markdown-mermaid-writing

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.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/markdown-mermaid-writing/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized, actionable, and uses progressive disclosure effectively with a clear reference index and verified bundle files. Its weaknesses are some motivational padding that over-explains concepts Claude already knows, and a templates/ directory that is referenced extensively but is missing from the bundle.

Suggestions

Add the missing templates/ directory with the 9 referenced document templates (pull_request, issue, kanban, decision_record, presentation, research_paper, project_documentation, how_to_guide, status_report), or remove the templates table and references if those templates are not bundled.

Trim the 'Why text-based diagrams win' comparison table and the 'core bet' philosophy paragraph, which explain git/build-step benefits Claude already understands, to improve token efficiency.

Move the lengthy diagram-type and template tables into their respective reference files, keeping only a concise pointer in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with comparison tables, a workflow diagram, and a reference index, but it spends tokens explaining benefits Claude already knows (git diffs, build steps, the motivational 'core bet' paragraph and 'Why text-based diagrams win' table) that could be trimmed.	3 / 5
Actionability	Provides concrete, executable guidance — mandatory diagram rules (accTitle/accDescr format, 'No %%{init}', snake_case node IDs), a copy-paste radar-beta correct/incorrect example, explicit file paths to read, and a final checklist — with only minor gaps.	4 / 5
Workflow Clarity	A clear 5-step core workflow (identify type → read style guide → pick diagram type → write → commit) is sequenced with an explicit closing checklist; no destructive/batch operations require validation loops, so the minor checkpoint gaps are acceptable.	4 / 5
Progressive Disclosure	Well-structured overview with a reference index pointing one level deep to real files (markdown_style_guide.md, mermaid_style_guide.md, 24 verified diagram guides, and an example asset), but the body repeatedly references a templates/ directory and '9 document templates' that do not exist in the bundle — a real broken-reference gap.	4 / 5
	Total	15 / 20 Passed

Description

85%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is comprehensive and explicit about both capabilities and when to use the skill, with a clearly distinct niche. Its main weakness is trigger-term coverage, which leans on formal categories ('scientific document', 'visualization') rather than the everyday vocabulary users would naturally say.

Suggestions

Add natural user-facing trigger terms such as 'diagram', 'mermaid', 'README', 'documentation', and '.md' so the description matches how users actually phrase requests.

Consider adding common synonyms like 'flowchart', 'architecture diagram', or 'sequence diagram' to broaden the natural trigger surface.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — creating scientific documents/reports/analyses/visualizations, establishing text-based diagrams as the default standard, full style guides, 24 diagram type references, and 9 document templates — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' ('Comprehensive markdown and Mermaid diagram writing skill... establishes text-based diagrams as the default documentation standard') and 'when' ('Use when creating any scientific document, report, analysis, or visualization') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes some natural triggers ('scientific document, report, analysis, or visualization') but omits common terms users would actually say such as 'diagram', 'mermaid', 'README', 'documentation', or '.md', so coverage has noticeable gaps.	3 / 5
Distinctiveness Conflict Risk	The narrow 'markdown and Mermaid diagram writing' niche with 'text-based diagrams as the default documentation standard' is clearly distinct from other skills and unlikely to trigger for the wrong skill.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 26 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/markdown-mermaid-writing/SKILL.md
Commit: 1e5eeff

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.