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 geniusdapeng-collab/super-mickey --skill supermickey-studiogit clone --depth 1 https://github.com/geniusdapeng-collab/super-mickeyWrote 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/geniusdapeng-collab/super-mickey/supermickey-studio)<a href="https://agentmods.dev/skills/geniusdapeng-collab/super-mickey/supermickey-studio"><img src="https://agentmods.dev/badge/skills/geniusdapeng-collab/super-mickey/supermickey-studio.svg" alt="Measured on agentmods" 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 | $0.00167 | $0.05276 |
| Opus 5 | $0.00084 | $0.02638 |
| Sonnet 5 | $0.00033 | $0.01055 |
| Haiku 4.5 | $0.00017 | $0.00528 |
Grade A, and why
supermickey-studio 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SuperMickey 视频提示词生成器
核心运行原则(最高优先级)
LLM 环节由本 Agent 自身模型承担:SuperMickey 系统中所有依赖 LLM 的模块(意图解析、剧本生成、场景卡 Agent、镜头设计 Agent、提示词引擎 Agent、导演审片 Agent、产品事实校验、营销技能路由、数据挖掘引擎五 Agent 等)一律由执行本技能的 Agent 用自己的模型能力就地运行,严格按照拉取到的最新代码中各模块的规范、字段定义、质量门执行。不需要、不等待、不尝试任何外部 API 密钥(ARK_API_KEY / KIMI_API_KEY 等)。
严禁降级运行:禁止跳过任何模块、禁止以"简化版/示意版/规范级运行"代替完整执行。必须按系统完整流水线跑完全部环节,每个环节的交付物一个不少,每个镜头的字段一个不缺,导演审片必须真实执行并给出评分结论。
不执行视频渲染:视频渲染环节一律跳过(用户后续手动渲染)。不需要配置渲染管线、不需要调用 Seedance 或任何渲染引擎。最终交付物止步于"镜头完整提示词"文本本身(定妆照为静态图片环节,按定妆照纪律执行,不在此限制内)。
真实代码核验:凡系统提供可执行校验的环节(预检、交付守卫、作品级校验、事实闸机、定妆照闸机、时长分配、技能路由、档案 Schema 校验),必须用 node 真实运行系统代码取得结果,禁止凭印象声明"已校验"。
确认机制双模说明:系统以 CLI 方式运行全流程时,每个主要环节(商品情报档案/创意主题/业务需求/PRD/镜头提示词/定妆照)均设人工确认门,逐一等待人工 approve 后才放行下游——这是系统生产纪律。但本技能调用方式下,由执行 Agent 按流水线连续跑完全部环节,各环节交付物照常产出,不中断等待用户确认;技能文件中出现"确认单"字样时,其用途是让 Agent 自检与向用户展示结果,而非等待批准的闸机。
执行流程(严格按顺序执行)
Step 0:前置检查(不可跳过)
- 克隆仓库默认分支最新代码(仓库已私有化,必须带令牌认证;优先 git clone 带认证头,失败则用 API 压缩包兜底):
git clone --depth 1 https://github.com/geniusdapeng-collab/super-mickey.git默认分支为 master,clone 得到的 HEAD 即"最新系统代码"。 - 确认当前版本号:只读克隆下来的
package.json的"version"字段,记录于执行日志。该字段是 SuperMickey 系统版本号的唯一权威来源。 - 运行规范预检:
node scripts/agent-preflight.js,退出码必须为 0;非 0 先修复再继续。 - 阅读并理解当前版本的系统架构、约束栈、提示词规范、输出格式定义、平台蓝图(hyperreality-system/config/platform-profiles.js)。
⚠️ 版本识别强制约束:
- 禁止通过 Git tag 列表、tag 版本号大小比较、文档标题、目录名、子系统内部编号推断"最新版本"。
- 禁止
git checkout任何 tag 或分支来获取"最新代码"——默认分支 HEAD 就是最新。- 仓库内出现的任何子系统历史内部编号与 SuperMickey 系统版本无关,一律忽略。
- 如果因网络或权限原因无法拉取最新代码,必须明确告知用户并停止执行,禁止基于记忆或旧版本继续运行。
- 测试目录中的镜头骨架(如 marketing-m*-test.js)只是模块单元测试夹具,禁止当作产物结构规范依据;产物结构以主管线(hyperreality-system/index.js)与预检规范卡为准。
Step 1:输入类型识别
接收用户提供的主题/故事/营销 Brief,判定输入类型:
- 故事/主题类:走电影叙事管线(创意主题生成 → 业务需求洞察 → PRD → 镜头提示词)。
- 社媒营销类(含商品名/平台名/种草/带货/投放等特征):走社媒营销管线,必须执行本技能"营销专属纪律"全部条款(见下文专章),且必须先执行节点 0。
Step 2:运行 SuperMickey 系统
基于拉取到的最新代码,按系统内部流程执行,关键节点必须逐项产出并即时输出交付物(输出后继续推进,不中断等待任何确认):
节点 0:珍妮纺织机·商品情报挖掘(社媒营销类强制,全链路第一环节)
- 触发条件:输入含商品名/营销 Brief 时必须最先执行本节点,早于创意主题生成;纯故事类任务跳过本节点并明确说明。
- 真实运行数据挖掘引擎(
hyperreality-system/engines/data-mining-engine/,spec 模式):engine.plan(input)产出三份采集任务书(A1 商品情报/A2 用户评价/A3 竞品侦察);- 本 Agent 按任务书就地联网检索并回填(严守任务书 discipline:评价原文回填、无源事实不回填、商品图禁 AI 图冒充);
engine.assemble(...)真实运行:五站流水线(采集→挖掘→侦察→交叉验证→装订),Schema 校验失败即拒收。
- 输出(全任务最先交付的两份文件):
00_商品情报档案.md:商品身份与价格带(含置信度)、官方卖点、商品图清单、使用场景、用户称赞点/吐槽点/原话、优缺点(用户共识与官方宣称分区)、竞品矩阵与差异化空位、钩子原料、情报缺口(gaps 逐条公示)、溯源清单(provenance)、交叉验证报告。00_商品主图清单.md:英雄照(编号 + URL + 角度 + 授权风险)+ 全部参考图 manifest,明确标注"仅作定妆照参考图,须核对真实性与型号一致性"。
- 连续执行(技能模式):两份文件产出即视为情报层就绪,Agent 生成档案确认单用于自检与向用户展示结果,随后直接向下游推进,不中断等待用户确认(人工确认门仅在系统 CLI 运行模式下生效,见"核心运行原则·确认机制双模说明")。
- 档案命中复用(同商品历史档案未过期)时直接加载消费并注明"[复用]",连续推进不中断。
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 · 178 lines · 167 tokens per session scan A cdd65e83b05b
supermickey-studio is a skill published in the GitHub repository geniusdapeng-collab/super-mickey (5 stars, last pushed 13d ago), licensed MIT. It adds 167 tokens to every session and 5,276 once invoked, about $0.0008 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
contextual-commit
Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.
repomix-explorer
Analyze or explore a codebase (remote or local repository) by packing it with the Repomix CLI, then reading and searching the generated output. Use when the user wants a high-level understanding of an unfamiliar or large repo, not a targeted edit. Trigger for: Structure/overview: "analyze this repo", "what's the…
repomix
Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
website-maintainer
Use this skill when working on the Repomix documentation website in website/ directory, including VitePress configuration, multi-language content, or translation workflows.
browser-extension-developer
Use this skill when developing or maintaining browser extension code in the browser/ directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.