Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Optimize Agent Browsing · majiayu000 | DecimalAI

agent toolingby majiayu000

Optimize Agent Browsing

majiayu000/optimize-agent-browsing

Source majiayu000/claude-skill-registry ↗License MIT

Analyze an OpenClaw agent's browser usage and recommend browsy migration

SkillScore95Maintained

Automatic

AI Engineer pack

Last verified 9/2/2026

What it changes

Passed 21 of 22 test cases with the skill, and 4 of 22 without it.

Without skill18%

With skill95%

Checks it passed that the model alone missed

The response maps text extraction calls to `browsy_find`.
The mapping replaces text inputs with `browsy_type_text`.
The tool mapping assigns table extraction to `browsy_tables`.

and 24 more in the full report

17 fixed4 passed either way1 still failing0 broke

Pass-rate lift: +77 pp
Tokens: +7%
Agent turns: 0%
Response time: -38%

Model gemini-3.6-flashMeasured 9/2/2026v121 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-optimize-agent-browsing/SKILL.md https://app.decimal.ai/s/majiayu000-optimize-agent-browsing/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-optimize-agent-browsing, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-optimize-agent-browsing/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-optimize-agent-browsing

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-optimize-agent-browsing/SKILL.md https://app.decimal.ai/s/majiayu000-optimize-agent-browsing/SKILL.md

Raw file: /s/majiayu000-optimize-agent-browsing/SKILL.md ↗ · machine-readable summary at /s/majiayu000-optimize-agent-browsing.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 17

Prompt

What specific configuration key must be enabled in the OpenClaw plugin settings after installing `openclaw-browsy` for the agent in `agents/bot.yaml`?

What was checked, without and with the skill
Checked	Without skill	With skill
The migration requirements specify configuring `preferBrowsy: true` in the plugin setup.	Missed	Passed

case-11 · gemini-3.6-flash · 9/2/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md89 linessingle file

Optimize Agent Browsing

Analyze an OpenClaw agent's browser tool usage patterns and identify which calls can be migrated from Playwright/CDP to browsy for faster, lighter execution.

Usage

/optimize-agent-browsing path/to/agent-config.yaml

What it does

Reviews how an agent uses browser tools and produces a migration plan:

Usage audit — scans agent configuration, tool definitions, and execution logs for browser-related tool calls (browser, web_browser, playwright_browser, browse_web)
Pattern classification — categorizes each browser usage into one of five patterns:
- Simple navigation (read-only page fetching) — direct browsy replacement
- Form interaction (login, search, data entry) — browsy handles natively
- Data extraction (tables, lists, structured content) — browsy tables/find tools
- JS-heavy SPA (React/Vue rendering required) — keep Playwright
- Screenshot/visual (pixel-level inspection needed) — keep Playwright
Tool mapping — for each migratable call, provides the exact browsy tool equivalent
Performance estimate — projects speed improvement (typically 10x) and memory savings (typically 60x) based on the migration ratio

Workflow

Read agent configuration file and tool registrations
Scan for browser tool calls in agent code/prompts
Classify each call into the 5 patterns above
For migratable patterns, map to browsy equivalents:
- browser.navigate(url) → browsy_browse
- browser.click(selector) → browsy_click (by element ID instead of CSS selector)
- browser.type(selector, text) → browsy_type_text
- browser.get_text(selector) → browsy_find
- browser.screenshot() → keep Playwright (browsy has no pixel rendering)
Generate migration checklist

Example output

Track record

Benchmark

21 / 22

test cases passed, vs 4 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / claude-skill-registry

skills/agent/optimize-agent-browsing/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Optimize Agent Browsing

Usage

What it does

Workflow

Example output

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills