CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

penny-web-search

Real-time web search and structured local-business/Places search using PennyAPI over x402. Use for fresh web results, recent facts, current events, research, verification, fact checking, and for finding businesses, restaurants, stores, services, local leads, addresses, ratings, phone numbers, websites, and coordinates. Penny Lite costs $0.001 per search call; Premium Search and Places cost $0.004 per call on Base USDC.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-structured, actionable single-file skill: exact endpoints, parameters, price verification, and the 402 payment-challenge flow with error-recovery guidance are all explicit. The main weaknesses are repetitive routing/price information across sections and the absence of one complete end-to-end request example.

Suggestions

Consolidate the Routing section and the Selection rule section into one statement of when to use Lite vs Premium vs Places, and state each price once, to remove the triplicated routing guidance.

Add one complete example request per tier (e.g. a curl or fetch call with method and headers plus the 402-then-retry interaction) so the POST body shapes become fully executable.

Move per-endpoint details (parameters, limits, price) into a compact table or a single reference section so "GET is also supported" and similar boilerplate is stated once instead of three times.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — no padding, no explaining concepts Claude already knows — but routing guidance is stated three times (Routing section, per-endpoint price lines, Selection rule) and "GET is also supported" repeats verbatim three times. Efficient with minor repetition that could be trimmed, matching anchor 4 rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Concrete endpoints, explicit input parameters with ranges/defaults, and copy-paste-ready POST body JSON (e.g. {"query":"coffee shops in Austin","num":5}) for all three routes. Not a 5 because there is no complete request example (method, headers, or an end-to-end call) — only bare body shapes — leaving a minor gap between "body shape" and "executable request".

4 / 5

Workflow Clarity

The flow is covered with real checkpoints: choose the cheapest satisfying route, expect 402 as the normal payment challenge, verify the quoted price matches the route before authorizing, and inspect payment/result state on ambiguous failure before retrying. Not a 5 because the sequence is dispersed across Routing, Payment behavior, and Selection rule rather than presented as one ordered workflow, leaving minor gaps in how the steps chain together.

4 / 5

Progressive Disclosure

A single self-contained SKILL.md with clean, well-labeled sections (Routing, Service, one section per endpoint, Payment behavior, Selection rule) and no nested or dangling references — nothing that clearly belongs in a separate file. Not a 5 because the Routing/Selection-rule duplication is inline repeated content that slightly bloats the overview, a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

91%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 description: third-person, explicit "what" and "Use for" triggers, rich natural-synonym coverage for both web and local/business search, and concrete pricing. The only weakness is that very broad terms like "research" and "verification" could collide with other search-oriented skills.

DimensionReasoningScore

Specificity

"Real-time web search and structured local-business/Places search using PennyAPI over x402" names the domain and concrete actions (web search, structured Places lookup) with concrete per-tier pricing, matching "lists several specific actions; minor gaps in coverage". Not a 5 because the capability list itself is only two actions — the depth comes from trigger enumeration rather than a comprehensive set of distinct capabilities.

4 / 5

Completeness

It clearly answers "what" ("Real-time web search and structured local-business/Places search using PennyAPI over x402") and "when" with an explicit "Use for..." clause listing concrete trigger phrases. Both halves are explicit, matching the top anchor exactly.

5 / 5

Trigger Term Quality

"fresh web results, recent facts, current events, research, verification, fact checking, businesses, restaurants, stores, services, local leads, addresses, ratings, phone numbers, websites, and coordinates" comprehensively covers natural phrasings and synonyms a user would actually say for both web-search and local-search intents. It is not a 4 because no common variation for either intent is obviously missing.

5 / 5

Distinctiveness Conflict Risk

The PennyAPI/x402/USDC framing carves a distinct niche, but broad triggers like "research", "verification", and "current events" overlap generic web-search skills, leaving minor conflict risk. Not a 5 because of that overlap; not a 3 because the paid-API and Places-specific triggers are unmistakable.

4 / 5

Total

18

/

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

ayoubsalem-spec/penny-web-search-skill

Path

SKILL.md

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.