Mmcp.market

markdown-mermaid-writing skill

by K-Dense-AI·K-Dense-AI/scientific-agent-skills·47k stars·MIT

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.

A100/100content scan

Is the markdown-mermaid-writing skill safe?

Clean: nothing in its files matched our rules. We read 37 files in the folder on 2026-09-28.

No findings.

Install the markdown-mermaid-writing skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.

git clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/scientific-agent-skills/skills/markdown-mermaid-writing ~/.claude/skills/markdown-mermaid-writing
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

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

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:

💡 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:

Step 2: Read the style guide

Before writing any .md file: read references/markdownstyleguide.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 — 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/mermaidstyleguide.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
  • snakecase 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

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

More skills from K-Dense-AI/scientific-agent-skills

  • AadaptyvHow 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`.
  • AaeonThis 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.
  • AalphagenomeLook up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), score variants or scan windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and build Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind variant effect prediction, or wants to prioritise or mechanistically interpret non-coding, regulatory, splicing, enhancer, promoter, or chromatin-accessibility effects of SNVs from a VCF, credible set, or region. Research use only; not a clinical tool.
  • Aanalytical-method-validationPlan, 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.
  • AanndataData 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.
  • AarborAutonomously 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.
  • AarboretoInfer 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.
  • AastropyCore Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing or debugging astronomical data analysis code with Astropy.
  • AautoskillObserve the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
  • Abenchling-integrationBenchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.
  • Abgpt-paper-searchSearch scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.
  • AbidsUse this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars, or creating BIDS derivatives.

All agent skills → · MCP servers