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

77%

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

65%

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 executable commands, but it is bloated with redundant example sections, lacks validation checkpoints in its batch/reset workflows, and references several non-existent files from an over-long monolith. Trimming duplication and fixing dangling references would raise quality.

Suggestions

Collapse the 'Common Patterns' and 'Examples for Claude' sections into a single concise set of examples to eliminate repeated identical search.sh invocations.

Add explicit validation checkpoints to batch/reset workflows (e.g. verify the search returns results before proceeding; confirm server health after restart) to support validate-fix-retry loops.

Either create the referenced examples/basic-search.md and README.md or remove the broken pointers, and move inline reference material (Understanding Results, Performance, Security) into those files so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Core commands are present and not padded with library tutorials, but the ~560-line body duplicates the same search invocation across 'Common Patterns' and 'Examples for Claude' and re-explains obvious Markdown parsing Claude already knows.	2 / 3
Actionability	Commands are real and copy-paste ready (e.g. bash "$SKILLS_ROOT/web-search/scripts/search.sh" "query" N and full curl calls against http://127.0.0.1:8923/api/search), with concrete error/solution pairs matching the score-3 anchor.	3 / 3
Workflow Clarity	A numbered workflow and troubleshooting diagnostics are present, but destructive/batch operations (cache deletion, server rebuild) lack explicit validation checkpoints or validate-fix-retry feedback loops, capping this at 2 per the rubric.	2 / 3
Progressive Disclosure	Bundle scripts exist and are referenced, but the SKILL.md is a monolithic wall of text and points to files that do not exist (examples/basic-search.md, README.md, dist/server/index.js), so references are poorly signaled and partly broken.	2 / 3
	Total	9 / 12 Passed

Description

90%

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 concise, well-targeted description with an explicit Use-when clause and natural trigger terms; its only weakness is naming a single action rather than enumerating several concrete capabilities. Third-person voice is used correctly.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('Real-time web search using Playwright-controlled browser') but lists a single core action rather than multiple distinct concrete actions, so it sits below the score-3 anchor.	2 / 3
Completeness	It states what the skill does ('Real-time web search using Playwright-controlled browser') and gives an explicit 'Use this skill when...' trigger clause, clearly answering both what and when.	3 / 3
Trigger Term Quality	Natural terms users would say ('current information', 'latest documentation', 'recent news', 'data beyond your knowledge cutoff') give good coverage of common variations, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The Playwright-controlled web-search niche and the 'beyond your knowledge cutoff (January 2025)' framing give clear, distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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
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: 2921c1e

Reviewed: about 10 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.