Ready to supercharge your AI agents?

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

Get Started Free →

Browsh — measured AI agent skill | DecimalAI

sundial-org/browsh

NewSkillScoreMaintained

A modern text-based browser. Renders web pages in the terminal using headless Firefox.

researchby sundial-org

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

DevOps & SRE pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/sundial-org-browsh/SKILL.md

decimalai skills pull sundial-org-browsh --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/sundial-org-browsh/SKILL.md https://app.decimal.ai/s/sundial-org-browsh/SKILL.md

Raw file: /s/sundial-org-browsh/SKILL.md ↗ · machine-readable summary at /s/sundial-org-browsh.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 1h ago

Yes — +14% lift-51% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-62%	0%
case-07	✗→✓	▲ Improved	-73%	0%
case-08	✗→✓	▲ Improved	24%	0%
case-14	✗→✓	▲ Improved	-73%	0%
case-18	✓→✗	▼ Worse	-33%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

sundial-org / awesome-openclaw-skills

skills/browsh/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

Browsh

A fully-modern text-based browser. It renders stories and videos, filters ads, and saves bandwidth.

Prerequisites

browsh binary must be in PATH.
firefox binary must be in PATH (Browsh uses it as a headless backend).

Local Setup (if installed in ~/apps): Ensure your PATH includes the installation directories:

bash
export PATH=$HOME/apps:$HOME/apps/firefox:$PATH

Usage

Start Browsh:

bash
browsh

Open a specific URL:

bash
browsh --startup-url https://google.com

Note: Browsh is a TUI application. Run it inside a PTY session (e.g., using tmux or the process tool with pty=true).

Want to see if sundial-org/browsh would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.