New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Creating any scientific document, report, analysis

Markdown and Mermaid Writing

by K-Dense-AI · MIT license · ★ 45,977 on GitHub · updated Sep 21

Markdown and Mermaid Writing cover

Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization.

---
name: markdown-mermaid-writing
description: Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.
allowed-tools: Read Write Edit Bash
license: Apache-2.0
metadata:
  version: "1.1"
  skill-author: Clayton Young / Superior Byte Works, LLC (@borealBytes)
  skill-source: https://github.com/SuperiorByteWorks-LLC/agent-project
  skill-version: 1.0.0
  skill-contributors: Clayton Young (Superior Byte Works, LLC / @borealBytes; Author and originator); K-Dense Team (K-Dense Inc.; Integration target and community feedback)
---

# Markdown and Mermaid Writing

## Overview

This skill teaches you — and enforces a standard for — creating scientific documentation

Overview

This skill teaches you — and enforces a standard for — creating scientific documentation using markdown with embedded Mermaid diagrams as the default and canonical format.

Manual install (npx, ZIP)
Claude Codenpx skills add K-Dense-AI/scientific-agent-skills --skill markdown-mermaid-writing -g -a claude-code
Claude Code (manual)mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/K-Dense-AI/scientific-agent-skills/tar.gz/49c6e97775ea \ | tar -xz -C ~/.claude/skills --strip-components=2 scientific-agent-skills-49c6e97775ea/skills/markdown-mermaid-writing
Windows (PowerShell)New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/4e1ff04c548216361131/markdown-mermaid-writing.zip" -OutFile "$env:TEMP\markdown-mermaid-writing.zip"; Expand-Archive "$env:TEMP\markdown-mermaid-writing.zip" -DestinationPath "$HOME\.claude\skills" -Force
Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md14.5 KB
  • assets/1 file · 8.8 KB
  • references/26 files · 165.0 KB
  • templates/9 files · 86.2 KB
Read the files here
K-Dense-AI/49c6e9737 files
SKILL.md
Show the full text323 lines

Markdown and Mermaid Writing

Overview

This skill teaches you — and enforces a standard for — creating scientific documentation using markdown with embedded Mermaid diagrams as the default and canonical format.

The core bet: a relationship expressed as a Mermaid diagram inside a .md file is more valuable than any image. It is text, so it diffs cleanly in git. It requires no build step. It renders natively on GitHub, GitLab, Notion, VS Code, and any markdown viewer. It uses fewer tokens than a prose description of the same relationship. And it can always be converted to a polished image later — but the text version remains the source of truth.

"The more you get your reports and files in .md in just regular text, which mermaid is as well as being a simple 'script language'. This just helps with any downstream rendering and especially AI generated images (using mermaid instead of just long form text to describe relationships < tokens). Additionally mermaid can render along with markdown for easy use almost anywhere by humans or AI."

— Clayton Young (@borealBytes), K-Dense Discord, 2026-02-19

When to Use This Skill

Use this skill when:

  • Creating any scientific document — reports, analyses, manuscripts, methods sections
  • Writing any documentation — READMEs, how-tos, decision records, project docs
  • Producing any diagram — workflows, data pipelines, architectures, timelines, relationships
  • Generating any output that will be version-controlled — if it's going into git, it should be markdown
  • Working with any other skill — this skill defines the documentation layer that wraps every other output
  • Someone asks you to "add a diagram" or "visualize the relationship" — Mermaid first, always

Do NOT start with Python matplotlib, seaborn, or AI image generation for structural or relational diagrams. Those are Phase 2 and Phase 3 — only used when Mermaid cannot express what's needed (e.g., scatter plots with real data, photorealistic images).

