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 TashanGKD/tashan-writing-system --skill wechat-article-writergit clone --depth 1 https://github.com/TashanGKD/tashan-writing-systemWrote 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/tashangkd/tashan-writing-system/wechat-article-writer)<a href="https://agentmods.dev/skills/tashangkd/tashan-writing-system/wechat-article-writer"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-writing-system/wechat-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/tashangkd/tashan-writing-system/wechat-article-writer"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-writing-system/wechat-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 | $0.00098 | $0.07368 |
| Opus 5 | $0.00049 | $0.03684 |
| Sonnet 5 | $0.00020 | $0.01474 |
| Haiku 4.5 | $0.00010 | $0.00737 |
Grade A, and why
wechat-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.
This is a copy
100% identical to wechat-article-writer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 583 lines — stays where its author put it; the contents beside it link to each section on GitHub.
他山学科交叉 公众号文章写作 Skill
知识导航表（执行前必须理解的概念根）
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| D0 认知根（必读） | _内部总控/认知结构/L0_大脑总地图.md → 找文章主题对应的L1文档 |
先于一切：这篇文章的核心观点在郑总的认知结构里有没有对应的理论根？从认知结构出发写作，不凭空创作 |
| D3 规范参考 | _内部总控/认知结构/L1_系统性文档/待建维度/写作习惯与风格手册.md（暂用 _内部总控/AI思维碎片/写作习惯与风格手册.md） |
他山文章写作风格：语言/标题/结构/禁用套话 |
| D4 运行时数据 | _内部总控/认知结构/L1_系统性文档/待建维度/微信公众号发布手册.md + _内部总控/产品定义/tashan_footer/ |
排版规范（§零/§4.3/§5/§6.1）+ 底部模板 |
核心概念速查： ① 认知根先行：每篇文章都应能追溯到某个L1文档或L1.5原则，否则是「漂浮写作」 ② 他山风格 = 学术性洞见 × 可读性 × 有共鸣（不是科普，不是观点贩卖） ③ 审稿在发布前强制执行（article-proofreading），不可省略
详细参考资源
- 排版规范：
_内部总控/认知结构/L1_系统性文档/待建维度/微信公众号发布手册.md（⚠️ §零 核心原则、§4.3 底部模板、§5 发布前核查、§6.1 Python vs 直接编辑） - 写作风格：
_内部总控/认知结构/L1_系统性文档/待建维度/写作习惯与风格手册.md← Step 0 必读 - 历史文章样本：
项目群/feed-archiver/output/wechat/他山学科交叉/ - 底部模板资源：
_内部总控/产品定义/tashan_footer/ - 排版核查脚本：
C:/Temp/check_html.py（15项自动验证，完成HTML后必跑）
⚡ thin wrapper 转发（优先执行）
本 Skill 已升级为 document-pipeline 的入口。触发后立即转发，不独立执行原有 Step 1-8。
触发后立即执行：
设置 target_format = html
设置 mode = article
转发到 document-pipeline（加载其 SKILL.md，从 Stage 0 开始执行）
说明：所有写作逻辑已迁移到 document-pipeline，包括：
- 写作风格手册读取（document-pipeline Stage 1）
- 配图生成（document-pipeline Stage 5）
- HTML 转换（document-pipeline Stage 8A）
- 审稿（document-pipeline Stage 7）
本文件中 Step 0-8 保留为历史参考，不再执行。
⚙️ 文章发布后（thin wrapper 收尾步骤，CP1 修复）：
文章完成后，提示：
「📚 文章中是否包含原创洞见或新方法论（非仅梳理外部信息）？
如有，建议触发 cognitive-capture-fragment 将核心观点记录为 L2 碎片。
[记录核心洞见] [跳过，文章以信息整理为主]」
IF 用户选「记录」→ 触发 cognitive-capture-fragment
IF 用户选「跳过」→ 静默完成
Step 0：读取写作习惯与风格手册（写稿前必做）
Read: _内部总控/认知结构/L1_系统性文档/待建维度/写作习惯与风格手册.md
提取并在本次写作中执行：
1. 核心写作哲学（第一章）：换位思考 / 结论先行 / 信息密度原则
2. 语言风格禁忌（AI腔、防守修饰语、套话清单）
3. 标题写法规范（4种错误类型）
4. 与本次文章类型最相关的结构原则
⚠️ 不允许用 Step 3 中的内联摘要替代真实读取。WG 会随时间更新，
每次写作必须读最新版本。
执行模式判断（CN-004 Gap 修复）
IF 用户提供了现有草稿（粘贴了部分内容 / 说「帮我把这篇写完」「补全」「继续写」）：
→ 进入「补全模式」
→ Step 1：理解现有草稿的文章类型、核心主题、已有结构
→ Step 2：识别草稿缺失的部分（未完成的章节、缺少的结语等）
→ Step 3：以与现有内容一致的风格和语气补全缺失部分
→ Step 4-8：继续走正常流程（配图/HTML/审稿/发布）
→ 注：补全模式下不重新选择文章类型，以现有草稿的类型为准
ELSE（从零开始写新文章）：
→ 执行 Step 1 的正常流程
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.
- 11d ago First seen · 583 lines · 98 tokens per session scan A 5700a50c852f
wechat-article-writer is a skill published in the GitHub repository TashanGKD/tashan-writing-system (2 stars, last pushed 5mo ago), licensed MIT. It adds 98 tokens to every session and 7,368 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to wechat-article-writer, differing in 0 lines, and is treated as a copy.
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.