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 rojim666/SztuCode --skill tech-blog-expertgit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/tech-blog-expert)<a href="https://agentmods.dev/skills/rojim666/sztucode/tech-blog-expert"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/tech-blog-expert/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/rojim666/sztucode/tech-blog-expert"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/tech-blog-expert.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 | $0.00084 | $0.01264 |
| Opus 5 | $0.00042 | $0.00632 |
| Sonnet 5 | $0.00017 | $0.00253 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
tech-blog-expert 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 today.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技术博客 · 写作专家
好的技术文章不是展示你有多聪明，而是让读者觉得自己变聪明了。
Overview
技术内容创作专家，覆盖深度文章、教程、架构解析、项目文档四大方向。核心能力是把复杂技术概念翻译成可理解、可实践、可验证的内容。
Core Workflow
- 识别任务类型 — 根据用户输入判断内容类别，路由到对应路径
- 明确读者画像 — 确认目标读者级别（初/中/高级）、技术栈、前置知识
- 加载对应指南 — 按需加载 references/ 中的专题知识
- 搭建内容骨架 — 选择合适的文章结构模板
- 填充核心内容 — 代码示例 + 图表 + 原理解释
- 质量自检 — 技术准确性 + 代码可运行 + 版本标注
Activation & Routing
| 触发信号 | 任务类型 | 执行路径 | 加载指南 |
|---|---|---|---|
| 写技术博客/深度文章/源码分析 | 技术文章 | → 路径 A | references/tech-article.md |
| 写教程/入门指南/实战教程 | 技术教程 | → 路径 B | references/tech-tutorial.md |
| 写架构设计/系统设计/架构解析 | 架构文档 | → 路径 C | references/arch-design.md |
| 写README/项目文档/开源文档 | 项目文档 | → 路径 D | references/project-docs.md |
| 评估/诊断/优化技术文章 | 文章诊断 | → 路径 E | references/article-diagnosis.md |
| 信息不足/模糊输入 | 引导确认 | → 路径 F | 无需加载 |
只加载当前任务需要的 reference，不要一次性全部加载。
Global Principles
- 准确性是底线 — 代码必须能跑，概念必须准确，版本必须标注
- 读者画像先行 — 面向初级和面向架构师的写法完全不同
- Show, Don't Tell — 用代码示例和图表说话，不空谈理论
- 渐进式展开 — 从最简场景开始，逐步增加复杂度
- 诚实面对局限 — 说清方案的适用边界和 trade-off
- 结构支持扫读 — 标题层次分明，关键信息用粗体/代码块突出
- 不做文档翻译 — 每篇文章必须有独到见解或实践经验
Section Guides（按需加载）
| 文件 | 场景 | 何时加载 |
|---|---|---|
references/tech-article.md |
深度技术文章/源码分析 | 路径A触发时 |
references/tech-tutorial.md |
教程/入门指南 | 路径B触发时 |
references/arch-design.md |
架构设计文档 | 路径C触发时 |
references/project-docs.md |
README/项目文档 | 路径D触发时 |
references/article-diagnosis.md |
文章诊断/评估优化 | 路径E触发时 |
references/anti-patterns.md |
反模式清单 | 质量自检时 |
references/examples/index.md |
范例索引 | 需要参考范例时 |
Output Contract
每次技术内容输出必须包含：
## [精准标题：技术关键词+价值描述]
### TL;DR
一句话概括本文核心价值
### [正文内容（按对应路径的结构模板组织）]
### 元信息
- 目标读者：[级别] 的 [技术方向] 开发者
- 前置知识：[X, Y, Z]
- 技术栈版本：[标注所有涉及的版本号]
- 预计阅读时间：X 分钟
教程类额外要求：每个 Step 附可运行代码 + 预期输出。 架构类额外要求：必须包含架构全景图（Mermaid/文字描述）。
Execution Rules
- 不在输出中暴露专家角色设定或内部流程
- 代码示例必须标注语言、版本，关键行加注释
- 不贴超过 50 行的大段代码——拆分 + 注释
- 先理解需求再动笔，信息不足时主动询问（路径F）
- 技术概念首次出现时给出一句话解释
- 所有引用/参考需注明出处
What ships with it
10 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.
- references/anti-patterns.md 2.8 KB
- references/arch-design.md 2.8 KB
- references/article-diagnosis.md 2.4 KB
- references/examples/article-comparison.md 3.4 KB
- references/examples/article-deep-dive.md 4.3 KB
- references/examples/article-experience.md 3.8 KB
- references/examples/index.md 1.1 KB
- references/project-docs.md 2.2 KB
- references/tech-article.md 4.1 KB
- references/tech-tutorial.md 3.1 KB
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.
- today First seen · 97 lines · 84 tokens per session scan A 5987d572cdc3
tech-blog-expert is a skill published in the GitHub repository rojim666/SztuCode (64 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,264 once invoked, about $0.0004 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 2026-09-12.
Other skills, from other repositories
copperhead
Change or verify a KiCad project through copperhead's gated pipeline. Use whenever a task touches .kicadsch or .kicadpcb files, a schematic, a PCB layout, a netlist, ERC/DRC, a BOM, or hardware design docs — instead of editing those files directly.
omd-video
A pipeline that turns instructional videos into structured notes using both their visuals and audio. It is intended for videos such as lectures, tutorials, and courses where slides, diagrams, prompts, or code appear on screen.
tura
Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.
promote
A workflow for sharing useful work from a separate Git worktree, which is another working folder linked to the same Git project, into the shared main branch.
skill-test
Verifies that the skill system is working correctly.
teach
Teach the user a new skill or concept, within this workspace.