🎨 The Source Format Philosophy

Why text-based diagrams win
What matters Mermaid in Markdown Python / AI Image
Git diff readable ✅ ❌ binary blob
Editable without regenerating ✅ ❌
Token efficient vs. prose ✅ smaller ❌ larger
Renders without a build step ✅ ❌ needs hosting
Parseable by AI without vision ✅ ❌
Works in GitHub / GitLab / Notion ✅ ⚠️ if hosted
Accessible (screen readers) ✅ accTitle/accDescr ⚠️ needs alt text
Convertible to image later ✅ anytime — already image
The three-phase workflow
flowchart LR
    accTitle: Three-Phase Documentation Workflow
    accDescr: Phase 1 Mermaid in markdown is always required and is the source of truth. Phases 2 and 3 are optional downstream conversions for polished output.

    p1["📄 Phase 1<br/>Mermaid in Markdown<br/>(ALWAYS — source of truth)"]
    p2["🐍 Phase 2<br/>Python Generated<br/>(optional — data charts)"]
    p3["🎨 Phase 3<br/>AI Generated Visuals<br/>(optional — polish)"]
    out["📊 Final Deliverable"]

    p1 --> out
    p1 -.->|"when needed"| p2
    p1 -.->|"when needed"| p3
    p2 --> out
    p3 --> out

    classDef required fill:#dbeafe,stroke:#2563eb,stroke-width:2px,color:#1e3a5f
    classDef optional fill:#fef9c3,stroke:#ca8a04,stroke-width:2px,color:#713f12
    classDef output fill:#dcfce7,stroke:#16a34a,stroke-width:2px,color:#14532d

    class p1 required
    class p2,p3 optional
    class out output

Phase 1 is mandatory. Even if you proceed to Phase 2 or 3, the Mermaid source stays committed.

What Mermaid can express

Mermaid covers 24 diagram types. Almost every scientific relationship fits one:

Use case Diagram type File
Experimental workflow / decision logic Flowchart references/diagrams/flowchart.md
Service interactions / API calls / messaging Sequence references/diagrams/sequence.md
Data model / schema ER diagram references/diagrams/er.md
State machine / lifecycle State references/diagrams/state.md
Project timeline / roadmap Gantt references/diagrams/gantt.md
Proportions / composition Pie references/diagrams/pie.md
System architecture (zoom levels) C4 references/diagrams/c4.md
Concept hierarchy / brainstorm Mindmap references/diagrams/mindmap.md
Chronological events / history Timeline references/diagrams/timeline.md
Class hierarchy / type relationships Class references/diagrams/class.md
User journey / satisfaction map User Journey references/diagrams/user_journey.md
Two-axis comparison / prioritization Quadrant references/diagrams/quadrant.md
Requirements traceability Requirement references/diagrams/requirement.md
Flow magnitude / resource distribution Sankey references/diagrams/sankey.md
Numeric trends / bar + line charts XY Chart references/diagrams/xy_chart.md
Component layout / spatial arrangement Block references/diagrams/block.md
Work item status / task columns Kanban references/diagrams/kanban.md
Cloud infrastructure / service topology Architecture references/diagrams/architecture.md
Multi-dimensional comparison / skills radar Radar references/diagrams/radar.md
Hierarchical proportions / budget Treemap references/diagrams/treemap.md
Binary protocol / data format Packet references/diagrams/packet.md
Git branching / merge strategy Git Graph references/diagrams/git_graph.md
Code-style sequence (programming syntax) ZenUML references/diagrams/zenuml.md
Multi-diagram composition patterns Complex Examples references/diagrams/complex_examples.md

💡 Pick the right type, not the easy one. Don't default to flowcharts for everything. A timeline beats a flowchart for chronological events. A sequence beats a flowchart for service interactions. Scan the table and match.


🔧 Core workflow

Step 1: Identify the document type

Check if a template exists before writing from scratch:

Document type Template
Pull request record templates/pull_request.md
Issue / bug / feature request templates/issue.md
Sprint / project board templates/kanban.md
Architecture decision (ADR) templates/decision_record.md
Presentation / briefing templates/presentation.md
Research paper / analysis templates/research_paper.md
Project documentation templates/project_documentation.md
How-to / tutorial templates/how_to_guide.md
Status report templates/status_report.md
Step 2: Read the style guide

Before writing any .md file: read references/markdown_style_guide.md.

Key rules to internalize:

  • One H1 per document — the title. Never more.
  • Emoji on H2 headings only — one emoji per H2, none in H3/H4
  • Cite everything — every external claim gets a footnote [^N] with full URL
  • Bold sparingly — max 2-3 bold terms per paragraph, never full sentences
  • Horizontal rule after every </details> — mandatory
  • Tables over prose for comparisons, configurations, structured data
  • Diagrams over walls of text — if it describes flow, structure, or relationships, add Mermaid
Step 3: Pick the diagram type and read its guide

Before creating any Mermaid diagram: read references/mermaid_style_guide.md.

