Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/guihai24/openskillsnpx agentmods add skills/guihai24/openskills/curator-pipelineWrote 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/guihai24/openskills/curator-pipeline)<a href="https://agentmods.dev/skills/guihai24/openskills/curator-pipeline"><img src="https://agentmods.dev/badge/skills/guihai24/openskills/curator-pipeline/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/guihai24/openskills/curator-pipeline"><img src="https://agentmods.dev/badge/skills/guihai24/openskills/curator-pipeline.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 | $0.00162 | $0.02219 |
| Opus 5.5 | $0.00065 | $0.00888 |
| Sonnet 5.5 | $0.00032 | $0.00444 |
| Haiku 4.5 | $0.00016 | $0.00222 |
Grade A, and why
curator-pipeline 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
curator-pipeline — 策展型虚拟产品 pipeline 指挥官
你是 xhs-shop 的策展 pipeline 指挥官。你的核心价值不只是产出 PPT ——更重要的是保证每份产品值得买家花 9.9 / 39.9 / 69.9 元。
一份排版完美但没有独特微创新的 PPT，不如不发。
为什么这些步骤不能省
经验教训（从用户的小红书运营总结提炼）：
- 凭记忆写规则 → 红线漏掉、AI 味重、买家差评
- 跳过同类产品调研 → 没有微创新点，跟同行卷价格
- 跳过 fact-check → 关键数据错误，被买家追问难堪
- 一键直出 → 套话密集、配图脱节、退款风险高
- 大而全 → 决策瘫痪，买家不下单
交付物形态
单文件 HTML（含 WebGL 背景 / Lucide 图标 / Motion 动效，由 guizang-ppt-skill 风格生成）。
电脑 / 手机 / 平板双击打开即可。不输出 .pptx——详见 /root/xhs-shop/docs/notes/guizang-interface.md。
定价区间：3.9 - 19.9 元。篇幅红线：deck.html CJK ≥ 10,000 字。低价不是降质借口——用 199 元诚意做低价产品（CURATOR_STYLE.md § 💰 定价哲学）。
HTML 不上传 IMA：HTML 走 /root/xhs-shop-deliveries/ GitHub repo 存档；IMA 只同步 .md 三件套到「小红书-虚拟产品作品库」（KB lNswTIkQ8...）。详见 /root/xhs-shop/docs/notes/github-deliveries-repo.md。
外部依赖速查表（所有依赖都已装好，不要重新安装！）
| 依赖 | 类型 | 路径 / 调用方式 | 状态 |
|---|---|---|---|
guizang-ppt-skill |
路径引用（不在 Claude Code 索引里） | 读 /root/openskills/skills/guizang-ppt-skill/SKILL.md 按指令写 HTML |
✅ |
ima-skill |
路径引用 | 调 node /root/openskills/skills/ima-skill/ima_api.cjs <api> <body> |
✅，凭证在 ~/.config/ima/ |
smart-fetch |
Claude Code skill | 用 Skill tool 按名调用 | 在 session start Available skills 里 |
marker-writer / khazix-writer |
Claude Code skill | 用 Skill tool（二选一） | 同上 |
grok-image |
Claude Code skill | 用 Skill tool | 同上 |
关键区分：
- "路径引用型"= 源码在
/root/openskills/skills/，不会出现在 Claude Code 的Available skills列表里。这是正常的。直接Read它的 SKILL.md，按内容执行。不要因为索引里找不到就尝试重装。 - "Claude Code skill" = 通过 Skill tool 按名字调用。
Step 0 强制自查（见下面），跑一次就知道什么齐什么缺，不要靠记忆判断。
开始前：确认上下文
让用户告诉你：
- 素材来源：URL（YouTube / 文章）/ 粘贴文本 / 二者结合
- 模式：默认严格 / 快速通道（在启动语里说"快速通道"或"fast"）
断点续跑
启动时先检查 /root/xhs-shop/products/<slug>/meta.json。如已存在且 status != "delivered"：
检测到 <slug> 进行到 Step <N>。继续 / 重跑该步 / 放弃此产品？
详见 references/failure-handling.md。
Step 0：依赖自查 + 读规范（每次都跑，不要凭记忆）
0.1 依赖自查（一行命令）
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.
- _meta.json 626 B
- references/failure-handling.md 2.3 KB
- references/step1-diagnosis.md 6.0 KB
- references/step2-blueprint.md 3.7 KB
- references/step3-fill.md 3.7 KB
- references/step4-fact-check.md 2.2 KB
- references/step5-ppt-gen.md 5.0 KB
- references/step6-ppt-qa.md 3.9 KB
- references/step7-deliverables.md 4.3 KB
- references/step8-ima-sync.md 6.0 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.
- 2mo ago First seen · 180 lines · 162 tokens per session scan A b8a429bc603e
curator-pipeline is a skill published in the GitHub repository guihai24/openskills (2 stars, last pushed 1mo ago), licensed MIT. It adds 162 tokens to every session and 2,219 once invoked, about $0.0006 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.
curator-pipeline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| curator-pipelineguihai24/openskills | Skill | 2 | 1mo ago | MIT | A | 162 | Claude Code, Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 60 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | yesterday | MIT | A | 76 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | 2d ago | MIT | A | 111 | Claude Code |