Borrowing it
Nothing to install: this file belongs to shangyankeji/super-dev. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shangyankeji/super-dev/main/.agents/skills/super-dev-seeai/SKILL.mdgit clone --depth 1 https://github.com/shangyankeji/super-devWrote 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/shangyankeji/super-dev/super-dev-seeai)<a href="https://agentmods.dev/skills/shangyankeji/super-dev/super-dev-seeai"><img src="https://agentmods.dev/badge/skills/shangyankeji/super-dev/super-dev-seeai.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.09031 |
| Opus 5 | $0.00009 | $0.04516 |
| Sonnet 5 | $0.00004 | $0.01806 |
| Haiku 4.5 | $0.00002 | $0.00903 |
Grade A, and why
super-dev-seeai 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 8d 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 — 680 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Super Dev SEEAI - 赛事极速版 (Codex)
关键约束提醒（每次操作前必读）
以下规则在整个开发过程中始终有效，不得以任何理由违反：
-
图标系统: 功能图标只能来自 Lucide / Heroicons / Tabler 图标库。绝对禁止使用 emoji 表情 作为功能图标、装饰图标或临时占位。如果你发现自己即将输出包含 emoji 的 UI 代码，停下来，改用图标库组件。
-
AI 模板化禁令: 禁止紫/粉渐变主色调、禁止 emoji 图标、禁止无信息层级的卡片墙、禁止默认系统字体直出。
-
代码即交付: 不允许“先用 emoji 顶上后面再换”。图标库必须在第一行 UI 代码前就锁定。
-
自检规则: 在向用户展示任何 UI 代码或预览前，必须自检源码中不存在任何 emoji 字符（Unicode range U+2600-U+27BF, U+1F300-U+1FAFF）。发现后先替换为正式图标库再继续。
Direct Activation Rule（强制）
- If this skill is invoked, Super Dev SEEAI competition mode is already active.
- Do not spend a turn explaining the skill or deciding whether to enter the workflow.
- Treat this as a distinct fast-delivery contract optimized for time-boxed competition work.
- Keep quality, but compress the path aggressively after Spec.
触发方式（强制）
- Treat
super-dev-seeai: <需求描述>andsuper-dev-seeai：<需求描述>as the AGENTS-driven natural-language SEEAI entry. - Treat
$super-dev-seeaias the explicit Codex CLI Skill entry for the competition mode. - In Codex App/Desktop, selecting
/super-dev-seeaifrom the slash Skill list is the official app entry. - Do not route SEEAI requests back to ordinary chat or to the full standard Super Dev contract.
Runtime Contract（强制）
- Super Dev SEEAI is still Super Dev governance, but with a competition-fast contract.
- The host remains responsible for model execution, tools, search, terminal, and edits.
- Use Codex native web/search/edit/terminal capabilities for research, building, and validation.
- Keep local
super-devCLI for governance artifacts only when it materially helps the fast path. - The mode is designed for 30-minute showcase builds such as a polished landing page, mini-game, or focused demo tool.
- Default decision rule: protect one demo path first, one wow point second, and only then add extra engineering depth.
首轮响应契约（强制）
- 首次触发时第一轮回复必须说明：Super Dev SEEAI 赛事模式已激活，当前阶段是
research。 - 先快速理解需求，再做极短顺位思考：作品类型、评委 wow 点、必须完成项、主动放弃项。
- 如果用户需求模糊，最多只补 1 个关键问题；能合理假设时直接给出假设并推进，不展开长澄清。
- 先完成 fast research，再写 compact research / PRD / architecture / UIUX。
- 文档确认后创建 compact Spec，然后直接进入 full-stack sprint。
- 不要在 SEEAI 模式里重新切回标准 Super Dev 的 preview confirm / 长质量闭环。
- 若会落盘 workflow state，必须把
flow_variant = seeai一起写入。
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.
- 8d ago First seen · 680 lines · 18 tokens per session scan A 66c8ff4aa296
super-dev-seeai is a skill published in the GitHub repository shangyankeji/super-dev (274 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 9,031 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
miniapp-dev
A development guide for BitFun MiniApps, which are small applications that run inside BitFun. It covers creating new MiniApps as well as maintaining the MiniApp framework.
3d-web-experiences
Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…
a11y-checklist
WCAG 2.2 AA quick reference — semantics, keyboard, names, states, contrast, motion, errors. Use when building or reviewing UI components.
perf-checklist
Performance quick reference — Core Web Vitals, bundle size, rendering, DB queries, caching. Use during implementation or review when perf matters.
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.