brave-search

Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.

2.23x

Quality

—

Does it follow best practices?

Impact

96%

2.23x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, concise skill body with clear routing guardrails and concrete command forms. Its chief defect is that the scripts it instructs Claude to invoke are missing from the bundle, which undercuts both executability and the progressive-disclosure structure.

Suggestions

Bundle the referenced search.py and content.py in a scripts/ directory so the documented commands are actually executable as shipped.

Confirm the {baseDir} path resolves to that scripts directory, or add a one-line note stating where the scripts live, so the reference path is verifiable.

If the scripts are intentionally not bundled, replace the command examples with self-contained inline code or explicitly justify their absence.

Dimension	Reasoning	Score
Conciseness	The body is lean — 'Headless web search and content extraction using Brave Search API. No browser or setup required.' plus terse bash invocations and a compact output-format block; it does not explain concepts Claude already knows and every section earns its place, matching the 'lean and efficient' anchor.	3 / 3
Actionability	Commands like '{baseDir}/search.py "query" -n 10 --content' are concrete and flag-specific in form, but the referenced scripts (search.py, content.py) are absent from the bundle, so the examples are not actually executable as shipped — fitting 'some concrete guidance but incomplete; missing key details' rather than 'fully executable / copy-paste ready'.	2 / 3
Workflow Clarity	This is a simple single-purpose skill where each action is unambiguous, and the 'Special URL Handling (CRITICAL)' block acts as an explicit pre-routing guardrail (GitHub -> gh, .md -> curl) before action, satisfying the simple-skill allowance for a 3.	3 / 3
Progressive Disclosure	The body is well-organized into clear sections and points one level deep to bundled scripts, but the referenced paths ({baseDir}/search.py, content.py) do not exist in the bundle (no scripts/ directory); per the guideline to score against actual bundle structure, unresolved referenced paths cap this at 'some structure but... references present but not clearly signaled' rather than a 3.	2 / 3
	Total	10 / 12 Passed

Description

82%

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-structured description that covers both what the skill does and when to use it with natural trigger terms. Its main weakness is the broad 'any web content' trigger, which risks overlap with built-in web tools.

Suggestions

Tighten the 'when' clause to differentiate from built-in web tools, e.g. 'Use for headless web search and page-content extraction when no browser session is available.'

Add one more concrete action verb (e.g. 'fetch and extract readable content') to lift specificity from naming two actions to multiple distinct capabilities.

Dimension	Reasoning	Score
Specificity	Quotes 'Web search and content extraction via Brave Search API' — it names the domain and two concrete actions (search, content extraction), but stops short of the multiple distinct concrete actions (e.g. extract text/tables, fill forms, merge) that define a 3.	2 / 3
Completeness	It states what ('Web search and content extraction via Brave Search API') and gives an explicit when clause ('Use for searching documentation, facts, or any web content'), satisfying both halves; the judging guideline only caps at 2 when a 'Use when...' clause is missing, which it is not.	3 / 3
Trigger Term Quality	'searching documentation, facts, or any web content' gives good coverage of natural phrasings a user would actually say, matching the 'good coverage of natural terms' anchor rather than the 'some relevant keywords but missing common variations' anchor at 2.	3 / 3
Distinctiveness Conflict Risk	'via Brave Search API' and 'no browser required' carve a niche, but the trigger 'any web content' is broad and overlaps heavily with built-in web search/fetch tools, fitting 'somewhat specific but could still overlap with similar skills' rather than the clearly-non-conflicting 3.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Dicklesworthstone/pi_agent_rust
Commit: abece4a

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.