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 gy910210/hermes-research-skills --skill doc-diagram-orchestrator-zhgit clone --depth 1 https://github.com/gy910210/hermes-research-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/gy910210/hermes-research-skills/doc-diagram-orchestrator-zh)<a href="https://agentmods.dev/skills/gy910210/hermes-research-skills/doc-diagram-orchestrator-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/doc-diagram-orchestrator-zh/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/gy910210/hermes-research-skills/doc-diagram-orchestrator-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/doc-diagram-orchestrator-zh.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 | $0.00132 | $0.01220 |
| Opus 5 | $0.00066 | $0.00610 |
| Sonnet 5 | $0.00026 | $0.00244 |
| Haiku 4.5 | $0.00013 | $0.00122 |
Grade A, and why
doc-diagram-orchestrator-zh 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes 适配说明
- 本 skill 现面向 Hermes 使用，优先依赖 Hermes 原生工具：
search_files、read_file、write_file、patch、session_search、delegate_task、cronjob、browser、web/search、vision。 - 若正文提到
references/...或scripts/...，优先读取当前 skill 目录下对应文件，不再依赖 Claude 专属目录结构。 - 原始 Claude
agents/openai.yaml不作为执行前提；需要并行研究、分工精读或角色评审时，改用 Hermes 的delegate_task。 - 保留原有研究方法论与产物契约，但执行层统一按 Hermes 工具体系落地。
Document Diagram Orchestrator（中文）
目标：把纯文字文稿转成“可委派绘图”的结构化任务，而不是直接让绘图器猜全文。
输入
doc_path或原始文稿内容（优先 Markdown）audience:"internal"|"external"|"academic"|"exec"（默认academic）density:"light"|"balanced"|"rich"（默认balanced）preferred_renderer: drawing skill 名称（可选）max_diagrams（默认3）
输出
diagram_slots: 适合出图的位置列表，含小节、原因、图型、优先级、落位建议diagram_specs: 可直接委派给 drawing skill 的最小绘图规格edit_plan: 说明每张图插在何处、如何和上下文衔接
工作流
- 读取文稿并先理解主线，不要一上来就画图。
- 对 Markdown 文件优先运行
python3 scripts/find_diagram_slots.py <doc_path> --top <N>获取候选出图点。 - 只保留能显著降低理解成本的位置，默认控制在
2-4张图，不要把每个小节都机械地画出来。 - 依据 diagram-selection.md 选择图型。
- 先冻结事实边界，产出
diagram_specs，再进入绘图阶段。 - 若存在明确的 drawing skill，只把
diagram_specs的最小必要信息委派给它，不要把整篇文稿原样转交。 - 若不存在 drawing skill，直接输出 Mermaid 作为回退方案。
- 依据 output-contract.md 生成图注、插图位置和正文过渡语。
选择图型
- 使用结构图：表达系统组成、分层、模块关系、backbone 与 capability stack。
- 使用流程图：表达阶段、步骤、pipeline、decision flow、从 A 到 B 的演进。
- 使用时序图：表达 user/agent/tool/platform/merchant 之间的交互与往返调用。
- 使用对比图：表达路径 A vs B、学术 vs 工业、优劣与 trade-off。
- 使用时间线：表达年份推进、阶段演化、里程碑变化。
- 使用矩阵图：表达两个维度的交叉，例如能力 x 风险、价值 x 可控性。
调用外部 Drawing Skill
- 先完成“分析与编排”，再调用绘图 skill。
- 交给绘图 skill 的内容至少包含：
diagram_typegoalsource_evidencenodesedges或lanescaptionstyle_constraints
- 明确要求绘图 skill 不要补充文中没有的实体、关系或因果。
- 若绘图结果与原文冲突，以原文为准，必要时回退 Mermaid。
质量门槛
- 让图减少认知负担，而不是把段落换一种方式重复一遍。
- 让图中每个节点都能在原文找到依据。
- 让单图默认控制在
5-9个核心节点；超过12个节点时优先拆图。 - 让一张图只表达一个主问题，不要混入结构、流程、对比三种逻辑。
- 在关系不清晰时不要强行出图。
What ships with it
3 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.
- 12d ago First seen · 76 lines · 132 tokens per session scan A 7cf207e769b5
doc-diagram-orchestrator-zh is a skill published in the GitHub repository gy910210/hermes-research-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 132 tokens to every session and 1,220 once invoked, about $0.0007 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
slides
Create, edit, review, and export native PowerPoint presentations through Kun's governed presentation workflow.
ppt-master-branding
Use when generating Lifewood-branded PDF documentation, manuals, reports, one-pagers, or presentation-style deliverables — enforces PDF-only output (no PPTX/PPT), 16:9 landscape canvas, one-topic-per-page pagination with content compression before continuation pages, hierarchical X.0/X.1 numbering, bottom-anchored…
ppt-assistant
A presentation-planning assistant that turns a topic into a complete outline and draft package for making a PowerPoint presentation.
ppt-slide-writer
A slide-by-slide writing assistant for PowerPoint presentations. It creates titles, key points, and suggestions for charts or other visuals from an existing structure.
ppt-slide-polisher
A presentation finishing assistant for PowerPoint slides. It adds speaker notes, suggests cuts, and writes transitions between slides.
ai-pptx
A presentation review assistant that examines supplied slide material and explains whether its main message is clear.