browser-guide

Best practices for using the managed browser — handling login walls, CAPTCHAs, lazy-loaded content, paywalls, and tab cleanup. Target=camoufox 主力路径。

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/browser-guide/SKILL.md

Quality

Content

81%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 body is a highly actionable, well-sequenced operational guide with concrete commands, complete code examples, explicit validation checkpoints, and feedback loops for destructive multi-session browser use, held back only by repeated headed/headless and close-teardown guidance that could be consolidated.

Dimension	Reasoning	Score
Conciseness	The body is operational and free of concepts Claude already knows, but the headed/headless rules are restated in section 0.1, again as a blockquote in 1-B, and again in section 3, and the close-teardown guidance is repeated, so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready camoufox-cli commands, a fully enumerated command set, concrete screenshot/close invocations, and complete correct-vs-wrong JS IIFE examples with exact retry limits and timeouts covering the common cases.	5 / 5
Workflow Clarity	Login (1-A–1-E), CAPTCHA (2→3 fallback), lazy-load, and paywall flows are clearly sequenced with explicit validation checkpoints (poll every 3s, 3-/5-minute timeouts, retry caps) and feedback loops including the fail-first wait-retry and close --all teardown for the destructive multi-session case.	5 / 5
Progressive Disclosure	A single self-contained file with clear numbered sections (0–6) and sub-sections, no nesting or broken references; the only gap is that detailed CLI flag semantics and per-platform headed rules are inlined rather than split into a reference file.	4 / 5
	Total	17 / 20 Passed

Description

66%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.

The description clearly communicates the skill's purpose and names concrete, natural trigger scenarios, but it omits an explicit "Use when..." clause and relies on a single generic verb, which caps completeness and limits trigger specificity.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when driving a managed browser against login walls, CAPTCHAs, paywalls, lazy-loaded pages, or when managing browser tabs.'

Replace the uniform 'handling' with distinct concrete verbs per concern (e.g. 'bypass login walls, solve CAPTCHAs, scroll lazy-loaded content, surface paywalled content, clean up tabs') to lift specificity toward 5.

Add common synonyms (login screen, verification challenge, subscription wall) and the camoufox/cli trigger term so users phrase requests that match the skill naturally.

Dimension	Reasoning	Score
Specificity	Names the managed-browser domain and lists several concrete concerns (login walls, CAPTCHAs, lazy-loaded content, paywalls, tab cleanup), but the single uniform verb "handling" leaves minor gaps in action diversity versus a fully comprehensive action list.	4 / 5
Completeness	Clearly states what the skill does (browser best practices for access barriers) but provides no explicit "Use when..." trigger guidance, so per the missing-trigger cap completeness cannot exceed 3.	3 / 5
Trigger Term Quality	Includes natural keywords users would say (login walls, CAPTCHAs, paywalls, lazy-loaded content) with good coverage, but lacks synonyms (e.g. login screen, verification, subscribe wall) and file-extension-style triggers needed for a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (managed-browser access-barrier handling) with distinctive triggers, with only minor overlap risk against a generic browser-driving skill.	4 / 5
	Total	15 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: TeamWiseFlow/xiaobei
Path: skills/browser-guide/SKILL.md
Commit: fdc03d6

Reviewed: 11 days 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.