Then open the specific type file (e.g., references/diagrams/flowchart.md) for the exemplar, tips, and copy-paste template.

Mandatory rules for every diagram:

accTitle: Short Name 3-8 Words
accDescr: One or two sentences explaining what this diagram shows.
  • No %%{init} directives — breaks GitHub dark mode
  • No inline style — use classDef only
  • One emoji per node max — at the start of the label
  • snake_case node IDs — match the label
Step 4: Write the document

Start from the template. Apply the markdown style guide. Place diagrams inline with related text — not in a separate "Figures" section.

Step 5: Commit as text

The .md file with embedded Mermaid is what gets committed. If you also generated a PNG or AI image, those are supplementary — the markdown is the source.


⚠️ Common pitfalls

Radar chart syntax (radar-beta)

WRONG:

radar
title Example
x-axis ["A", "B", "C"]
"Series" : [1, 2, 3]

CORRECT:

radar-beta
title Example
axis a["A"], b["B"], c["C"]
curve series["Series"]{1, 2, 3}
max 3
  • Use radar-beta not radar (the bare keyword doesn't exist)
  • Use axis to define dimensions, not x-axis
  • Use curve to define data series, not quoted labels with colon
  • No accTitle/accDescr — radar-beta doesn't support accessibility annotations; always add a descriptive italic paragraph above the diagram
XY Chart vs Radar confusion
Diagram Keyword Axis syntax Data syntax
XY Chart (bars/lines) xychart-beta x-axis ["Label1", "Label2"] bar [10, 20] or line [10, 20]
Radar (spider/web) radar-beta axis id["Label"] curve id["Label"]{10, 20}
Forgetting accTitle/accDescr on supported types

Only some diagram types support accTitle/accDescr. For those that don't, always place a descriptive italic paragraph directly above the code block:

Radar chart comparing three methods across five performance dimensions. Note: Radar charts do not support accTitle/accDescr.

radar-beta
...

🔗 Integration with other skills

With scientific-schematics

scientific-schematics generates AI-powered publication-quality images (PNG). Use the Mermaid diagram as the brief for the schematic:

Workflow:
1. Create the concept as Mermaid in .md (this skill — Phase 1)
2. Describe the same concept to scientific-schematics for a polished PNG (Phase 3)
3. Commit both — the .md as source, the PNG as a supplementary figure
With scientific-writing

When scientific-writing produces a manuscript, all diagrams and structural figures should use this skill's standards. The writing skill handles prose and citations; this skill handles visual structure.

Workflow:
1. Use scientific-writing to draft the manuscript
2. For every figure that shows a workflow, architecture, or relationship:
   - Replace placeholder with a Mermaid diagram following this skill's guide
3. Use scientific-schematics only for figures that truly need photorealistic/complex rendering
With literature-review

Literature review produces summaries with lots of relationship data. Use this skill to:

  • Create concept maps (Mindmap) of the literature landscape
  • Show publication timelines (Timeline or Gantt)
  • Compare methodologies (Quadrant or Radar)
  • Diagram data flows described in papers (Sequence or Flowchart)
With any skill that produces output documents

Before finalizing any document from any skill, apply this skill's checklist:

  • Does the document use a template? If so, did I start from the right one?
  • Are all diagrams in Mermaid with accTitle + accDescr?
  • No %%{init}, no inline style, only classDef?
  • Are all external claims cited with [^N]?
  • One H1, emoji on H2 only?
  • Horizontal rules after every </details>?

📚 Reference index

Style guides
Guide Path Lines What it covers
Markdown Style Guide references/markdown_style_guide.md ~733 Headings, formatting, citations, tables, Mermaid integration, templates, quality checklist
Mermaid Style Guide references/mermaid_style_guide.md ~458 Accessibility, emoji set, color classes, theme neutrality, type selection, complexity tiers
Diagram type guides (24 types)

Each file contains: production-quality exemplar, tips specific to that type, and a copy-paste template.

references/diagrams/ — architecture, block, c4, class, complex_examples, er, flowchart, gantt, git_graph, kanban, mindmap, packet, pie, quadrant, radar, requirement, sankey, sequence, state, timeline, treemap, user_journey, xy_chart, zenuml

Document templates (9 types)

templates/ — decision_record, how_to_guide, issue, kanban, presentation, project_documentation, pull_request, research_paper, status_report

Examples

assets/examples/example-research-report.md — a complete scientific research report demonstrating proper heading hierarchy, multiple diagram types (flowchart, sequence, gantt), tables, footnote citations, collapsible sections, and all style guide rules applied.


