CtrlK
BlogDocsLog inGet started
Tessl Logo

amazon-search

Search Amazon products - find items, compare prices, read reviews

62

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/research-tools/capabilities/amazon-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The body is a strong, self-contained API skill: executable commands, complete parameter and response documentation, and clear error handling with recovery guidance. Its weaknesses are redundancy — the same curl example repeated three times and a confusing duplicate <details> block pointing at a different endpoint — and one error-handling note about -q flags that is inconsistent with the POST/JSON style used everywhere else.

Suggestions

Deduplicate the curl examples: the Examples section repeats the exact command from "Basic Product Search", and the <details> curl-equivalent block duplicates it against a different endpoint (api.orth.sh) — collapse these into one canonical example with a note on the endpoint difference.

Remove or rewrite the final error-handling bullet about separate -q flags and '&' in query strings: it describes GET-style flags that conflict with the POST JSON-body pattern used throughout the skill.

Trim the Examples section to show only query variations (e.g., a table of user phrasing → q value) rather than repeating the full curl command for each case.

DimensionReasoningScore

Conciseness

The body is mostly efficient with no explanations of concepts Claude already knows, but the identical base curl command is repeated three times (Usage "Basic Product Search", the <details> "curl equivalent" block, and the first Example), which is unnecessary padding that could be tightened. It is not a 2 because there is no conceptual over-explanation, only duplicated examples.

3 / 5

Actionability

Fully executable, copy-paste-ready curl commands with auth headers and JSON bodies; a concrete parameter list, a documented response schema, and worked examples covering the common cases (basic search, category filter, price-constrained, rating-based). It clearly matches the anchor-5 example rather than anchor 4, which implies minor gaps in executability.

5 / 5

Workflow Clarity

This is a simple single-purpose skill whose single action is unambiguous: read credentials from ~/.gooseworks/credentials.json (with a fallback instruction if missing), export env vars, run the curl call, interpret organic_results, and handle errors. The error-handling section provides feedback loops (429 wait-and-retry, empty results → try broader terms), satisfying the simple-skill exception for a 5; no destructive or batch operations are involved.

5 / 5

Progressive Disclosure

Sections are well-organized (Setup, When to Use, Usage, Parameters, Response, