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 wuyaojunkylin/research-digital-curation-skills --skill research-digital-curation-workflowgit clone --depth 1 https://github.com/wuyaojunkylin/research-digital-curation-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/wuyaojunkylin/research-digital-curation-skills/research-digital-curation-workflow)<a href="https://agentmods.dev/skills/wuyaojunkylin/research-digital-curation-skills/research-digital-curation-workflow"><img src="https://agentmods.dev/badge/skills/wuyaojunkylin/research-digital-curation-skills/research-digital-curation-workflow/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/wuyaojunkylin/research-digital-curation-skills/research-digital-curation-workflow"><img src="https://agentmods.dev/badge/skills/wuyaojunkylin/research-digital-curation-skills/research-digital-curation-workflow.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 | $0.00078 | $0.00604 |
| Opus 5 | $0.00039 | $0.00302 |
| Sonnet 5 | $0.00016 | $0.00121 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
research-digital-curation-workflow 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 12d 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.
What it actually says
研究型数字策展工作流
概述
这是研究型数字策展项目的总控 skill。它负责判断项目当前处于哪一层，并把工作带回“研究材料 -> 策展文本 -> 叙事结构 -> 视觉呈现 -> 原型实现 -> 方法回收”的顺序。
阶段诊断
先判断用户的问题卡在哪一层：
- 选题和对象不清楚：使用
curatorial-topic-framing。 - 研究材料存在，但还不是页面文本：使用
research-to-curatorial-copy。 - 策展文本存在，但页面结构不清楚：使用
curatorial-narrative-modules。 - 页面结构存在，但视觉语言不稳定：使用
curatorial-visual-language。 - 结构和视觉规则已确认，需要实现原型：使用
curatorial-prototype-standardization。 - 一轮工作需要记录、复盘或提炼方法：使用
curatorial-log-method-recovery。
如果多个阶段同时薄弱，从最早的薄弱阶段开始。对象、文本或结构还没有稳定时，不进入高保真视觉、动效或代码实现。
工作顺序
- 界定策展对象、目标观众、进入尺度、材料边界和阶段边界。
- 把研究材料转译成具体的策展页面文本。
- 把策展文本拆解成页面类型、模块、导航和交互层级。
- 定义视觉语言、材料身份、字体层级、图像规则和交互语法。
- 先建立一个标准原型或标准单元，再扩展到同类内容。
- 记录关键判断、放弃方向、固定规则和可复用方法。
输出
输出应包含阶段判断、下一步路径、建议调用的阶段 skill、所需输入和预期产出。如果用户要求直接做页面或写代码，但上游判断缺失，应说明缺失的判断，并引导回到对应阶段。
参考范式
《汴京十二时辰》是这一工作流的参考案例，但后续项目不必采用时辰、街道、明暗线或历史城市结构。需要把它们抽象为核心内容单元、跨单元分析页、材料层和标准单元扩展。
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.
- 12d ago First seen · 41 lines · 78 tokens per session scan A d566f691a2d3
research-digital-curation-workflow is a skill published in the GitHub repository wuyaojunkylin/research-digital-curation-skills (3 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 604 once invoked, about $0.0004 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
exhibition-outline
A template for turning an exhibition plan into a three-page presentation outline. The pages cover the theme, its explanation and visitor story, and a detailed area-by-area display plan.
exhibition-theme-brainstorm
A structured brainstorming method for creating exhibition themes, meaning the ideas and story that guide a museum, company, or institutional display. It develops themes from broad ideas, an organisation’s identity, its values, and possible visual expressions.
tender-analysis
A workflow for reviewing tender documents, which are formal project requests that describe requirements and bidding rules. It extracts project details, technical and business conditions, deadlines, scoring rules, risks, and questions for clarification.
interaction-team-deliverables
A design-delivery guide for turning an exhibition plan into instructions that an interaction-design team can implement. It covers interactive exhibits, content-management tools, user experience, visualisation, and switching between multiple visual styles.
tender-booklet-writing
A Chinese-language writing skill for explaining each page of a bid proposal booklet. A bid proposal booklet is a presentation document prepared to respond to a tender or contract request.
ppt-layout
A page-by-page layout guide for turning an exhibition plan into a presentation. It defines each slide’s purpose, text hierarchy, content, visual suggestions, and one-sentence takeaway.