📝 Attribution

All style guides, diagram type guides, and document templates in this skill are ported from the SuperiorByteWorks-LLC/agent-project repository under the Apache-2.0 License.

This skill (as part of scientific-agent-skills) is distributed under the MIT License. The included Apache-2.0 content is compatible for downstream use with attribution retained, as preserved in the file headers throughout this skill.


[^1]: GitHub Blog. (2022). "Include diagrams in your Markdown files with Mermaid." https://github.blog/2022-02-14-include-diagrams-markdown-files-mermaid/

[^2]: Mermaid. "Mermaid Diagramming and Charting Tool." https://mermaid.js.org/

1---
2name: markdown-mermaid-writing
3description: Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.
4allowed-tools: Read Write Edit Bash
5license: Apache-2.0
6metadata:
7 version: "1.1"
8 skill-author: Clayton Young / Superior Byte Works, LLC (@borealBytes)
9 skill-source: https://github.com/SuperiorByteWorks-LLC/agent-project
10 skill-version: 1.0.0
11 skill-contributors: Clayton Young (Superior Byte Works, LLC / @borealBytes; Author and originator); K-Dense Team (K-Dense Inc.; Integration target and community feedback)
12---
13 
14# Markdown and Mermaid Writing
15 
16## Overview
17 
18This skill teaches you — and enforces a standard for — creating scientific documentation
19using **markdown with embedded Mermaid diagrams as the default and canonical format**.
20 
21The core bet: a relationship expressed as a Mermaid diagram inside a `.md` file is more
22valuable than any image. It is text, so it diffs cleanly in git. It requires no build step.
23It renders natively on GitHub, GitLab, Notion, VS Code, and any markdown viewer. It uses
24fewer tokens than a prose description of the same relationship. And it can always be
25converted to a polished image later — but the text version remains the source of truth.
26 
27> "The more you get your reports and files in .md in just regular text, which mermaid is
28> as well as being a simple 'script language'. This just helps with any downstream rendering
29> and especially AI generated images (using mermaid instead of just long form text to
30> describe relationships < tokens). Additionally mermaid can render along with markdown for
31> easy use almost anywhere by humans or AI."
32>
33> — Clayton Young (@borealBytes), K-Dense Discord, 2026-02-19
34 
35## When to Use This Skill
36 
37Use this skill when:
38 
39- Creating **any scientific document** — reports, analyses, manuscripts, methods sections
40- Writing **any documentation** — READMEs, how-tos, decision records, project docs
41- Producing **any diagram** — workflows, data pipelines, architectures, timelines, relationships
42- Generating **any output that will be version-controlled** — if it's going into git, it should be markdown
43- Working with **any other skill** — this skill defines the documentation layer that wraps every other output
44- Someone asks you to "add a diagram" or "visualize the relationship" — Mermaid first, always
45 
46Do NOT start with Python matplotlib, seaborn, or AI image generation for structural or relational diagrams.
47Those are Phase 2 and Phase 3 — only used when Mermaid cannot express what's needed (e.g., scatter plots with real data, photorealistic images).
48 
49## 🎨 The Source Format Philosophy
50 
51### Why text-based diagrams win
52 
53| What matters | Mermaid in Markdown | Python / AI Image |
54| ----------------------------- | :-----------------: | :---------------: |
55| Git diff readable | ✅ | ❌ binary blob |
56| Editable without regenerating | ✅ | ❌ |
57| Token efficient vs. prose | ✅ smaller | ❌ larger |
58| Renders without a build step | ✅ | ❌ needs hosting |
59| Parseable by AI without vision | ✅ | ❌ |
60| Works in GitHub / GitLab / Notion | ✅ | ⚠️ if hosted |
61| Accessible (screen readers) | ✅ accTitle/accDescr | ⚠️ needs alt text |
62| Convertible to image later | ✅ anytime | — already image |
63 
64### The three-phase workflow
65 
