Agent skill

Agentation Self Driving

by theexperiencecompany in theexperiencecompany/gaia

Autonomous design critique mode using the Agentation annotation toolbar.

Custom licenceAuto-check passedProductivity & Automation

Install Agentation Self Driving

skills CLI
$ npx skills add theexperiencecompany/gaia --skill agentation-self-driving -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install theexperiencecompany/gaia agentation-self-driving --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/theexperiencecompany/gaia.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agentation-self-driving .claude/skills/agentation-self-driving && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agentation-self-driving
GitHub stars
308
Token cost
~2.8k tokens
SKILL.md length
1,016 words
Files
2 (incl. references)
Skills in repo
17
Repo updated
First seen
Licence
Custom licence

At a glance

Autonomous design critique mode using the Agentation annotation toolbar.

  • Works in 8 steps: Scroll to the target area via eval… → Pick a specific element — heading,… → Get its bounding box via eval… → …
  • The user asks to critique this page
  • SKILL.md covers Launch — Always Headed, Critical: How to Create…, The Loop and What to Critique, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agentation Self Driving is an agent skill from theexperiencecompany/gaia. Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate," or wants an AI agent to autonomously add design feedback annotations to a web page via the browser. Requires the Agentation toolbar to be installed on the target page and agent-browser skill to be available.

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/two-session-workflow.md`).

It sits in Productivity & Automation, covering Design review and critique and Browser automation. The repository describes itself as: Your proactive personal AI assistant & companion for daily productivity 🌎.

When your agent uses it

  • The user asks to critique this page
  • Add design annotations
  • Self-driving mode
  • Wants an AI agent to autonomously add design feedback annotations to a web page via the browser

Example prompts

  • “critique this page,”
  • “add design annotations,”
  • “review the UI,”
  • “/agentation-self-driving”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Bash(agent-browser:*)

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Scroll to the target area via eval (scrollIntoView)
  2. Pick a specific element — heading, paragraph, button, section container
  3. Get its bounding box via eval (getBoundingClientRect)
  4. Execute the coordinate-click sequence (mouse move → mouse down → mouse up)
  5. Read the full snapshot output to find dialog refs at the bottom
  6. Write the critique (fill @ref) and submit (click @ref)
  7. Verify the annotation was added (see below)
  8. Move to the next area

What it can do on your machine

Read from SKILL.md and the folder at commit 26424cb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(agent-browser:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agentation Self Driving loads about 2.8k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 1,016 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,016 words (~2,791 tokens).

“Autonomously critique a web page by adding design annotations via the Agentation toolbar — in a visible headed browser so the user can watch the agent work in real time, like watching a self-driving car navigate.”

— opening of SKILL.md by theexperiencecompany, Custom licence
name
agentation-self-driving
allowed-tools
Bash(agent-browser:*)

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in .agents/skills/agentation-self-driving of theexperiencecompany/gaia.

  • SKILL.md
  • references/two-session-workflow.md

Open the folder on GitHubat commit 26424cb

Compare with similar skills

Agentation Self Driving next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agentation Self Driving compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agentation Self Driving this skilltheexperiencecompany/gaia308—~2.8kAutomated safety check: PassCustom licence
UX Audit WalkthroughAIPexStudio/AIPex1.3k—~1.9kAutomated safety check: PassMIT
Ostackmr-daedalium/ostack-saas114—~6.1kAutomated safety check: NotesMIT
Browser Usecacity/VideoHub1683 repos~2.2kAutomated safety check: WarnMIT
Agent Browserquran/quran.com-frontend-next1.9k40 repos~3.3kAutomated safety check: PassNone
Dev-Browser CLI AutomationSawyerHood/dev-browser6.7k1 repos~455Automated safety check: PassMIT

Similar skills

  • UX Audit Walkthrough

    AIPexStudio/AIPex

    Walks a Figma prototype or live webpage screen by screen and scores it against four minimalist usability principles.

    1.3k GitHub stars~1.9k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Ostack

    mr-daedalium/ostack-saas

    Fast headless browser for QA testing and site dogfooding. An agent skill from mr-daedalium/ostack-saas.

