perplexity
Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.
94
91%
Does it follow best practices?
Impact
99%
1.62xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description with excellent trigger terms and clear boundaries. The explicit exclusion criteria ('NOT for library/framework docs', 'NOT for workspace questions') are particularly valuable for avoiding conflicts. The main weakness is the lack of specific capability details beyond generic 'search and research'.
Suggestions
Add 2-3 specific capabilities like 'retrieve current information, summarize findings with sources, answer factual questions' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web search/research) and the tool (Perplexity AI), but lacks specific concrete actions beyond generic 'search and research'. Doesn't specify what kinds of results it returns or capabilities like summarization, source citation, etc. | 2 / 3 |
Completeness | Clearly answers both what (web search and research using Perplexity AI) and when (explicit trigger terms listed). Also includes helpful exclusion criteria (NOT for library/framework docs, NOT for workspace questions) which aids skill selection. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'search', 'find', 'look up', 'ask', 'research', 'what's the latest'. These are common, natural phrases users would actually use when needing web search. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from Context7 for library/framework docs and excludes workspace questions. The specific trigger terms and exclusion criteria create a clear niche for generic web research queries. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that excels at conciseness and actionability. The tool selection chain and concrete examples make it immediately usable. The only weakness is that cross-references to related skills (Context7, Graphite MCP, Nx MCP) could be linked rather than just mentioned.
Suggestions
Add links to related skill files (e.g., '[Context7 MCP](./context7.md)') to improve navigation between related tools
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables, bullet points, and minimal prose. No unnecessary explanations of what Perplexity or search tools are—assumes Claude's competence throughout. | 3 / 3 |
Actionability | Provides fully executable TypeScript code examples with specific parameters, clear decision trees for tool selection, and concrete examples of correct vs incorrect usage patterns. | 3 / 3 |
Workflow Clarity | Clear priority-ordered tool selection chain with explicit decision criteria. The 'Which Perplexity tool?' quick reference and examples section provide unambiguous guidance for each scenario. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in a single file. References to other tools (Context7, Graphite MCP, etc.) are mentioned but not linked to their respective skill files. | 2 / 3 |
Total | 11 / 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
- softaworks/agent-toolkit
- Commit
3027f20
- 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.