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 lindixu6-hash/ai-content-workflow-skills --skill xhs-post-writergit clone --depth 1 https://github.com/lindixu6-hash/ai-content-workflow-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/lindixu6-hash/ai-content-workflow-skills/xhs-post-writer)<a href="https://agentmods.dev/skills/lindixu6-hash/ai-content-workflow-skills/xhs-post-writer"><img src="https://agentmods.dev/badge/skills/lindixu6-hash/ai-content-workflow-skills/xhs-post-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/lindixu6-hash/ai-content-workflow-skills/xhs-post-writer"><img src="https://agentmods.dev/badge/skills/lindixu6-hash/ai-content-workflow-skills/xhs-post-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 | $0.00047 | $0.01429 |
| Opus 5.5 | $0.00019 | $0.00572 |
| Sonnet 5.5 | $0.00009 | $0.00286 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
xhs-post-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 2mo 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content OS 写作引擎
本 Skill 只负责前三段:
播种(输入) → 发芽 → 成长(初稿)
第四段“修剪”由总控路由到外部 dbs-content。不要在本 Skill 内新增标题确认、编导确认或五维审核等可见节点。
总则
- 一次只推进一个阶段,用户明确指令后再进入下一阶段。
- 展示不等于写入;用户说“保存、采用、写入”后才能修改文件。
- 保留用户真实经历,不编造身份、数据、结果、采访或引用。
- 一篇只证明一个核心判断。
- 具体动作、物件、反应优先于抽象总结。
- 不用“封神、王炸、天花板、降维打击”等营销黑话。
- 不强造金句,不把每段整理成相同长度和相同节奏。
阶段一|播种(输入)
输入是用户想写的选题。
执行:
- 保留用户原始题目,不擅自换题。
- 判断平台、目标人群和用户看完后的状态变化。
- 信息不足时最多追问两个问题:
- 主要写给谁?
- 看完后希望对方知道、会做、能判断或能表达什么?
- 不在此阶段写标题、正文或完整策略。
固定输出:
# 播种
- 原始选题:
- 平台:
- 目标人群:
- 看完变化:
- 核心冲突:
回复“发芽”,生成四个不同机制的角度。
阶段二|发芽
围绕已确认的种子生成四张机制不同的芽。
机制同构
- 从选题抽出两到三条底层结构,不做关键词字面联想。
- 去历史、经济学、生物学、人类学、社会学等远领域寻找机制相同的真实案例。
- 把案例落回用户处境,形成可以服务正文的判断。
每张芽
## 01 · 【视角】:标题
🌱 种子
一个具体、可核验的事实。
🌿 关联
它如何解释当前选题。
💡 Aha
> 一句准确的人话。
质量门槛:
- 四张芽的视角和因果机制不得重复。
- 案例与选题共享因果机制,而非表面意象。
- 引用需要可核验;无法核实时不用伪数据。
- 每张芽必须改变观众怎么看、怎么做、怎么选或怎么表达。
- 每张芽最多突出一个数字。
展示四张芽后停止,等待用户选择一张或多张。不要额外生成三套编导组合。
阶段三|成长(给初稿)
成长阶段内部完成三件事,但只对用户显示一个节点:
补足真实经历 → 平台编导 → 完整初稿 V1
真实经历
优先使用当前对话和用户提供的材料。至少寻找三类信息:
- 只有用户本人能说出的动作、物件或反应。
- 一个真实决策过程或失败边界。
- 一个可拍摄、截图或核验的结果证据。
信息足够时直接继续;不足时一次只问:
关于这个选题,你有哪些真实经历或可以公开的证据?
禁止把一句经历扩写成用户没说过的人生故事。
平台路由
- 小红书:调用
../xiaohongshu-viral-director/SKILL.md,先在内部生成编导报告。 - 其他平台:沿用本 Skill 的通用口播结构,不伪装调用不存在的平台 Skill。
编导报告属于成长节点内部,不要求用户单独确认,不形成新的页面阶段。
写作参考
写作前完整读取:
references/writing_methodology.mdreferences/writing_quality_benchmarks.md
初稿要求
初稿必须同时使用:
- 原始选题。
- 用户选择的芽。
- 用户保留或标记的原句。
- 用户真实经历和证据。
- 平台编导给出的主线与内容形态。
口播开头前三句分别完成:
- 0–1 秒:最强判断、冲突或问题。
- 1–2 秒:真实结果、反应或处境。
- 2–5 秒:全篇最高价值,让观众现在就有所得。
正文默认链条:
前三句交付价值 → 真实经历 → 所选芽的事实 → 机制解释 → 可迁移判断 → 落回用户
要求:
- 相邻两句可以互相推出,不从个案突然跳到宏大结论。
- 抽象概念后立刻给具体场景。
- 每三到五秒推进一次判断、证据、反转或后果。
- 单句超过三十字时优先拆分。
- 保留一到三处自然反应、自嘲或没有完全想通的地方。
- 结尾解决正文提出的问题,不机械喊关注。
固定输出:
# 成长|初稿 V1
## 标题
标题
## 正文
完整正文
## 证据与素材
- 可拍:
- 可截图:
- 待核验:
输出完整 V1 后停止,只问:
直接修改、保存,还是进入“修剪”?
用户确认前不修改文件,也不自动进入修剪。
阶段验收
- 播种保留了用户原始选题。
- 发芽包含四个不同机制。
- 用户已经选择芽。
- 成长至少使用三处真实细节。
- 小红书内容已在内部经过平台编导。
- 前五秒已交付最高价值。
- 全文只有一个核心机制。
- 没有编造事实、数据和影响。
- 完整初稿已经单独展示。
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.
- 2mo ago First seen · 183 lines · 47 tokens per session scan A f0a4fc9141ff
xhs-post-writer is a skill published in the GitHub repository lindixu6-hash/ai-content-workflow-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,429 once invoked, about $0.0002 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 2026-08-31.
xhs-post-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xhs-post-writerlindixu6-hash/ai-content-workflow-skills | Skill | 5 | 2mo ago | MIT | A | 47 | Claude Code, Codex |
| cosyvoice-ssmlJamailar/Beav | Skill | 2.3k | yesterday | none | A | 0 | Claude Code, Codex |
| video-directorJamailar/Beav | Skill | 2.3k | yesterday | none | A | 154 | Claude Code, Codex |
| xhs-titleJamailar/Beav | Skill | 2.3k | yesterday | none | A | 105 | Claude Code, Codex |
| image-directorJamailar/Beav | Skill | 2.3k | yesterday | none | A | 0 | Claude Code, Codex |
| redclaw-style-definitionJamailar/Beav | Skill | 2.3k | yesterday | none | A | 46 | Claude Code, Codex |
| skill-creatorJamailar/Beav | Skill | 2.3k | yesterday | none | A | 46 | Codex |