    114 GitHub stars~6.1k tokensUpdated 6 mo ago
    DevelopmentAuto-check: notes
  • Browser Use

    cacity/VideoHub

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    168 GitHub starsUsed in 3 repos~2.2k tokens
    Productivity & AutomationAuto-check: warnings
  • Agent Browser

    quran/quran.com-frontend-next

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    1.9k GitHub starsUsed in 40 repos~3.3k tokens
    Productivity & AutomationAuto-check passed
  • Dev-Browser CLI Automation

    SawyerHood/dev-browser

    Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web…

    6.7k GitHub starsUsed in 1 repo~455 tokens
    Productivity & AutomationAuto-check passed
  • Browser Automation

    openclaw/openclaw

    A skill your agent uses when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.

    392k GitHub stars~2.9k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from theexperiencecompany/gaia

All 17 skills in this repo
  • Audit Website

    theexperiencecompany/gaia

    Audit websites for SEO, performance, security, technical, content, and 15 other issue cateories with 230+ rules using the squirrelscan CLI.

    308 GitHub starsUsed in 1 repo~4.7k tokens
    Auto-check passed
  • Create DOCX

    theexperiencecompany/gaia

    Generate an editable Microsoft Word (.docx) document: reports, letters, memos, structured docs.

    308 GitHub stars~848 tokensUpdated today
    Auto-check passed
  • Create PDF

    theexperiencecompany/gaia

    Generate a polished, printable PDF: reports, letters, invoices, resumes, one-pagers.

    308 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Create PPTX

    theexperiencecompany/gaia

    Generate a PowerPoint (.pptx) slide deck: pitch decks, reviews, summaries.

    308 GitHub stars~895 tokensUpdated today
    Auto-check passed
  • Create Spreadsheet

    theexperiencecompany/gaia

    Generate an Excel (.xlsx) workbook or a CSV file: tables, financial models, data exports, formatted reports with charts.

    308 GitHub stars~802 tokensUpdated today
    Auto-check passed
  • Motion

    theexperiencecompany/gaia

    Build React animations with Motion (Framer Motion) - gestures (drag, hover, tap), scroll effects, spring physics, layout animations, SVG.

    308 GitHub stars~6.7k tokensUpdated today
    Auto-check passed

Questions about Agentation Self Driving

What does Agentation Self Driving do?

Autonomous design critique mode using the Agentation annotation toolbar. Agentation Self Driving is an agent skill from theexperiencecompany/gaia. Autonomous design critique mode using the Agentation annotation toolbar.

When should I use Agentation Self Driving?

Agentation Self Driving fits situations like: the user asks to critique this page; add design annotations; self-driving mode; wants an AI agent to autonomously add design feedback annotations to a web page via the browser.

How do I install Agentation Self Driving in Claude Code?

Run `npx skills add theexperiencecompany/gaia --skill agentation-self-driving -a claude-code`. Or copy the skill folder (.agents/skills/agentation-self-driving in theexperiencecompany/gaia) into .claude/skills/agentation-self-driving in your project. Claude Code loads it when a task matches its description.

How do I install Agentation Self Driving in Codex?

Run `npx skills add theexperiencecompany/gaia --skill agentation-self-driving -a codex`. Or copy the skill folder (.agents/skills/agentation-self-driving in theexperiencecompany/gaia) into .agents/skills/agentation-self-driving in your project. Codex loads it when a task matches its description.

Can I use Agentation Self Driving in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add theexperiencecompany/gaia --skill agentation-self-driving -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentation-self-driving, .gemini/skills/agentation-self-driving, .github/skills/agentation-self-driving and .opencode/skills/agentation-self-driving in your project.

What does Agentation Self Driving need to run?

SKILL.md names no scripts, command-line tools or credentials: Agentation Self Driving is instructions for the agent only. Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash(agent-browser:*).

Does Agentation Self Driving access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agentation Self Driving safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agentation Self Driving use?

Agentation Self Driving has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Agentation Self Driving use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 611 tokens, read only when the agent opens those files.

What are the alternatives to Agentation Self Driving?

Skills that share tags, products or a category with Agentation Self Driving: UX Audit Walkthrough (AIPexStudio/AIPex, 1.3k stars), Ostack (mr-daedalium/ostack-saas, 114 stars), Browser Use (cacity/VideoHub, 168 stars) and Agent Browser (quran/quran.com-frontend-next, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agentation Self Driving?

theexperiencecompany (a GitHub organization) maintains it in theexperiencecompany/gaia, which has 308 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 10, 2026.

Source: theexperiencecompany/gaia on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.