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

70%

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-guide/SKILL.md

Quality

Content

75%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 highly actionable with concrete commands and runnable code, and workflows are clearly sequenced with explicit checkpoints and retry/escalation loops. It is well-structured but somewhat verbose with some repeated emphasis that could be trimmed.

Suggestions

Consolidate the repeated close/teardown guidance (sections 0.3 and the close rules reappear across sections) into one canonical checklist to reduce token cost.

Trim explanatory padding around camoufox-cli flags where the flag name plus a one-line behavior already conveys the rule.

If section 0 grows further, consider moving the per-flag reference into a REFERENCES.md file and keeping SKILL.md as an overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance about a custom tool Claude would not know, but it includes repeated emphasis (the close/teardown rules are restated several times) and some explanation that could be tightened without losing clarity.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands (e.g., `camoufox-cli --session <s> --json screenshot /tmp/qr-<platform>.png`, `camoufox-cli --json close --all`) and complete runnable code (the IIFE eval examples), covering the common login/CAPTCHA/eval/scroll cases.	5 / 5
Workflow Clarity	Multi-step flows (QR/SMS login, CAPTCHA fallback, lazy-load) are clearly numbered with explicit checkpoints (snapshot polls, 3-minute/5-minute timeouts, retry caps) and feedback loops, with only minor validation gaps in sections like eval.	4 / 5
Progressive Disclosure	No bundle files exist; content is a single well-organized file with clear numbered sections (0–6) and subsections and no nested references, giving good structure with minor organization gaps in the long dense section 0.	4 / 5
	Total	16 / 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 names a clear domain and several concrete capabilities with natural trigger terms, but lacks an explicit "Use when..." trigger clause, capping completeness. It is distinguishable but could sharpen its triggers.

Suggestions

Add an explicit "Use when..." clause naming concrete user triggers (e.g., "Use when driving a managed browser against pages with login walls, CAPTCHAs, paywalls, or lazy-loaded content").

Include natural synonyms users actually say ("login wall", "paywall", "verification code", "infinite scroll") to improve trigger-term coverage toward the comprehensive anchor.

Tighten "tab cleanup" into a more concrete action (e.g., "closing browser sessions after use") to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (managed browser) and several concrete capabilities — "handling login walls, CAPTCHAs, lazy-loaded content, paywalls, and tab cleanup" — giving good coverage, though they are scenarios rather than crisp discrete actions, leaving minor gaps vs. the comprehensive anchor.	4 / 5
Completeness	It clearly states what the skill does (best practices for the managed browser, handling the listed scenarios) but contains no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric cap completeness stays at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ("login walls", "CAPTCHAs", "paywalls", "lazy-loaded content") with good coverage, but misses common synonyms/variations that would push it to the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The managed-browser/camoufox framing is a mostly distinct niche with limited overlap risk against related skills, though the trigger phrasing is not sharp enough to guarantee minimal conflict.	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: 72fd07a

Reviewed: 16 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.