CtrlK
BlogDocsLog inGet started
Tessl Logo

local-search

Search for places, businesses, and locations using Google Maps APIs via x402. USE FOR: - Finding businesses by name or type - Searching nearby places - Getting detailed place information (address, hours, reviews) - Finding restaurants, stores, services in an area - Getting business ratings and reviews - Getting aerial flyover videos of an address - Getting solar/rooftop insights and imagery for a building TRIGGERS: - "find", "search for", "locate", "nearby" - "restaurants near", "hotels in", "stores around" - "business details", "opening hours", "reviews for" - "places in", "what's near", "directions to" - "aerial view", "flyover video", "solar potential", "rooftop" Use agentcash.fetch for Google Maps endpoints. Choose partial ($0.02) vs full ($0.05-0.08) based on data needs.

65

Quality

80%

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

65%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 examples throughout, but it bloats the context window by inlining reference material and duplicating code in Workflows, and it ships dead links to missing rule files. Workflow checklists also omit the validation checkpoints expected for batch operations.

Suggestions

Move the Quick Reference table, full parameter lists, and Response Data field catalogs into a `references/api-reference.md` file and link to it from SKILL.md to cut inlined bulk.

Fix the two broken rule links: create `rules/getting-started.md` and `rules/partial-vs-full.md` or remove the references.

Add explicit validation checkpoints to the Workflows (e.g., "confirm search returned results before fetching full details", "handle empty/error responses") and remove the duplicated `agentcash.fetch` examples that already appear in the dedicated sections.

DimensionReasoningScore

Conciseness

Most sections are lean, but ~275 lines of inlined API reference (Quick Reference table, full parameter lists, Response Data field catalogs) belong in a reference file, and the Workflows section re-duplicates `agentcash.fetch` calls already shown in the dedicated sections.

3 / 5

Actionability

Every endpoint ships a copy-paste-ready `agentcash.fetch(...)` call with a real URL, method, and body, and parameter tables specify types, defaults, and constraints — fully executable across the common cases.

5 / 5

Workflow Clarity

The Workflows use checkbox sequences, but batch operations (fetch full details for several selected places) lack explicit validation checkpoints or error-recovery loops; the rubric caps batch workflows without validation at 3.

3 / 5

Progressive Disclosure

Section headers provide some structure and references are signaled, but the two referenced `rules/*.md` files do not exist in any bundle (dead links) and the bulk API reference is inlined rather than split out, matching the "content that should be separate is inline" anchor.

3 / 5

Total

14

/

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 description: concrete capabilities, explicit trigger guidance, and a clear niche via Google Maps over x402. The only weakness is that several trigger terms are generic enough to overlap with broader search skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Finding businesses by name or type", "Searching nearby places", "Getting detailed place information", "Getting aerial flyover videos", "Getting solar/rooftop insights") covering the skill comprehensively, matching the 5-anchor example.

5 / 5

Completeness

Explicitly answers "what" ("Search for places, businesses, and locations using Google Maps APIs via x402") and "when" (USE FOR + TRIGGERS blocks with concrete trigger phrases), matching the 5-anchor example.

5 / 5

Trigger Term Quality

TRIGGERS span natural phrases users actually say ("find", "search for", "restaurants near", "hotels in", "aerial view", "flyover video", "solar potential", "rooftop") with synonyms and variations, matching comprehensive coverage.

5 / 5

Distinctiveness Conflict Risk

The Google-Maps-via-x402 niche is clear, but generic triggers like "find", "search for", and "nearby" overlap with general web/search skills, leaving minor conflict risk rather than minimal.

4 / 5

Total

19

/

20

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.

Validation13 / 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

relative_links

Relative link issues: 2 missing

Warning

Total

13

/

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.