brave-search
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
91
87%
Does it follow best practices?
Impact
96%
2.23xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
75%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 functional and well-structured with clear 'what' and 'when' clauses, plus a useful differentiator ('no browser required'). Its main weaknesses are moderate specificity in listing concrete actions and incomplete coverage of natural trigger terms users might use when requesting web searches. Adding more specific capabilities and common search-related vocabulary would strengthen it.
Suggestions
Add more specific concrete actions, e.g., 'Searches the web, retrieves page content, finds documentation, looks up facts and current information via Brave Search API.'
Expand trigger terms to include natural user phrases like 'look up', 'find online', 'search the internet', 'Google', 'website', 'URL' to improve matching coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web search, content extraction) and the tool (Brave Search API), but doesn't list multiple specific concrete actions beyond 'search' and 'extract'. Missing details like summarizing results, finding URLs, comparing sources, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (web search and content extraction via Brave Search API) and 'when' (Use for searching documentation, facts, or any web content). The 'Use for...' clause serves as an explicit trigger guidance, and the 'Lightweight, no browser required' adds useful differentiation context. | 3 / 3 |
Trigger Term Quality | Includes some natural keywords like 'search', 'documentation', 'web content', and 'facts', but misses common user variations like 'look up', 'find online', 'Google', 'search the web', 'search the internet', 'URL', or 'website'. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly distinguishable by specifying Brave Search API and explicitly noting 'no browser required', which differentiates it from browser-based web scraping or browsing skills. The specific tool mention creates a clear niche. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, well-crafted skill that is concise, actionable, and well-structured. It provides executable commands, clear output format expectations, and critical edge-case handling for GitHub URLs and markdown files. The only minor note is the 'When to Use' section could arguably be trimmed, but it serves a useful routing purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what Brave Search is or how APIs work. The 'When to Use' section is borderline but serves as a useful decision guide. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready bash commands with clear flag combinations. The output format section shows exactly what to expect. Special URL handling gives specific alternative tools and commands. | 3 / 3 |
Workflow Clarity | This is a simple, single-purpose skill (search and extract). The two operations (search and content extraction) are clearly separated with unambiguous usage. The critical special URL handling section provides clear decision logic for edge cases. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized into logical sections (Requirements, Search, Extract, Output Format, Special Handling, When to Use) with clear headers and appropriate depth. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
6e3d68c
- Reviewed
Table of Contents
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.