browser-use-integration

Self-hosted AI browser automation using Browser Use with any LLM (Claude, GPT, Ollama). Use when building web scraping agents, data extraction pipelines, self-hosted automation, or when you need flexibility without API rate limits.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/browser-use-integration/SKILL.md

Quality

Content

46%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with extensive executable code, but it is padded with redundant use cases and comparison tables, lacks validation in its batch workflows, and ships broken reference paths with orphaned bundle files. Tightening the body and fixing the references would substantially raise quality.

Suggestions

Fix the References section to point at the actual bundle files (`references/api-reference.md`, `references/wsl2-setup.md`) or add the referenced `browser-use-setup.md` / `llm-configuration.md`, and move the inlined LLM Configuration and Self-Hosting/Docker sections into those reference files.

Collapse the five redundant Use Cases into one or two representative examples and remove the marketing 'Key Advantages' bullets and the Stagehand/Cost Comparison tables to cut verbosity.

Add a validation/verification checkpoint to the batch Data Entry example (e.g. confirm each save succeeded before continuing) so the batch workflow clears the workflow-clarity cap.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: marketing bullets ('3-5x Faster: Optimized for browser tasks'), a redundant Use Cases section repeating the same Agent pattern five times, and padded Cost Comparison and Stagehand comparison tables that add little Claude-doesn't-know value.	2 / 5
Actionability	Provides mostly executable, copy-paste-ready code across install, agent.py, LLM configs, retry/timeout, and Docker, with only minor gaps (undefined `llm` variable in pattern snippets, `os` used without import in the Claude config block).	4 / 5
Workflow Clarity	The Quick Start is a clear 4-step sequence, but the batch Data Entry and Rate Limiting use cases lack validation/verification checkpoints, triggering the cap-at-3 rule for batch operations without feedback loops.	3 / 5
Progressive Disclosure	The body references `references/browser-use-setup.md` and `references/llm-configuration.md`, neither of which exists in the bundle, while the actual files (`api-reference.md`, `wsl2-setup.md`) are never linked; additionally large sections (LLM Configuration, Self-Hosting/Docker, Use Cases) that belong in separate files are inlined.	2 / 5
	Total	11 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly answers both what the skill does and when to use it, with concrete trigger terms and a distinct self-hosted niche. Minor improvements would be adding a few more action synonyms and tightening the overlap with generic scraping skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Self-hosted AI browser automation using Browser Use with any LLM') and lists several specific applications ('web scraping agents, data extraction pipelines, self-hosted automation'), with only minor coverage gaps relative to the body's fuller action set.	4 / 5
Completeness	Clearly states what it does and follows with an explicit 'Use when...' clause carrying concrete trigger phrases, matching the anchor for answering both what and when.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('web scraping agents', 'data extraction pipelines', 'self-hosted automation', 'API rate limits') with good coverage, though a few synonyms (e.g. crawling, form filling) are absent.	4 / 5
Distinctiveness Conflict Risk	The 'Browser Use' + 'self-hosted' + 'any LLM' framing carves a distinct niche, with only minor overlap risk against general web-scraping skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (521 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/browser-use-integration/SKILL.md
Commit: 93ed392

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.