CtrlK
BlogDocsLog inGet started
Tessl Logo

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 - Crawling multiple pages from a website 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" - "crawl", "crawl site", "scrape entire site" Use `npx agentcash@latest fetch` for stableenrich.dev endpoints. Prefer Exa for semantic/neural search, Firecrawl for direct scraping.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

73%Weight 40%Scale 1-5

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

Highly actionable with executable commands throughout and clear per-endpoint guidance, but workflow checklists lack validation checkpoints and the referenced rules/*.md files are absent from the bundle, weakening progressive disclosure.

Suggestions

Add explicit verification checkpoints to the Deep Research workflow (e.g., confirm balance succeeded, verify extracted URLs before synthesis) to lift it above a flat checklist.

Create the referenced rules/getting-started.md and rules/when-to-use.md files, or remove the dead links, so signaled navigation resolves to real content.

Move the per-endpoint full option lists into a reference file and keep only one representative example per endpoint inline, reducing redundancy between the two reference tables.

DimensionReasoningScore

Conciseness

Largely efficient with copy-paste curl commands and tight tables, but some redundancy (the Quick Reference table and 'When to Use What' table overlap heavily) and minor padding like 'Cheapest option ($0.002) when you already have URLs' repeated in Cost Optimization.

4 / 5

Actionability

Every capability has a fully executable `npx agentcash@latest fetch` command with realistic JSON bodies, plus a parameter table covering required/optional fields and limits — copy-paste ready across all common cases.

5 / 5

Workflow Clarity

Multi-step workflows are present as checklists (Deep Research, Blocked Site Scraping), but the crawl workflow is the only one with a real validation/polling loop; the Deep Research checklist lacks verification checkpoints and the batch extract step has no error-handling guidance.

3 / 5

Progressive Disclosure

The body is well-sectioned but references rules/getting-started.md and rules/when-to-use.md — files that do not exist in any bundle directory — so the signaled navigation points to missing material, and substantial reference content (full option lists per endpoint) is inlined rather than split out.

3 / 5

Total

15

/

20

Passed

Description

96%Weight 40%Scale 1-5

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 strong, specific description that explicitly covers both what the skill does and when to use it, with rich natural trigger terms. The main risk is overlap with generic research/search triggers that could fire for other skills.

Suggestions

Tighten trigger terms like 'what is', 'explain', and 'answer this' to scope them to factual/lookup contexts where paid Exa answer is warranted, reducing overlap with free WebSearch.

DimensionReasoningScore

Specificity

Names the domain (neural web search/content extraction via x402 APIs) and lists many concrete actions — 'Extracting clean text from web pages', 'Scraping sites that block standard fetchers', 'Crawling multiple pages from a website', 'Getting direct answers to factual questions' — covering the full capability surface.

5 / 5

Completeness

Explicitly answers both 'what' (neural search and content extraction via x402 endpoints) and 'when' via a dedicated 'USE FOR' list plus a 'TRIGGERS' section with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural terms including synonyms and scenario phrasing: 'research', 'investigate', 'deep dive', 'similar to', 'pages like', 'scrape', 'blocked site', 'can't access', 'paywall', 'crawl' — terms a user would genuinely say.

5 / 5

Distinctiveness Conflict Risk

A clear niche (paid x402 web APIs) with distinct triggers, but broad research triggers like 'research', 'investigate', 'what is', 'explain' overlap somewhat with general WebSearch/use of other skills, creating minor conflict risk.

4 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
Merit-Systems/agentcash-skills
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.