Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.
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 zts212653/clowder-ai --skill agent-product-promo-directorgit clone --depth 1 https://github.com/zts212653/clowder-aiWrote 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/zts212653/clowder-ai/agent-product-promo-director)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/agent-product-promo-director"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/agent-product-promo-director/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/zts212653/clowder-ai/agent-product-promo-director"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/agent-product-promo-director.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00234 | $0.02764 |
| Opus 5 | $0.00117 | $0.01382 |
| Sonnet 5 | $0.00047 | $0.00553 |
| Haiku 4.5 | $0.00023 | $0.00276 |
Grade A, and why
agent-product-promo-director 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Product Promo Director
这是一层创意导演合同，不是 renderer。它解决 Agent 产品特有的问题：产品的价值常藏在接球、规划、交接、工具动作、纠错、记忆与恢复里；如果只拍最终成果，观众看到的是“它做了什么”，看不到“为什么需要这个产品”。
Intent Gate
先判断本轮问题：
| Intent | 本轮交付 | 下一步 |
|---|---|---|
reference research |
查官方原片，记录可观察镜头/叙事/声音语法及推断边界 | 时效性强先用 deep-research，再回本 Skill 合成 brief |
creative direction |
产品主角、格式、故事、镜头、声音、证据合同 | 由 operator 验收主语与情绪 |
production 且 brief 未锁 |
先完成本 Skill，不开机 | brief 通过后转 video-forge |
production 且 brief 已锁 |
不重复导演流程 | 直接转 video-forge |
review |
按本合同判断已有片子在卖产品、成果还是功能表 | 给 verdict，不擅自拍新版 |
用户给出的页面、thread、录屏或成果是候选素材，不是拍摄授权，也不是自动主题。
1. 锁定真正的主角
先写三句话：
- Before belief: 观众看片前相信什么？
- After belief: 看完后要改信什么？
- Product-hero sentence:
这个产品让 [谁] 能 [发生什么变化]，同时 [人仍如何拥有关系/控制权]。
然后做替换测试：把最终成果换成另一种成果，故事仍成立吗？
- 成立：产品是主角，成果是 proof。
- 不成立：影片大概率在卖成果。
- 例外：产品的类别承诺本来就是成果品质（如图像生成）。这时成果可以占更多画面，但选择、迭代、控制和产品身份仍须清楚。
2. 选择叙事容器，不迷信时长
| 格式 | 适用问题 | 容器 |
|---|---|---|
| 45–90 秒 brand hero | 一个类别承诺与情绪转变 | 一个愿望 + 2–3 个因果 proof beat + payoff |
| 2–5 分钟 demo film | 复杂能力需要可信过程 | 一个真实案例从意图走到验证结果 |
| 5–10 分钟 launch film | 多个产品支柱与发布语境 | 主持人/情绪脊柱 + 同一项目的章节化展开 |
| tutorial / walkthrough | 教会具体操作 | 任务步骤与理解检查；不要冒充品牌片 |
时长取决于需要改变多少信念、提供多少证据，而不是固定 house number。
3. 把 Agent 变成可见动作
每个 proof beat 至少覆盖一条可观察循环：
意图 → 接受/委托 → 可见工作状态 → 交接/工具/动作 → 人类纠正或控制 → 持久结果 → 延续
可拍的不是隐秘推理，而是：
- 计划、角色和当前 holder；
- 进度、工具回执、共享空间变化；
- 权限请求、暂停、接管、纠正和恢复；
- 记忆如何让下一步接上，而不是重新开始。
禁止展示或伪造 chain-of-thought。不要用假进度条、假输入、假并发替代真实行为。
4. 写成因果故事
七拍不是固定模板，但每一章必须回答上一章制造的问题：
- Tension — 今天哪里孤单、碎裂、慢或不可控？
- Promise — 产品带来什么新关系或新类别？
- First proof — 用一个小循环教会观众看片语法。
- Escalation — 任务变复杂、跨猫、跨工具或跨端。
- Control — 人能看见、纠正、批准、打断或接管。
- Payoff — 成果工作，并能追溯到前面的动作。
- Return — 回到产品、关系和下一次可能性；不要停在成果 beauty shot。
如果影片有多个功能，每个功能必须成为同一因果任务里的动作，不能各拍一条广告再拼起来。
5. 镜头与运动语法
每一拍写清：观众此刻的问题 / 唯一焦点 / 状态变化 / 为什么此刻移动或切镜。
- 产品世界是视觉脊柱。 Thread、角色、工具、workspace、权限、纠错与延续保持空间连续性。
- 一拍一件事。 同时高亮三个面板等于没有焦点。
- Establish → focus → settle。 先定位，再揭示变化，最后给观众读懂的时间。
- 主体先动，镜头后动。 优先 UI 状态、对象、布局、人物和真实动作；镜头只为注意力、亲密、尺度或发现服务。
- 在意义变化处切。 接球、holder 变化、工具返回、纠正落地、proof 出现都是天然切点。
- 用连续性跨表面。 位置/形状/动作 match cut，或 J/L sound bridge，把 thread、workspace、浏览器和手机连成同一世界。
- 完成时稳定。 Payoff 需要笃定，不需要再推一次镜头。
What ships with it
2 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 · 178 lines · 234 tokens per session scan A 5c0052048ad5
agent-product-promo-director is a skill published in the GitHub repository zts212653/clowder-ai (2,980 stars, last pushed 2d ago), licensed MIT. It adds 234 tokens to every session and 2,764 once invoked, about $0.0012 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
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.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
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).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.