CtrlK
BlogDocsLog inGet started
Tessl Logo

concept-diagrams

Generate flat, minimal light/dark-aware SVG diagrams as standalone HTML files, using a unified educational visual language with 9 semantic color ramps, sentence-case typography, and automatic dark mode. Best suited for educational and non-software visuals — physics setups, chemistry mechanisms, math curves, physical objects (aircraft, turbines, smartphones, mechanical watches), anatomy, floor plans, cross-sections, narrative journeys (lifecycle of X, process of Y), hub-spoke system integrations (smart city, IoT), and exploded layer views. If a more specialized skill exists for the subject (dedicated software/cloud architecture, hand-drawn sketches, animated explainers, etc.), prefer that — otherwise this skill can also serve as a general-purpose SVG diagram fallback with a clean educational look. Ships with 15 example diagrams.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

A highly actionable, well-sequenced skill body with concrete code, a validation checklist, and good reference structure for the files that exist. The main gap is progressive disclosure: it cites a templates/ directory and an examples/ directory that are not shipped in the bundle.

Suggestions

Ship the referenced templates/template.html and the examples/ directory, or remove/soften those references so every cited path resolves.

Consider moving the 9-ramp x 7-stop hex color table into a reference file (e.g. references/color-palette.md) and keeping only the class-name usage rules inline, reducing body token load.

Trim overlap between the Diagram Types section and the Quick Reference table so each subject appears with its guidance in one place.

DimensionReasoningScore

Conciseness

Dense and prescriptive — exact px rules, stroke widths, color-stop mapping, a copy-paste boilerplate and a validation checklist — with no padding explaining what SVG or HTML is. A score-2 case would include unnecessary explanation; this assumes Claude's competence and earns a 3, though the 15-row examples table and Quick Reference table partly restate the Diagram Types section.

3 / 3

Actionability

Provides fully executable, copy-paste-ready material: the exact SVG boilerplate, single-line and two-line node patterns with coordinates, the arrow-marker defs block, box-width formulas, and working Python/bash snippets. Matches the score-3 anchor of fully executable, copy-paste-ready code.

3 / 3

Workflow Clarity

A clear numbered workflow (steps 1-5) backed by a 12-item Validation Checklist to run before finalizing, plus an explicit security checkpoint for the preview server (bind 127.0.0.1, never 0.0.0.0, pick a free port). Explicit validation steps and feedback-style gating match the score-3 anchor.

3 / 3

Progressive Disclosure

Main body is a clear overview with well-signaled one-level-deep references (physical-shape-cookbook.md, infrastructure-patterns.md, dashboard-patterns.md) that all exist, but it also references templates/template.html and an examples/ directory of 15 files, neither of which is present in the bundle. Missing referenced paths and the large inline 9x7 color palette table keep it at a 2 rather than a 3.

2 / 3

Total

11

/

12

Passed

Description

100%

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

A strong, specific description that concretely states capabilities, embeds natural trigger terms across many domains, and gives explicit when-to-use and prefer-specialized-skill guidance. Its clear niche and deconfliction guidance keep conflict risk low.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and specifics — "Generate flat, minimal light/dark-aware SVG diagrams as standalone HTML files", "9 semantic color ramps", "sentence-case typography", "automatic dark mode" — plus a long enumeration of concrete subject types. Matches the score-3 anchor of listing multiple specific concrete actions rather than vague language.

3 / 3

Completeness

Clearly answers both what (generate SVG diagrams as standalone HTML) and when ("Best suited for educational and non-software visuals — ..."), plus explicit fallback and prefer-specialized-skill guidance. Has an explicit trigger/use-when clause, matching the score-3 anchor.

3 / 3

Trigger Term Quality

Embeds natural phrases users would actually say: "physics setups, chemistry mechanisms, math curves", "aircraft, turbines, smartphones, mechanical watches", "anatomy, floor plans, cross-sections", "smart city, IoT", "lifecycle of X, process of Y". Good coverage of natural terms, matching the score-3 anchor.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche (educational/non-software visuals) and explicitly directs overlapping cases to other skills (architecture-diagram, excalidraw, animation), leaving a distinct general-purpose SVG fallback. Unlikely to trigger for the wrong skill, matching the score-3 anchor.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
NousResearch/hermes-agent
Reviewed

Table of Contents

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.