Borrowing it
Nothing to install: this file belongs to HWYD/ai-mind. 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/HWYD/ai-mind/main/.agents/skills/ai-mind-technical-blog/SKILL.mdgit clone --depth 1 https://github.com/HWYD/ai-mindWrote 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/hwyd/ai-mind/ai-mind-technical-blog)<a href="https://agentmods.dev/skills/hwyd/ai-mind/ai-mind-technical-blog"><img src="https://agentmods.dev/badge/skills/hwyd/ai-mind/ai-mind-technical-blog/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/hwyd/ai-mind/ai-mind-technical-blog"><img src="https://agentmods.dev/badge/skills/hwyd/ai-mind/ai-mind-technical-blog.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 | $0.00098 | $0.02383 |
| Opus 5 | $0.00049 | $0.01192 |
| Sonnet 5 | $0.00020 | $0.00477 |
| Haiku 4.5 | $0.00010 | $0.00238 |
Grade A, and why
ai-mind-technical-blog 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Mind 技术博客
围绕一个真实工程问题,写出 AI Mind 的版本演进、架构设计、核心流程、关键取舍、验证方式与当前边界。将可发表的工程复盘与版本流水账、框架教程区分开。
硬边界
- 只处理 AI Mind 技术博客,并独立核对源码、测试和版本资料后再写入文章。
- 只在用户明确要求创建、撰写或优化正式博客时写文件;只允许创建或修改
private-folder/blogs/下的 Markdown 文章。选题和大纲默认只在对话中输出。 - 不创建候选选题、内部证据、草稿副本、README、日志或其他辅助文件。优化已有文章时原地迭代,不创建“优化版”“最终版”等副本。
- 不把
private-folder/的草稿或历史文章当作实现事实来源;仅将private-folder/blogs/用于既有文章迭代和写作风格参考。 - 不把计划、推测、未实现能力或虚构的性能/业务数据写成已完成事实。文档和代码冲突时,以最新实际源码与测试为准;若核心事实无法确认,先向用户提出该问题。
资料读取与事实判定
先界定文章的版本、主题和主要工程问题,再按最小必要范围读取资料。默认以当前工作区的最新实际实现为准;Git 变更和提交用于定位演进过程与变更边界,不以是否打 tag 或是否发布作为写作前置条件,也不向文章读者暴露内部验证状态。
按以下优先级建立事实:
- 用户明确指定的版本、文章主题、已有文章和写作范围。
- 与主题直接相关的最新源码、测试、运行脚本、Git diff 与提交记录。
- 对应
specs/<version-topic>/中的spec.md、plan.md、tasks.md、acceptance.md、decisions.md、research.md与quickstart.md;用它们理解动机、约束、Non-goals 和验证设计。 - 相关
docs/adr/、docs/architecture/与.specify/memory/constitution.md;用它们确认长期边界。 docs/versions/、docs/releases/、README.md;仅用于公开叙事和术语交叉检查。- 同主题历史博客;仅用于风格、系列衔接或原文件优化。
为每个文章核心断言在工作中确认其证据:已实现、部分实现、仅设计或未确认。内部完成这份核对即可;不要把机械检查表或内部验证状态塞进正文。只有未确认事实会改变文章中心论点时才停止并向用户说明。
动笔前建立内部“论点—证据”映射:中心论点要有对应的实现或行为证据;问题和约束要能回溯到版本资料、代码或 Git 变更;每段关键代码、图或流程只服务一个明确判断。不要让代码片段承担多个未经解释的结论,也不要用一组文件名代替证据。
模式路由
选题分析
用于“分析某个版本适合写什么博客”。不要创建文章文件。输出:
- 版本真实实现摘要,以及它解决的工程问题。
- 2 至 4 个候选选题;分别说明技术价值、可用证据、叙事风险和适合的读者。
- 一个明确推荐主题及理由。
- 是否应与相邻版本合并;能形成同一因果链才建议合并,否则建议拆为系列。
- 仅列出会影响选题判断的未确认事实。
不要把“新增了哪些功能”当作选题本身。优先选择有明确矛盾、约束、方案和取舍的主题。
大纲设计
用于“根据主题整理博客大纲”。默认只在对话输出并等待用户确认。输出:
- 2 至 3 个标题候选与文章中心论点。
- 一条从问题到边界的工程叙事主线。
- 二级或三级章节结构;每节说明要回答的问题和对应证据。
- 应展示的少量代码片段及其职责。
- 是否需要真实架构图、流程图或图片占位,以及每张图应表达什么。
标题应表达工程对象与具体问题、方案或取舍;可以使用问题式标题,但不要使用夸张标题党、泛化的“深入理解”或“本版更新了什么”。让陌生读者能在开头数段理解项目背景、当前工程问题和本文结论。不要让章节按文件列表或版本号推进;每个章节标题只承担一个主题,并尽量直接表达该节的判断。
初稿写作
用于“写博客”“生成完整初稿”或用户已给出主题/大纲的场景。主题或大纲已明确时直接写作;没有时在内部完成必要的选题与大纲判断,不要求用户依次运行前两种模式。