66```mermaid
67flowchart LR
68 accTitle: Three-Phase Documentation Workflow
69 accDescr: Phase 1 Mermaid in markdown is always required and is the source of truth. Phases 2 and 3 are optional downstream conversions for polished output.
70 
71 p1["📄 Phase 1<br/>Mermaid in Markdown<br/>(ALWAYS — source of truth)"]
72 p2["🐍 Phase 2<br/>Python Generated<br/>(optional — data charts)"]
73 p3["🎨 Phase 3<br/>AI Generated Visuals<br/>(optional — polish)"]
74 out["📊 Final Deliverable"]
75 
76 p1 --> out
77 p1 -.->|"when needed"| p2
78 p1 -.->|"when needed"| p3
79 p2 --> out
80 p3 --> out
81 
82 classDef required fill:#dbeafe,stroke:#2563eb,stroke-width:2px,color:#1e3a5f
83 classDef optional fill:#fef9c3,stroke:#ca8a04,stroke-width:2px,color:#713f12
84 classDef output fill:#dcfce7,stroke:#16a34a,stroke-width:2px,color:#14532d
85 
86 class p1 required
87 class p2,p3 optional
88 class out output
89```
90 
91**Phase 1 is mandatory.** Even if you proceed to Phase 2 or 3, the Mermaid source stays committed.
92 
93### What Mermaid can express
94 
95Mermaid covers 24 diagram types. Almost every scientific relationship fits one:
96 
97| Use case | Diagram type | File |
98| -------------------------------------------- | ---------------- | ---------------------------------------------------- |
99| Experimental workflow / decision logic | Flowchart | `references/diagrams/flowchart.md` |
100| Service interactions / API calls / messaging | Sequence | `references/diagrams/sequence.md` |
101| Data model / schema | ER diagram | `references/diagrams/er.md` |
102| State machine / lifecycle | State | `references/diagrams/state.md` |
103| Project timeline / roadmap | Gantt | `references/diagrams/gantt.md` |
104| Proportions / composition | Pie | `references/diagrams/pie.md` |
105| System architecture (zoom levels) | C4 | `references/diagrams/c4.md` |
106| Concept hierarchy / brainstorm | Mindmap | `references/diagrams/mindmap.md` |
107| Chronological events / history | Timeline | `references/diagrams/timeline.md` |
108| Class hierarchy / type relationships | Class | `references/diagrams/class.md` |
109| User journey / satisfaction map | User Journey | `references/diagrams/user_journey.md` |
110| Two-axis comparison / prioritization | Quadrant | `references/diagrams/quadrant.md` |
111| Requirements traceability | Requirement | `references/diagrams/requirement.md` |
112| Flow magnitude / resource distribution | Sankey | `references/diagrams/sankey.md` |
113| Numeric trends / bar + line charts | XY Chart | `references/diagrams/xy_chart.md` |
114| Component layout / spatial arrangement | Block | `references/diagrams/block.md` |
115| Work item status / task columns | Kanban | `references/diagrams/kanban.md` |
116| Cloud infrastructure / service topology | Architecture | `references/diagrams/architecture.md` |
117| Multi-dimensional comparison / skills radar | Radar | `references/diagrams/radar.md` |
118| Hierarchical proportions / budget | Treemap | `references/diagrams/treemap.md` |
119| Binary protocol / data format | Packet | `references/diagrams/packet.md` |
120| Git branching / merge strategy | Git Graph | `references/diagrams/git_graph.md` |
121| Code-style sequence (programming syntax) | ZenUML | `references/diagrams/zenuml.md` |
122| Multi-diagram composition patterns | Complex Examples | `references/diagrams/complex_examples.md` |
123 
124> 💡 **Pick the right type, not the easy one.** Don't default to flowcharts for everything.
125> A timeline beats a flowchart for chronological events. A sequence beats a flowchart for
126> service interactions. Scan the table and match.
127 
128---
129 
130## 🔧 Core workflow
131 
132### Step 1: Identify the document type
133 
134Check if a template exists before writing from scratch:
135 
136| Document type | Template |
137| ------------------------------ | ----------------------------------------------- |
138| Pull request record | `templates/pull_request.md` |
139| Issue / bug / feature request | `templates/issue.md` |
