CtrlK
BlogDocsLog inGet started
Tessl Logo

news-shopping

Search Google News, Google Shopping, Google Images, and Google Lens using Serper APIs via x402. USE FOR: - Finding recent news articles on a topic - Current events and breaking news - Product searches and price comparisons - Shopping research and product discovery - Industry news monitoring - Image search and finding photos/headshots of people - Reverse image search (Google Lens) TRIGGERS: - "news about", "latest news", "recent articles" - "current events", "breaking", "headlines" - "shopping", "buy", "price", "product search" - "compare prices", "where to buy", "deals on" - "image of", "photo of", "headshot", "reverse image search" Use agentcash.fetch for Serper endpoints. Most endpoints are $0.04 per call; Lens is $0.20.

71

Quality

89%

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

78%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 content with executable examples for every endpoint and clear workflow checklists, weakened mainly by repeated cost/returns information and a dangling reference to a missing rules/getting-started.md file. Progressive disclosure is the weakest dimension: too much reference detail lives inline and the one external link is broken.

Suggestions

Create the referenced rules/getting-started.md (or remove/fix the link) so the Setup section's progressive-disclosure pointer resolves to a real file.

De-duplicate cost information — keep it in the Quick Reference price column and the Cost Estimation table, and drop the redundant restatement in the description's closing line.

Merge each endpoint's inline "Returns" list with the consolidated "Response Data" section to remove the repeated field listings and tighten the body.

DimensionReasoningScore

Conciseness

The body is mostly lean and reference-style, but cost appears three times (description, the Quick Reference price column, and a dedicated Cost Estimation section) and per-endpoint "Returns" fields are duplicated in the later "Response Data" section — minor padding that could be trimmed. Not a 5 because of these repetitions; not a 3 because the bulk of each token earns its place.

4 / 5

Actionability

Every endpoint ships a copy-paste-ready `agentcash.fetch(...)` call with full URL, method, and body, plus documented parameters and worked examples (time filters, country/language, people queries), covering the common cases fully.

5 / 5

Workflow Clarity

Workflows (News Monitoring, Breaking News, Product Research, Price Comparison) give clear checkboxed sequences with example calls; these are read-only searches so the destructive/batch cap-at-3 does not apply. Held at 4 rather than 5 because validation/error-recovery checkpoints are only implicit (e.g., "Review and summarize top stories") with no retry-on-empty guidance.

4 / 5

Progressive Disclosure

Sections and a Quick Reference table give decent structure, but the bulk reference content (per-endpoint details, response fields, tips) is inlined in SKILL.md rather than split out, and the single external reference — [rules/getting-started.md](rules/getting-started.md) — points to a file that does not exist in the bundle. Not a 2 because sectioning is reasonable; not a 4 because of the broken reference and heavy inlining.

3 / 5

Total

16

/

20

Passed

Description

100%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, well-structured description: concrete capabilities, comprehensive natural triggers, explicit what-and-when guidance, and a distinct niche. Voice is imperative/neutral with no first- or second-person phrasing that would trigger a specificity penalty.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across four distinct search surfaces — "Search Google News, Google Shopping, Google Images, and Google Lens", "Finding recent news articles", "Product searches and price comparisons", "Reverse image search" — giving comprehensive coverage rather than vague abstractions.

5 / 5

Completeness

Explicitly answers both "what" (search Google News/Shopping/Images/Lens via Serper APIs over x402) and "when" (a USE FOR list plus a concrete TRIGGERS block), matching the anchor for clearly answering both with concrete trigger phrases.

5 / 5

Trigger Term Quality

The TRIGGERS block supplies comprehensive natural phrases a user would actually say — "news about", "latest news", "breaking", "headlines", "compare prices", "where to buy", "deals on", "photo of", "headshot", "reverse image search" — including synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Serper-powered Google News/Shopping/Images/Lens) with distinct trigger phrases, so overlap with other skills is minimal; it would not fire for unrelated requests.

5 / 5

Total

20

/

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.

Validation — 13 / 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: 1 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.