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 Jxin-Cai/jxin-skills --skill tech-article-writergit clone --depth 1 https://github.com/Jxin-Cai/jxin-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/jxin-cai/jxin-skills/tech-article-writer)<a href="https://agentmods.dev/skills/jxin-cai/jxin-skills/tech-article-writer"><img src="https://agentmods.dev/badge/skills/jxin-cai/jxin-skills/tech-article-writer/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/jxin-cai/jxin-skills/tech-article-writer"><img src="https://agentmods.dev/badge/skills/jxin-cai/jxin-skills/tech-article-writer.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 | $0.00115 | $0.02297 |
| Opus 5 | $0.00057 | $0.01149 |
| Sonnet 5 | $0.00023 | $0.00459 |
| Haiku 4.5 | $0.00012 | $0.00230 |
Grade A, and why
tech-article-writer 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 11d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Article Writer
面向中文技术文章的完整创作技能。文章要专业、可验证、好读，并保留作者自己的判断。不要把文章写成百科词条、产品宣传稿或模板化 AI 长文。
参考文件加载
按任务需要读取，不要一次性把所有参考文件加载进上下文：
- 新文章基础结构：article-structure.md
- 写作语言与案例原则：writing-guidelines.md
- Markdown 规范：markdown-rules.md
- 自动调研与引用：research-phase.md
- 中文 AI 模式审计：anti-ai-patterns.md
- 复杂主题动态规划：dynamic-outline.md
- 风格 profile：style-profiles/README.md
- 图片与架构图：diagram-integration.md
- 会话与用户偏好：memory-system.md
默认风格是 default-sanqi.yaml。用户要求正式、克制的技术文档风格时加载 formal-tech.yaml。
创作新文章
1. 明确任务
先从用户输入中提取：
- 主题、目标读者、发布渠道
- 写作目标与核心结论
- 期望字数、截止时间、是否需要代码/图片
- 用户提供的材料、代码、链接和事实边界
只有真正影响方案的缺口才提问。用户已给出明确要求时直接执行。
2. 选择风格
- 未指定时使用
default-sanqi.yaml。 - 用户指定 profile 时读取对应 YAML。
- 用户提供 3 篇以上历史文章并要求模仿时，先运行：
python scripts/extract_style.py \
--articles-dir <历史文章目录> \
--output <custom-profile.yaml>
提取结果是风格草稿。检查并删除偶然高频词、隐私和不应固化的表达后再使用。
3. 确认写作策略
用简短清单给出：
- 文章定位与读者
- 建议结构模式
- 预计字数与代码/图片数量
- 当前风格 profile
- 是否联网调研
用户要求直接完成时，自行检查后继续，不要把流程变成连续审批。
4. 自动调研
除非用户明确跳过，按照 research-phase.md 执行：
- 从实践者、架构师、初学者三个视角生成搜索问题。
- 使用
WebSearch搜索，使用WebFetch阅读关键原文。 - 优先官方文档、标准、论文和一线工程团队复盘。
- 建立 3-5 张高价值素材卡，保存为
<article>.materials.json。 - 关键数字和强结论至少交叉验证一次。
无法联网时说明限制，不编造引用、URL、数字或“业内共识”。
5. 选择大纲模式
- 普通教程、单一工具介绍、短篇文章：黄金五段式。
- 多子系统、方案权衡、5000 字以上或强依赖主题：按照 dynamic-outline.md 使用动态大纲。
动态大纲仍以五个根节点保持叙事节奏，但允许 2-3 层子节点。每个节点标注：摘要、预计字数、内容类型、素材卡和依赖。
先生成骨架：每个叶节点只写 1-2 句摘要。确认逻辑完整后再展开正文。
6. 创建初始版本
首次落盘后立即创建快照：
python scripts/version_manager.py \
--action snapshot \
--article-file <article.md> \
--note "初始骨架"
What ships with it
29 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.
- .tech-article-writer/sessions/2026-02-06-00-35-article-session.json 1.3 KB
- .tech-article-writer/sessions/2026-02-06-01-09-article-session.json 1.3 KB
- assets/article-template.md 2.2 KB
- evals/evals.json 2.4 KB
- references/anti-ai-patterns.md 3.1 KB
- references/article-structure.md 12 KB
- references/diagram-integration.md 18 KB
- references/dynamic-outline.md 2.7 KB
- references/markdown-rules.md 6.3 KB
- references/memory-system.md 9.1 KB
- references/research-phase.md 3.4 KB
- references/style-profiles/default-sanqi.yaml 461 B
- references/style-profiles/formal-tech.yaml 332 B
- references/style-profiles/README.md 2.1 KB
- references/writing-guidelines.md 7.5 KB
- scripts/check_article_quality.py 14 KB runs code
- scripts/convert_diagrams.py 12 KB runs code
- scripts/extract_style.py 6.3 KB runs code
- scripts/format_citations.py 4.7 KB runs code
- scripts/generate_cover_prompt.py 7.1 KB runs code
- scripts/generate_summary.py 8.0 KB runs code
- scripts/humanize_check.py 8.8 KB runs code
- scripts/record_session.py 8.8 KB runs code
- scripts/shared/__init__.py 385 B runs code
- scripts/shared/article_utils.py 1.5 KB runs code
- scripts/shared/constants.py 372 B runs code
- scripts/test_detection.py 1.1 KB runs code
- scripts/test_upgrade_features.py 5.2 KB runs code
- scripts/version_manager.py 7.0 KB runs code
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.
- 11d ago First seen · 255 lines · 115 tokens per session scan A 00e08ea64852
tech-article-writer is a skill published in the GitHub repository Jxin-Cai/jxin-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 115 tokens to every session and 2,297 once invoked, about $0.0006 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…