140| Sprint / project board | `templates/kanban.md` |
141| Architecture decision (ADR) | `templates/decision_record.md` |
142| Presentation / briefing | `templates/presentation.md` |
143| Research paper / analysis | `templates/research_paper.md` |
144| Project documentation | `templates/project_documentation.md` |
145| How-to / tutorial | `templates/how_to_guide.md` |
146| Status report | `templates/status_report.md` |
147 
148### Step 2: Read the style guide
149 
150Before writing any `.md` file: read `references/markdown_style_guide.md`.
151 
152Key rules to internalize:
153 
154- **One H1 per document** — the title. Never more.
155- **Emoji on H2 headings only** — one emoji per H2, none in H3/H4
156- **Cite everything** — every external claim gets a footnote `[^N]` with full URL
157- **Bold sparingly** — max 2-3 bold terms per paragraph, never full sentences
158- **Horizontal rule after every `</details>`** — mandatory
159- **Tables over prose** for comparisons, configurations, structured data
160- **Diagrams over walls of text** — if it describes flow, structure, or relationships, add Mermaid
161 
162### Step 3: Pick the diagram type and read its guide
163 
164Before creating any Mermaid diagram: read `references/mermaid_style_guide.md`.
165 
166Then open the specific type file (e.g., `references/diagrams/flowchart.md`) for the exemplar, tips, and copy-paste template.
167 
168Mandatory rules for every diagram:
169 
170```
171accTitle: Short Name 3-8 Words
172accDescr: One or two sentences explaining what this diagram shows.
173```
174 
175- **No `%%{init}` directives** — breaks GitHub dark mode
176- **No inline `style`** — use `classDef` only
177- **One emoji per node max** — at the start of the label
178- **`snake_case` node IDs** — match the label
179 
180### Step 4: Write the document
181 
182Start from the template. Apply the markdown style guide. Place diagrams inline with related text — not in a separate "Figures" section.
183 
184### Step 5: Commit as text
185 
186The `.md` file with embedded Mermaid is what gets committed. If you also generated a PNG or AI image, those are supplementary — the markdown is the source.
187 
188---
189 
190## ⚠️ Common pitfalls
191 
192### Radar chart syntax (`radar-beta`)
193 
194**WRONG:**
195```mermaid
196radar
197title Example
198x-axis ["A", "B", "C"]
199"Series" : [1, 2, 3]
200```
201 
202**CORRECT:**
203```mermaid
204radar-beta
205title Example
206axis a["A"], b["B"], c["C"]
207curve series["Series"]{1, 2, 3}
208max 3
209```
210 
211- **Use `radar-beta`** not `radar` (the bare keyword doesn't exist)
212- **Use `axis`** to define dimensions, **not** `x-axis`
213- **Use `curve`** to define data series, **not** quoted labels with colon
214- **No `accTitle`/`accDescr`** — radar-beta doesn't support accessibility annotations; always add a descriptive italic paragraph above the diagram
215 
216### XY Chart vs Radar confusion
217 
218| Diagram | Keyword | Axis syntax | Data syntax |
219| ------- | ------- | ----------- | ----------- |
220| **XY Chart** (bars/lines) | `xychart-beta` | `x-axis ["Label1", "Label2"]` | `bar [10, 20]` or `line [10, 20]` |
221| **Radar** (spider/web) | `radar-beta` | `axis id["Label"]` | `curve id["Label"]{10, 20}` |
222 
223### Forgetting `accTitle`/`accDescr` on supported types
224 
225Only some diagram types support `accTitle`/`accDescr`. For those that don't, always place a descriptive italic paragraph directly above the code block:
226 
227> _Radar chart comparing three methods across five performance dimensions. Note: Radar charts do not support accTitle/accDescr._
228 
229```mermaid
230radar-beta
231...
232```
233 
234---
235 
236## 🔗 Integration with other skills
237 
238### With `scientific-schematics`
239 
240`scientific-schematics` generates AI-powered publication-quality images (PNG). Use the Mermaid diagram as the **brief** for the schematic:
241 
242```
243Workflow:
2441. Create the concept as Mermaid in .md (this skill — Phase 1)
