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 zjp1997720/zhijian-skills --skill wechat-stylergit clone --depth 1 https://github.com/zjp1997720/zhijian-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/zjp1997720/zhijian-skills/wechat-styler)<a href="https://agentmods.dev/skills/zjp1997720/zhijian-skills/wechat-styler"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/wechat-styler/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/zjp1997720/zhijian-skills/wechat-styler"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/wechat-styler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.01900 |
| Opus 5.5 | $0.00012 | $0.00760 |
| Sonnet 5.5 | $0.00006 | $0.00380 |
| Haiku 4.5 | $0.00003 | $0.00190 |
Grade A, and why
wechat-styler 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- wechat-styler — 88% identical, 265 lines differ
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeChat Styler
把已定稿或已授权排版的 Markdown 转成可评审公众号 HTML。默认保留正文并自动加入智见品牌首尾引导（默认 Flow 纸色底 GIF，SVG 为 --cta-style svg 备用）；组件改写、主题开场动画和微信编辑器注入按需加载。
分支路由
先选分支，再读取对应 reference。默认转换无需读取组件、动画或编辑器细则。
| 用户需求 | 执行分支 | 读取 |
|---|---|---|
| 公众号排版、HTML、换主题、批量转换 | 默认转换 | references/conversion-workflow.md；主题需要判断时再读 references/theme-guide.md |
| 结构化组件、丰富排版、开场动画 | 组件与动画 | 默认转换 reference + references/component-guide.md + references/svg-animation-design.md |
| 注入公众号、保存草稿、核验编辑器中的成品 | 编辑器注入 | references/opencli-injection.md + references/wechat-compatibility.md |
| 修改 Zhijian 主题视觉基线 | 主题维护 | references/zhijian-theme-baseline.md + references/theme-guide.md |
任务中出现新需求时只补读新增分支。
授权与能力边界
- 用户已授权排版且正文、主题明确时，简报选择并直接生成 HTML 预览，不重复确认。只有缺口会改变原意、关键表达方向或交付格式且无法推断时才问；先完成不受影响的部分。
- 预览生成、编辑器写入和草稿保存是不同动作。沿用会话中已有授权；没有编辑器写入或保存授权时，只交付 HTML 与核验结果。
- 某后端因能力缺失而不可用时，可以选择已授权且满足注入验收条件的后端。遇到明确的权限拒绝或安全策略拒绝时必须停止并报告，不能换工具、CDP、浏览器自动化或间接脚本绕过。
- 不修改输入 Markdown；组件分支在内存或临时文件中改写。
工作流
1. 默认转换
默认保留正文、不增加正文组件；转换器自动加入品牌开头与结尾引导（默认 Flow 生成的纸色底 GIF，--cta-style svg 切回透明内联 SVG）。开场互斥、关闭方式与素材维护见 references/brand-cta.md；每次转换读取该规则。按 references/conversion-workflow.md 选择主题与参数、运行转换并完成最小 QA。用户只给文件路径时默认使用 zhijian。
2. 组件与动画
组件分支先通过严格段落密度门，再按 component-density 在内存中改写 Markdown。默认 standard，只有用户明确要求“克制”或“丰富、激进、多用组件”时改为 restrained 或 rich。
执行时遵守：
- 金句、NOTE、WARNING 和其他组件替换对应原文，不在正文后重复同一意思。
:::compare、:::flow、:::timeline独占一行且前后留空行；矩阵对比保留 table。- 卡片只放短文本；组件数量、横向布局和完整语法按
references/component-guide.md。 - 从正文推断开场标题、副标题和不超过 3 个标签；模板选择与 SVG 技术边界按
references/svg-animation-design.md。 - 话题标签：frontmatter 没有
topics时，从正文选 3–4 个写入转换用的 frontmatter（或传--topics）：栏目/合集标签固定在首位，再加 2–3 个对准目标读者或本篇主题的话题；不用「人工智能」「AI」这类泛词，品牌或产品名只在正文确实展示该产品时使用，不超过公众号上限 10 个。用户指定标签或明确不要时照办（--topics none）。 xiaolan-terminal只在用户明确要求小蓝、智见小蓝或品牌 IP 时使用。- 生成前完成组件 reference 中的检查清单，然后运行转换与移动端视觉 QA。
What ships with it
56 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.
