X Tutup
Skip to content

feat: improve skill review scores for browser-use and remote-browser#4310

Open
popey wants to merge 1 commit intobrowser-use:mainfrom
popey:improve/skill-review-v2
Open

feat: improve skill review scores for browser-use and remote-browser#4310
popey wants to merge 1 commit intobrowser-use:mainfrom
popey:improve/skill-review-v2

Conversation

@popey
Copy link

@popey popey commented Mar 9, 2026

Hullo 👋

I ran your skills through tessl skill review at work and found some targeted improvements.

score_card

Here's the before/after:

Skill Before After Change
browser-use 89% 96% +7%
remote-browser 81% 96% +15%
Changes made

browser-use skill:

  • Added a compact "Quick Reference" section after prerequisites with the 6 most common commands, improving progressive disclosure so agents can act faster without reading the full reference
  • Removed the redundant "Essential Commands" section that duplicated content already covered in both the Quick Reference and the detailed Commands section

remote-browser skill:

  • Expanded the frontmatter description with additional natural trigger terms (browse the web, open a webpage, click buttons, web automation, headless browser) and context (CI or cloud VM environments) to improve skill selection accuracy
  • Removed the redundant "Essential Commands" section that duplicated content from the Core Workflow and detailed Commands sections
  • Removed a minor redundant prose line ("Commands use the cloud browser:") before the Core Workflow code block

Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.

If you want to run reviews, evals and optimizations yourself, just npm install @tessl/cli then run tessl skill review path/to/your/SKILL.md, and click here to find out more.

Thanks in advance 🙏


Summary by cubic

Improves browser-use and remote-browser skill docs for faster agent use and better skill selection. Adds a quick reference and removes duplication, raising review scores to 96%.

  • New Features

    • browser-use: Added a compact Quick Reference with six common commands after prerequisites.
  • Refactors

    • Removed redundant Essential Commands sections in both skills.
    • remote-browser: Expanded frontmatter description with natural trigger terms and CI/cloud VM context.
    • remote-browser: Removed a redundant line before the Core Workflow.

Written for commit 0790587. Summary will update on new commits.

Hullo @MagMueller 👋

I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the before/after:

| Skill | Before | After | Change |
|-------|--------|-------|--------|
| browser-use | 89% | 96% | +7% |
| remote-browser | 81% | 96% | +15% |

<details>
<summary>Changes made</summary>

**browser-use skill:**
- Added a compact "Quick Reference" section after prerequisites with the 6 most common commands, improving progressive disclosure so agents can act faster without reading the full reference
- Removed the redundant "Essential Commands" section that duplicated content already covered in both the Quick Reference and the detailed Commands section

**remote-browser skill:**
- Expanded the frontmatter description with additional natural trigger terms (`browse the web`, `open a webpage`, `click buttons`, `web automation`, `headless browser`) and context (`CI or cloud VM environments`) to improve skill selection accuracy
- Removed the redundant "Essential Commands" section that duplicated content from the Core Workflow and detailed Commands sections
- Removed a minor redundant prose line ("Commands use the cloud browser:") before the Core Workflow code block

</details>

Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.

If you want to run reviews, evals and optimizations yourself, just `npm install @tessl/cli` then run `tessl skill review path/to/your/SKILL.md`, and click [here](https://tessl.io/registry/skills/submit) to find out more.

Thanks in advance 🙏
Copy link
Contributor

@cubic-dev-ai cubic-dev-ai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No issues found across 2 files


Since this is your first cubic review, here's how it works:

  • cubic automatically reviews your code and comments on bugs and improvements
  • Teach cubic by replying to its comments. cubic learns from your replies and gets better over time
  • Add one-off context when rerunning by tagging @cubic-dev-ai with guidance or docs links (including llms.txt)
  • Ask questions if you need clarification on any suggestion

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant

X Tutup