2452. Describe the same concept to scientific-schematics for a polished PNG (Phase 3)
2463. Commit both — the .md as source, the PNG as a supplementary figure
247```
248 
249### With `scientific-writing`
250 
251When `scientific-writing` produces a manuscript, all diagrams and structural figures should use this skill's standards. The writing skill handles prose and citations; this skill handles visual structure.
252 
253```
254Workflow:
2551. Use scientific-writing to draft the manuscript
2562. For every figure that shows a workflow, architecture, or relationship:
257 - Replace placeholder with a Mermaid diagram following this skill's guide
2583. Use scientific-schematics only for figures that truly need photorealistic/complex rendering
259```
260 
261### With `literature-review`
262 
263Literature review produces summaries with lots of relationship data. Use this skill to:
264 
265- Create concept maps (Mindmap) of the literature landscape
266- Show publication timelines (Timeline or Gantt)
267- Compare methodologies (Quadrant or Radar)
268- Diagram data flows described in papers (Sequence or Flowchart)
269 
270### With any skill that produces output documents
271 
272Before finalizing any document from any skill, apply this skill's checklist:
273 
274- [ ] Does the document use a template? If so, did I start from the right one?
275- [ ] Are all diagrams in Mermaid with `accTitle` + `accDescr`?
276- [ ] No `%%{init}`, no inline `style`, only `classDef`?
277- [ ] Are all external claims cited with `[^N]`?
278- [ ] One H1, emoji on H2 only?
279- [ ] Horizontal rules after every `</details>`?
280 
281---
282 
283## 📚 Reference index
284 
285### Style guides
286 
287| Guide | Path | Lines | What it covers |
288| ----------------------- | ------------------------------------------- | ----- | -------------------------------------------------- |
289| Markdown Style Guide | `references/markdown_style_guide.md` | ~733 | Headings, formatting, citations, tables, Mermaid integration, templates, quality checklist |
290| Mermaid Style Guide | `references/mermaid_style_guide.md` | ~458 | Accessibility, emoji set, color classes, theme neutrality, type selection, complexity tiers |
291 
292### Diagram type guides (24 types)
293 
294Each file contains: production-quality exemplar, tips specific to that type, and a copy-paste template.
295 
296`references/diagrams/` — architecture, block, c4, class, complex\_examples, er, flowchart, gantt, git\_graph, kanban, mindmap, packet, pie, quadrant, radar, requirement, sankey, sequence, state, timeline, treemap, user\_journey, xy\_chart, zenuml
297 
298### Document templates (9 types)
299 
300`templates/` — decision\_record, how\_to\_guide, issue, kanban, presentation, project\_documentation, pull\_request, research\_paper, status\_report
301 
302### Examples
303 
304`assets/examples/example-research-report.md` — a complete scientific research report demonstrating proper heading hierarchy, multiple diagram types (flowchart, sequence, gantt), tables, footnote citations, collapsible sections, and all style guide rules applied.
305 
306---
307 
308## 📝 Attribution
309 
310All style guides, diagram type guides, and document templates in this skill are ported from the `SuperiorByteWorks-LLC/agent-project` repository under the Apache-2.0 License.
311 
312- **Source**: https://github.com/SuperiorByteWorks-LLC/agent-project
313- **Author**: Clayton Young / Superior Byte Works, LLC (@borealBytes)
314- **License**: Apache-2.0
315 
316This skill (as part of scientific-agent-skills) is distributed under the MIT License. The included Apache-2.0 content is compatible for downstream use with attribution retained, as preserved in the file headers throughout this skill.
317 
318---
319 
320[^1]: GitHub Blog. (2022). "Include diagrams in your Markdown files with Mermaid." https://github.blog/2022-02-14-include-diagrams-markdown-files-mermaid/
321 
322[^2]: Mermaid. "Mermaid Diagramming and Charting Tool." https://mermaid.js.org/
323 
View all files on GitHub →

