browser

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./configs/microservice/bff-service/configs/agent-skills/clawhub/browser-automation/SKILL.md

Quality

Content

92%

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 and concise, with clearly sequenced workflows and validation/feedback checkpoints. Its one weakness is progressive disclosure: nearly everything lives inline in SKILL.md rather than being split into one-level-deep reference files.

Suggestions

Move the 'Reference: lib/browser.py' API list and 'Script conventions' into a separate references/ file (e.g. REFERENCE.md) and link to it from the body.

Consider extracting the per-mode step details (fetch, debug) into a reference doc so SKILL.md stays a concise routing overview.

Dimension	Reasoning	Score
Conciseness	The body is dense but almost entirely executable commands, routing tables, and tight conventions — every token earns its place and it assumes Claude's competence without explaining basics.	3 / 3
Actionability	Each mode is given as copy-paste-ready bash/docker exec commands with concrete flags and inline Python, fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Modes are sequenced into numbered steps with an explicit pre-check validation ('docker exec agent-browser echo ok') and a run→debug feedback loop ('If failed, switch to debug mode').	3 / 3
Progressive Disclosure	Sections are well-organized and the install.sh bundle is correctly referenced, but the skill is a single monolithic file with inline reference material (lib/browser.py API, script conventions) that could be split into separate reference files.	2 / 3
	Total	11 / 12 Passed

Description

67%

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

The description is specific and distinctive, naming four concrete capabilities tied to a clear bsession niche. Its main gap is the absence of an explicit 'Use when...' trigger clause, which limits completeness and trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when the user wants to scrape or monitor a website, automate a browser task, or debug a bsession').

Broaden trigger terms with common variations users would say ('web scraping', 'browser bot', 'monitor a page for changes').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'setup the bsession environment', 'fetch info from a website', 'create scripted automations', 'debug existing sessions' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does, but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('browser automation', 'fetch info from a website', 'debug existing sessions') but lacks common variations and an explicit trigger list, so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	The bsession-specific niche and 'Works from any repo' framing give it a clear, distinct trigger surface unlikely to collide with unrelated skills.	3 / 3
	Total	10 / 12 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/clawhub/browser-automation/SKILL.md
Commit: f618458

Reviewed: about 14 hours 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.