Skip to content
SkillCheatSheet Sign in

inspecting-hermes-desktop-dom

An AI agent skill from NousResearch/hermes-agent, scored 54 out of 100 by code.

54/ 100D

Code score by group

  • Spec20/20
  • Description10/20
  • Procedure3/15
  • Done criteria0/15
  • Resources8/10
  • Scripts5/8
  • Safety3/7
  • Upkeep5/5

It loses the most points in Done criteria (15), the group that checks whether there is a checklist and a step that verifies the work.

What the author says it does

Read the live Hermes desktop DOM/CSS over CDP.

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
NousResearch/hermes-agent
Folder
optional-skills/software-development/inspecting-hermes-desktop-dom
License
MIT
GitHub stars
262,839
SKILL.md lines
160
Other files
0

Add inspecting-hermes-desktop-dom to your agent

npx skills add NousResearch/hermes-agent --skill inspecting-hermes-desktop-dom

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

More skills from NousResearch/hermes-agent

  1. cloudflare-temporary-deploy

    Deploy a Worker live, no account, via wrangler --temporary.

    Verified87A
  2. hyperframes

    Render MP4/WebM videos from HTML compositions.

    Verified85A
  3. pdf

    PDF files: create, read, merge, fill, OCR, edit text.

    Verified84B
  4. auteur

    Design and build cinematic, award-level web pages.

    Verified83B
  5. setup-wizard-generator

    Generate a bash wizard guiding a human through manual setup.

    Verified83B
  6. email-inbox-triage

    Triage an inbox: prioritize threads, draft replies safely.

    Verified82B
  7. pretext

    Build creative browser demos with DOM-free text layout.

    Verified82B
  8. unreal-mcp

    Automate Unreal Engine editor scenes, actors, and renders.

    Verified82B

All skills in NousResearch/hermes-agent

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.