- 核对主题、版本范围、真实实现、关键测试和设计约束。
- 以一个主要工程问题组织文章:问题背景 → 原方案与现实约束 → 架构设计 → 核心流程 → 关键实现 → 设计取舍 → 验证方式 → 当前边界。
- 读取
references/article-shell.md,在标题后插入固定开头模板,并在文章末尾插入固定结尾模板。只替换模板中的<代码版本>;除非用户明确要求,否则不得改写其他模板文字、链接或表情。 - 固定开头后立刻进入真实工程问题:用一个场景或矛盾切入,再在 1 至 3 句内给出全文核心判断,并预留能解释该判断的图片或结构图占位。不要重复模板中的项目介绍,也不要用泛泛行业背景拖慢正文。
- 若用户要求创建或保存文章,先搜索
private-folder/blogs/是否已有相同版本和主题的文章;有则原地更新,无则按blog-YYYY-MM-DD-vX.Y.Z-topic.md创建。多版本文章使用blog-YYYY-MM-DD-vX.Y.Z-vX.Y.Z-topic.md,文件名不用空格。 - 仅在用户明确要求时将初稿写入文件;否则在对话中交付 Markdown 正文。
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.
- 10d ago First seen · 110 lines · 98 tokens per session scan A 2f5b9a3fac5f
ai-mind-technical-blog is a skill published in the GitHub repository HWYD/ai-mind (19 stars, last pushed 3d ago), licensed MIT. It adds 98 tokens to every session and 2,383 once invoked, about $0.0005 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
boost-modules
Skill "boost-modules" from av/harbor, covering harbor boost custom modules, module structure, quick reference, output methods and stream text to client.
frontmcp-development
Use when building any FrontMCP server component other than a tool (for tools, use create-tool). Covers @Resource static resources and parameterized URI templates; @Prompt reusable prompts (RAG, multi-turn); @Provider singleton dependency-injection providers (database pools, API clients); @Agent autonomous LLM agents…
web-performance-reviewer
Review web frontends for performance issues by driving the rendered site through Chrome DevTools MCP — throttled performance traces, Core Web Vitals judged against thresholds, network waterfall analysis, and heap-snapshot leak checks for SPAs. Composes on top of web-static, web-sprinkles, or web-components. Strictly…
web-static
Build modern static websites using semantic HTML and CSS without external dependencies or build systems. Also owns the verification loop for such sites — drives the rendered pages through Chrome DevTools MCP (console, accessibility snapshot, viewport resize, dark/reduced-motion emulation, Lighthouse), executes the…
zcfg
Integrate zcfg (Zero Dependency Configuration Utility) into Java applications. Use when adding configuration loading, reading properties files, setting up application configuration, or integrating zcfg into a Java project. Triggers on "zcfg", "add configuration", "load properties", "application configuration with…
zcl
Add colored terminal output to Java applications using zcl (Zero-dependency Colour Logger). Use when adding colored console output, terminal logging with colors, ANSI color support, or integrating zcl into a Java project. Triggers on "zcl", "colored output", "colored logging", "terminal colors", "ANSI colors"…