exa-search
AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).
54
62%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/exa-search/SKILL.mdQuality
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 solid description with explicit trigger guidance and clear differentiation from related skills. Its main weakness is that the 'what' portion could be more specific about the concrete actions supported (e.g., keyword search, similarity search, content summarization). Overall it performs well for skill selection purposes.
Suggestions
Expand the capability list with more concrete actions, e.g., 'Performs keyword and similarity-based web searches, extracts full page content, and filters by domain or date.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web search via Exa) and mentions 'content extraction' and 'find similar pages', but doesn't list multiple concrete actions in detail—e.g., it doesn't specify what kinds of content extraction, filtering, or output formats are supported. | 2 / 3 |
Completeness | Clearly answers both 'what' (AI-powered web search via Exa with content extraction) and 'when' (explicit 'Use when' clause with specific trigger phrases and a scope boundary distinguishing it from academic database skills). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'exa search', 'web search with content', 'find similar pages', and differentiates from academic databases (arXiv, Semantic Scholar). These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from academic database tools (arXiv, Semantic Scholar) and ties to the specific 'Exa' platform, making it clearly distinguishable from other search-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a comprehensive guide to Exa web search with clear workflow steps and concrete command examples, but suffers from significant verbosity. The integration-contract references, wiki ingestion logic, and comparison table consume many tokens without proportional value. The workflow lacks explicit validation checkpoints for error-prone operations like API calls and script resolution failures during search execution.
Suggestions
Cut the comparison table and role/positioning section — Claude can be told when to use Exa in a single sentence rather than a full table of all search skills.
Move the wiki integration (Step 6) to a separate reference file and add a one-line pointer from the main skill, as it's a conditional side-effect that adds ~40 lines of complexity.
Add explicit validation after Step 3 (e.g., check exit code, verify results are non-empty) before proceeding to presentation — especially important since this involves an external API call.
Replace the pseudocode in Step 6 (`if [ -d research-wiki/ ] and query category was "research paper"`) with actual executable bash to match the actionability standard set in earlier steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is excessively verbose. The role/positioning table explaining other skills, the lengthy integration-contract references, the detailed argument parsing list, and the extensive wiki integration section all add significant token overhead. Much of this (e.g., explaining what Exa is, the comparison table, the detailed policy references) could be dramatically condensed. | 1 / 3 |
Actionability | The skill provides concrete bash commands for script resolution and search execution, which is good. However, the actual search relies on an external `exa_search.py` script that isn't provided in the bundle, and Step 6's wiki integration uses pseudocode (`if [ -d research-wiki/ ] and query category was "research paper"`) rather than executable code. The argument parsing in Step 1 is descriptive rather than instructive. | 2 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced and covers the full process from parsing to wiki integration. However, there are no explicit validation checkpoints — no verification that the API key is valid, no check that search results were actually returned before proceeding to presentation, and no error handling for failed searches. The Key Rules mention checking EXA_API_KEY but the workflow steps don't include this validation. | 2 / 3 |
Progressive Disclosure | The skill references external files like `shared-references/integration-contract.md` and `shared-references/wiki-helper-resolution.md`, which is good progressive disclosure in principle. However, no bundle files are provided, making these references unverifiable. The main content itself is monolithic — the lengthy wiki integration section (Step 6) could be split into a separate reference file, and the inline argument documentation is extensive. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
6f1302d
- 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.