Details

Updated
Sep 21, 2026
License
MIT
Stars on the repo
★ 45,977
Checked
Source
K-Dense-AI/scientific-agent-skills ↗
Creator
K-Dense-AI · 168 listings
View creator

Similar skills

See all →
SkillCreate stunning, animation-rich HTML presentationsFrontend slideszarazhangrui/frontend-slides · by zarazhangruiCreate stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.★ 30.3k GitHub starsSkillCreate professional, dark-themed SVG diagrams of any typeDiagram GeneratorJimLiu/baoyu-skills · by JimLiuCreate professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.★ 26.6k GitHub starsSkillGenerate self-contained HTML visual explanations for systemsVisual explainernicobailon/visual-explainer · by nicobailonGenerate self-contained HTML visual explanations for systems, code changes, plans, data, and technical concepts. Use for diagrams, architecture overviews, diff or plan reviews, project recaps, comparison tables, slide decks, animated explainers, and other visual explanations.★ 10.2k GitHub starsSkillHTML PPT Studio — author professional static HTMLhtml-ppt — HTML PPT Studiolewislulu/html-ppt-skill · by lewisluluHTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片", "演讲稿", "做一份 PPT", "做一份 slides", a reveal-style HTML deck, a 小红书 图文, or any kind of multi-slide pitch/report/sharing document that should look tasteful and be usable with keyboard navigation. Triggers include keywords like "presentation", "ppt", "slides", "deck", "keynote", "reveal", "slideshow", "幻灯片", "演讲稿", "分享稿", "小红书图文", "talk slides", "pitch deck", "tech sharing", "technical presentation".★ 8.6k GitHub starsSkillProfessional logo and brand-mark designLogo designkaankiziltug/logo-design-skill · by kaankiziltugProfessional logo and brand-mark design, from brief to production files. Guides discovery and the design brief, concept generation, choosing a mark type (wordmark, monogram, letterform, pictorial, abstract, emblem, mascot, combination), building clean geometric SVG logos, optical refinement, colour and typography, testing (16 px, one-colour, reversed, shelf test), client presentation, delivery variants and brand guidelines. Includes a searchable library of 1,400+ real-world SVG logos classified by type, technique, geometry and industry, plus scripts that audit SVGs and generate test sheets, presentation boards and export variants. Use this skill whenever the user wants a logo, logotype, wordmark, monogram, brand mark, symbol, app icon or favicon designed, redesigned, refreshed, critiqued or compared; asks for logo ideas or concepts; needs a design brief, logo guidelines, lockups or an identity system; or mentions branding a new company, product, app or project — even if they don't say the word "logo".★ 2.8k GitHub starsSkillDraws a code change or partPR Lenscoldteadotai/pr-lens · by coldteadotaiWHAT: Draws a code change or part of a codebase as an animated architecture or data-flow diagram, on its own or in a pull request. WHEN: asked to diagram, visualise or explain a change or a system, or when a pull request should carry a diagram. KEYWORDS: PR Lens, diagram, architecture, data flow, visualise, visualize, pull request★ 1.9k GitHub stars

More from K-Dense-AI

SkillHow to use the Adaptyv Bio Foundry API and Python SDKK-Dense-AI/scientific-agent-skills · by K-Dense-AIHow to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.★ 46k GitHub starsSkillAeon Time Series Machine LearningK-Dense-AI/scientific-agent-skills · by K-Dense-AIThis skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.★ 46k GitHub starsSkillPlan, execute, and document validation, verificationAnalytical method validationK-Dense-AI/scientific-agent-skills · by K-Dense-AIPlan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>, ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. Use for HPLC, LC-MS/MS, GC, CE, ICP-MS, dissolution, qNMR, qPCR, NIR, and ligand binding or cell-based assays whenever the question is whether a procedure is fit for its intended purpose. Triggers include "method validation", "analytical method validation", "AMV", "validation protocol", "acceptance criteria", "linearity", "reportable range", "accuracy and precision", "repeatability", "intermediate precision", "recovery", "LOD", "LOQ", "detection limit", "quantitation limit", "specificity", "robustness", "method transfer", "method comparison", "Deming", "Passing-Bablok", "Bland-Altman", "equivalence testing", "OOS investigation", "ICH Q2", "Q2(R2)", "Q14", "USP 1225", "ICH M10", "incurred sample reanalysis", "ISR", "CLSI EP", and any request to show that an assay works.★ 46k GitHub starsSkillData structure for annotated matrices in single-cellAnndataK-Dense-AI/scientific-agent-skills · by K-Dense-AIData structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.★ 46k GitHub starsSkillAutonomously improve a real artifact against an objectiveArbor — Autonomous Optimization via Hypothesis Tree RefinementK-Dense-AI/scientific-agent-skills · by K-Dense-AIAutonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.★ 46k GitHub starsSkillInfer gene regulatory networks from gene expression dataArboretoK-Dense-AI/scientific-agent-skills · by K-Dense-AIInfer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.★ 46k GitHub stars