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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zts212653/clowder-ainpx agentmods add skills/zts212653/clowder-ai/writing-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/zts212653/clowder-ai/writing-skills)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/writing-skills"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/writing-skills/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/writing-skills"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/writing-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 64 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 65 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 66 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00144 | $0.03910 |
| Opus 5 | $0.00072 | $0.01955 |
| Sonnet 5 | $0.00029 | $0.00782 |
| Haiku 4.5 | $0.00014 | $0.00391 |
Grade A, and why
writing-skills scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 小改 skill 直接 push 不跑检查 | 可能把 raw first-party `curl localhost` 主路径带进 main，下一只合 PR 的猫才踩雷 | 跑 `check:skills:references` + `check:skills:surfaces` 与 claim 对应的定向测试；按五轴风险决定是否升 full gate | How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skills — Skill & MCP 元技能
铁律：软硬同重
Skill 和 MCP 的质量 = 代码的质量。 写得烂的 skill/MCP description → 猫选错工具 → 用户体验差。 写 skill = 为未来的猫写路标；写 MCP description = 为模型写路由信号。两者都不是日记。
价值门禁：别教聪明猫写 for 循环
写 skill 前先判定：它是不是在给聪明 agent 复述训练集里已经很强的通用知识？
好 skill 不是教聪明猫写 for 循环；好 skill 是把领域 know-how、历史坑、证据标准、行为刹车放到猫会自然经过的位置。
必须至少命中一项，否则不要写成 skill：
| 价值来源 | 适合写什么 | 不要写什么 |
|---|---|---|
| 领域 know-how | 项目/行业/供应商特有规则、版本坑、真相源路径 | React/pytest/for-loop 这类通用教程 |
| 历史坑 | 家里真实踩过的错误、rationalization、反例库 | 作者想象的最佳实践 |
| 证据标准 | 要读哪些源、怎样证明完成、何时升级 | “要认真”“要高质量” |
| 行为刹车 | 模型会但压力下会跳过的动作，如 TDD、查证、review、球权 | 模型本来稳定会做的步骤 |
| 认知路径 | 让猫想到该用的工具/MCP/真相源 | 把现成 docs 复制进上下文 |
更完整判据见 writing-skills/cat-cafe-skill-quality-principles.md。
载体与寿命自问
创建或扩写 skill 前，再回答两组问题：
- 这条信息忘了以后，必须每轮付代价，还是任务出现时按需再读即可？ 跨压缩持续约束才进 L0；单轮反射进 staging；runtime 专属执行边界进对应 harness；任务方法进 skill；事实契约留 docs/code；可机械判定的交给 test/lint/guard。
- 价值缺口来自哪里，产物在做什么？ 区分私有/项目知识、公开但新近知识、持续变化的外部事实、模型行为缺口；再区分知识 payload、resolver/probe、治理边界、结果 verifier。只会自然过期的 payload / 行为代偿需要 keep/tune/sunset 信号；resolver、治理与 verifier 不因模型变强就自动退役。
不要给全部 skill 建 expiry registry 或机械到期日。不确定效用且有明确 consumer 时，复用 F192 eval 的 keep/tune/sunset 闭环。
开工前：先看范本再动手
不要凭空写。 先读一个同类型的好例子，理解家里的风格和标准。
| 我要写... | 先看这个范本 | 为什么好 |
|---|---|---|
| 流程型 skill | cat-cafe-skills/tdd/SKILL.md |
清晰的分步流程 + 红绿重构纪律 |
| 调试型 skill | cat-cafe-skills/debugging/SKILL.md |
根因定位方法论 + 假设验证 |
| 门禁型 skill | cat-cafe-skills/quality-gate/SKILL.md |
检查清单 + 硬门禁 + 下一步 |
| MCP tool | ../.cat-cafe-shared-refs/mcp-tool-description-standard.md 的好/差对比 |
四项路由契约 + 有证据才写 Gotcha |
写 MCP tool 前还要 grep 家里现有同类 tool 的 description，保持风格一致。
四份必读文档的 T0 精华
以下是核心原则。详细展开、案例拆解、模板见对应 ref 文件。
T0-0：Skill 价值门禁（Clowder AI）
Skill 不是知识垃圾桶。写之前先选择正确载体：
| 需求 | 载体 |
|---|---|
| 通用语法/API，模型已经知道 | 不写；按需查官方文档 |
| 时效性强的外部事实 | Reference + 明确“必须查官方源” |
| 项目特有流程/历史坑/证据标准 | Skill |
| 高风险且可机械检测的行为 | Hook / runtime guard，不靠 prompt |
| 工具可发现性问题 | Skill + MCP description + system prompt 路标 |
What ships with it
7 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.
- 9d ago Changed · -1 lines 14d6e836e040
- 13d ago First seen · 228 lines · 144 tokens per session scan A 3ad161c5a14f
writing-skills is a skill published in the GitHub repository zts212653/clowder-ai (2,980 stars, last pushed 3d ago), licensed MIT. It adds 144 tokens to every session and 3,910 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…