- agents/interface.yaml 613 B
- agents/openai.yaml 505 B
- assets/brand-cta/manifest.json 4.6 KB
- assets/brand-cta/zhijian-cta-ending.svg 40 KB
- assets/brand-cta/zhijian-cta-opening.svg 29 KB
- assets/README.md 2.5 KB
- assets/xiaolan-terminal-pixel-closed.png 124 KB
- assets/xiaolan-terminal-pixel-open.png 120 KB
- assets/xiaolan-terminal-wave-high.png 39 KB
- assets/xiaolan-terminal-wave-mid.png 39 KB
- assets/zhijian-theme-mobile-baseline.png 155 KB
- assets/zhijian-theme-version-comparison-2026-07.jpg 482 KB
- LICENSE 1.0 KB
- package-lock.json 3.5 KB
- package.json 528 B
- references/brand-cta.md 7.0 KB
- references/component-guide.md 15 KB
- references/conversion-workflow.md 7.4 KB
- references/opencli-injection.md 9.3 KB
- references/svg-animation-design.md 20 KB
- references/theme-guide.md 8.8 KB
- references/wechat-compatibility.md 3.5 KB
- references/zhijian-theme-baseline.md 7.5 KB
- scripts/brand-cta.mjs 5.4 KB runs code
- scripts/components.mjs 17 KB runs code
- scripts/content-density-audit.mjs 7.1 KB runs code
- scripts/convert.mjs 66 KB runs code
- scripts/generate-cover-animation.mjs 77 KB runs code
- scripts/generate-preview.mjs 8.8 KB runs code
- scripts/inject-to-wechat.mjs 17 KB runs code
- scripts/mobile-visual-qa.mjs 10 KB runs code
- scripts/qa-browser.mjs 1.5 KB runs code
- scripts/validate.mjs 10 KB runs code
- scripts/wechat-image-hosts.mjs 351 B runs code
- scripts/wechat-image-pipeline.mjs 7.9 KB runs code
- scripts/wechat-opencli.mjs 22 KB runs code
- scripts/wechat-publish-core.mjs 14 KB runs code
- tests/brand-cta.test.mjs 11 KB runs code
- tests/content-density-audit.test.mjs 2.4 KB runs code
- tests/cover-animation.test.mjs 20 KB runs code
- tests/fixtures/zhijian-visual-baseline.md 1.1 KB
- tests/inject-cli.test.mjs 11 KB runs code
- tests/output-contract.test.mjs 18 KB runs code
- tests/qa-browser.test.mjs 1.8 KB runs code
- tests/wechat-image-pipeline.test.mjs 5.4 KB runs code
- tests/wechat-opencli-compat.test.mjs 4.7 KB runs code
- tests/wechat-opencli.test.mjs 1.7 KB runs code
- tests/wechat-publish-core.test.mjs 4.7 KB runs code
- themes/elegant.yaml 1.0 KB
- themes/kami.yaml 1.4 KB
- themes/magazine-forest.yaml 1.4 KB
- themes/magazine-indigo.yaml 1.4 KB
- themes/magazine-ink.yaml 1.4 KB
- themes/minimal.yaml 1000 B
- themes/modern.yaml 1.0 KB
- themes/zhijian.yaml 2.3 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.
- 3d ago Changed 77985e09316c
- 24d ago Changed 7e7a828ec763
- 29d ago Changed · -180 lines · -52 tokens per session 7e840b5afb92
- 2mo ago First seen · 285 lines · 81 tokens per session scan A e4a3082de451
wechat-styler is a skill published in the GitHub repository zjp1997720/zhijian-skills (787 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 1,900 once invoked, about $0.0001 per session on Opus 5.5. 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.
wechat-styler compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wechat-stylerzjp1997720/zhijian-skills | Skill | 787 | 4d ago | MIT | A | 29 | Claude Code, Codex |
| wechat-stylerzjp1997720/wechat-styler | Skill | 25 | 3mo ago | MIT | A | 81 | Codex |
| popular-web-designsNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 23 | Claude Code, Codex |
| build-ghost-app-uiTryGhost/Ghost | Skill | 56k | yesterday | MIT | A | 45 | Claude Code, Codex |
| figmaheygen-com/hyperframes | Skill | 80k | yesterday | Apache-2.0 | A | 66 | Claude Code |
| shade-page-templatesTryGhost/Ghost | Skill | 56k | yesterday | MIT | A | 38 | Claude Code, Codex |
| shade-use-primitivesTryGhost/Ghost | Skill | 56k | yesterday | MIT | A | 37 | Claude Code, Codex |