svg 428 B
- assets/lucide/brand-github.svg 878 B
- assets/lucide/brand-lark.svg 2.5 KB
- assets/lucide/brand-privy.svg 284 B
- assets/lucide/brand-sina-weibo.svg 1.5 KB
- assets/lucide/brand-wechat.svg 1.3 KB
- assets/lucide/brand-xiaohongshu.svg 3.5 KB
- assets/lucide/chart-line.svg 362 B
- assets/lucide/chart-network.svg 548 B
- assets/lucide/chart-no-axes-combined.svg 525 B
- assets/lucide/clipboard-check.svg 469 B
- assets/lucide/cloud-cog.svg 735 B
- assets/lucide/compass.svg 429 B
- assets/lucide/dna.svg 688 B
- assets/lucide/file-check-2.svg 475 B
- assets/lucide/file-code-2.svg 507 B
- assets/lucide/file-down.svg 507 B
- assets/lucide/file-lock-2.svg 536 B
- assets/lucide/file-pen-line.svg 617 B
- assets/lucide/focus.svg 477 B
- assets/lucide/folder-cog.svg 757 B
- assets/lucide/funnel.svg 447 B
- assets/lucide/gallery-thumbnails.svg 444 B
- assets/lucide/gallery-vertical-end.svg 399 B
- assets/lucide/gauge.svg 354 B
- assets/lucide/gem.svg 499 B
- assets/lucide/git-branch.svg 394 B
- assets/lucide/git-compare-arrows.svg 502 B
- assets/lucide/git-fork.svg 469 B
- assets/lucide/grid-2x2.svg 388 B
- assets/lucide/image-down.svg 489 B
- assets/lucide/images.svg 522 B
- assets/lucide/key-round.svg 533 B
- assets/lucide/layout-template.svg 451 B
- assets/lucide/library-big.svg 491 B
- assets/lucide/lightbulb.svg 451 B
- assets/lucide/list-checks.svg 418 B
- assets/lucide/list.svg 428 B
- assets/lucide/message-square-check.svg 457 B
- assets/lucide/monitor-cog.svg 747 B
- assets/lucide/network.svg 523 B
- assets/lucide/newspaper.svg 496 B
- assets/lucide/notebook-pen.svg 602 B
- assets/lucide/package-check.svg 554 B
- assets/lucide/palette.svg 649 B
- assets/lucide/panel-top.svg 364 B
- assets/lucide/panels-top-left.svg 393 B
- assets/lucide/pen-tool.svg 623 B
- assets/lucide/puzzle.svg 762 B
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.
- 9d ago First seen · 217 lines · 254 tokens per session scan A b129ec9dee07
skill-icon-generator is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 254 tokens to every session and 3,089 once invoked, about $0.0013 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 2026-09-03.
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.