web-research
Neural web search and content extraction using x402-protected APIs. Better than WebSearch for deep research and WebFetch for blocked sites. USE FOR: - Deep web research and investigation - Finding similar pages to a reference URL - Extracting clean text from web pages - Scraping sites that block standard fetchers - Getting direct answers to factual questions - Research requiring multiple sources TRIGGERS: - "research", "investigate", "deep dive", "find sources" - "similar to", "pages like", "more like this" - "scrape", "extract content from", "get the text from" - "blocked site", "can't access", "paywall" - "what is", "explain", "answer this" Use `npx agentcash fetch` for stableenrich.dev endpoints. Prefer Exa for semantic/neural search, Firecrawl for direct scraping.
Install with Tessl CLI
npx tessl i github:Merit-Systems/agentcash-skills --skill web-research95
Does it follow best practices?
Validation for skill structure
Discovery
100%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 an excellent skill description that hits all the key criteria. It provides specific capabilities, explicit trigger terms users would naturally use, clear differentiation from similar skills (WebSearch, WebFetch), and actionable guidance on when to use which underlying tool. The structured format with USE FOR and TRIGGERS sections makes it highly scannable for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'deep web research', 'finding similar pages', 'extracting clean text', 'scraping sites that block standard fetchers', 'getting direct answers'. Also specifies tools (Exa, Firecrawl) and technical details (x402-protected APIs, npx command). | 3 / 3 |
Completeness | Clearly answers both what (neural web search, content extraction, deep research, scraping blocked sites) AND when (explicit TRIGGERS section with natural language patterns like 'research', 'scrape', 'blocked site', 'can't access'). The 'USE FOR' and 'TRIGGERS' sections provide explicit guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user terms explicitly listed: 'research', 'investigate', 'deep dive', 'scrape', 'extract content', 'blocked site', 'paywall', 'similar to', 'pages like'. These are terms users would naturally say when needing this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly differentiates itself from similar skills ('Better than WebSearch for deep research and WebFetch for blocked sites'), carves out a clear niche for neural/semantic search and blocked site access, and specifies when to prefer Exa vs Firecrawl. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent token efficiency. The quick reference tables and decision matrices make it easy to navigate. The main weakness is the lack of explicit error handling and validation steps in the workflows, particularly for operations that could fail (blocked sites, empty results, API errors).
Suggestions
Add error handling guidance to workflows: what to do when Exa returns no results, when Firecrawl fails to scrape, or when API calls return errors
Include a validation step in the Deep Research workflow to verify content quality before synthesis (e.g., check if extracted text is meaningful, not just boilerplate)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables for quick reference, minimal prose, and assuming Claude understands the concepts. No unnecessary explanations of what APIs or web scraping are. | 3 / 3 |
Actionability | Every endpoint has complete, copy-paste ready bash commands with full JSON payloads. Options are clearly documented with defaults and constraints. Examples are executable, not pseudocode. | 3 / 3 |
Workflow Clarity | Workflows are presented as checklists with clear sequences, but lack explicit validation/error handling steps. The 'Deep Research' workflow doesn't specify what to do if searches return poor results or if content extraction fails. | 2 / 3 |
Progressive Disclosure | Clear structure with quick reference tables upfront, detailed sections below, and appropriate references to external files (rules/getting-started.md, rules/when-to-use.md) that are one level deep and well-signaled. | 3 / 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.
- 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.