web-search

Real-time web search using Playwright-controlled browser. Use this skill when you need current information, latest documentation, recent news, or any data beyond your knowledge cutoff (January 2025).

Quality

71%

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/web-search/SKILL.md

Quality

Content

63%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 concrete executable commands and a clear output contract, and its workflow plus diagnostics are solid. Its main weakness is verbosity from heavy duplication across example/tips/patterns sections, and references to non-existent documentation files.

Suggestions

Consolidate the duplicated guidance across 'Common Patterns', 'Examples for Claude', 'Best Practices', and 'Tips for Effective Use' into a single section to remove repetition and cut length substantially.

Remove or actually create the referenced README.md and examples/basic-search.md files so 'Additional Resources' links resolve to real bundle files.

Tighten the architecture diagram and 'How It Works' prose, which restate concepts Claude already knows, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	At ~560 lines the body repeats the same guidance across 'Common Patterns', 'Examples for Claude', 'Best Practices', and 'Tips for Effective Use' (e.g. be-specific-in-queries appears in multiple sections), making it noticeably verbose with several padded/duplicate sections.	2 / 5
Actionability	It provides fully executable, copy-paste-ready bash commands (e.g. `bash "$SKILLS_ROOT/web-search/scripts/search.sh" "query" 5`), shows the exact Markdown output format, and covers common cases including non-ASCII file input, matching the top anchor.	5 / 5
Workflow Clarity	The search→analyze→follow-up sequence is shown, an error-handling section and quick-diagnostics checklist provide feedback loops, and it is not a destructive/batch skill so no validation cap applies; minor checkpoint gaps keep it just below fully explicit.	4 / 5
Progressive Disclosure	Sectioning is reasonable and real bundle scripts (search.sh, start-server.sh, etc.) are referenced and exist, but 'Additional Resources' points to README.md and examples/basic-search.md that do not exist as bundle files, so references are partly broken and not cleanly one-level-deep.	3 / 5
	Total	14 / 20 Passed

Description

78%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 is strong: it answers both what the skill does and when to use it with concrete, natural trigger phrases and a clear technical niche. Minor room remains to enumerate more specific search actions and add a few synonyms.

Suggestions

Add 1-2 more concrete actions (e.g., 'fetch up-to-date docs, verify facts, compare recent products') to raise specificity from naming one action to comprehensive coverage.

Include a couple of natural synonyms users say (e.g., 'look up', 'find online', 'check the web') alongside the existing trigger terms.

Dimension	Reasoning	Score
Specificity	"Real-time web search using Playwright-controlled browser" names the domain and one concrete action (web search) but does not enumerate the breadth of search capabilities, matching the anchor for 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	It clearly states the what ("Real-time web search using Playwright-controlled browser") and an explicit when ("Use this skill when you need current information, latest documentation, recent news, or any data beyond your knowledge cutoff") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Phrases like "current information, latest documentation, recent news, or any data beyond your knowledge cutoff" provide good natural keyword coverage a user would say, though a few common synonyms (e.g. "look up", "find online") are missing.	4 / 5
Distinctiveness Conflict Risk	The Playwright-browser real-time-search niche is mostly distinct with clear triggers, but "current information / latest documentation" could minorly overlap with general knowledge or fetch-style skills, placing it just below fully distinct.	4 / 5
	Total	16 / 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 (562 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: netease-youdao/LobsterAI
Path: SKILLs/web-search/SKILL.md
Commit: 100d3f7

Reviewed: 2 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.