mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs(skills): make architecture-diagram vs concept-diagrams routing explicit

Browse source 
Both skills generate SVG system diagrams, but for very different subjects
and aesthetics. The old descriptions didn't make the split clear, so an
agent loading either one couldn't confidently pick.

Changes:

- Rewrote both frontmatter descriptions to state the scope up front plus
  an explicit 'for X, use the other skill instead' pointer.
- Added a symmetric 'When to use this skill vs <other>' decision table
  to the top of each SKILL.md body, so the guidance is visible whether
  the agent is reading frontmatter or full content.
- Added architecture-diagram <-> concept-diagrams to each other's
  related_skills metadata.

Rule of thumb baked into both skills:
  software/cloud infra -> architecture-diagram
  physical / scientific / educational -> concept-diagrams
This commit is contained in:
Teknium 2026-04-16 20:30:53 -07:00 • committed by Teknium
parent 19c589a20b
commit 7d535969ff
2 changed files with 31 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

21
optional-skills/creative/concept-diagrams/SKILL.md
View file

@ -1,6 +1,6 @@
---
name: concept-diagrams
description: Generate flat, minimal SVG diagrams for explaining concepts visually — physics, chemistry, math, engineering, systems, data flows, physical objects, and anatomy. Light/dark-mode aware, self-contained HTML output, and a consistent educational visual language (inspired by clod-style diagrams). Use when the user asks to illustrate a concept, mechanism, structure, or process — physical or abstract — and wants a clean, textbook-ready visual. For strict software/infra architecture, prefer the `architecture-diagram` skill instead.
description: Generate flat, minimal light/dark-aware SVG diagrams 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 integrations (smart city, IoT), and exploded layer views. Uses 9 semantic color ramps with automatic light/dark mode and sentence-case typography. Single self-contained HTML file. Use this when the goal is explaining a concept, mechanism, or physical structure to a reader — textbook-style visuals for any domain outside software infrastructure. For software system architecture specifically (frontend/backend/database/cloud services, microservice topology, deployment diagrams), use the `architecture-diagram` skill instead — it has a darker palette and component-type color semantics tuned for software stacks.
version: 0.1.0
author: v1k22 (original PR), ported into hermes-agent
license: MIT
@ -15,17 +15,28 @@ metadata:
Generate production-quality SVG diagrams with a unified flat, minimal design system. Output is a single self-contained HTML file that renders identically in any modern browser, with automatic light/dark mode.
Use this skill when the user asks to explain or illustrate:
**When to use this skill vs `architecture-diagram`:**
| Use `concept-diagrams` for | Use `architecture-diagram` for |
|----------------------------|--------------------------------|
| Physics, chemistry, math, biology | Software system architecture |
| Physical objects (aircraft, turbines, watches, phones) | Cloud infrastructure (VPC, regions, services) |
| Anatomy, cross-sections, exploded views | Microservice / service mesh topology |
| Floor plans, narrative journeys, lifecycles | Database + API layer diagrams |
| Educational / textbook-style visuals | Security groups, message buses |
| Flat, light/dark-adaptive aesthetic | Dark-themed tech/infra aesthetic |
If in doubt: is the subject software/cloud infra? Use `architecture-diagram`. Anything else — physical, scientific, educational — this skill.
Subjects this skill handles well:
- physical objects (aircraft, turbines, watches, smartphones, cells)
- scientific mechanisms (reactions, physics setups, electrical circuits)
- processes and flows (ETL, CI/CD, workflows, narrative journeys)
- system topologies (microservices, IoT hub-spoke, grids)
- general system topologies when a textbook/educational style is preferred (smart city hub-spoke, grids)
- floor plans, exploded views, cross-sections
- quantitative charts (grouped bars, energy profiles)
For a dark-themed, Cocoon-style software architecture diagram (frontend/backend/DB/cloud/security), prefer the `architecture-diagram` skill.
## Workflow
1. Decide on the diagram type (see Diagram Types below).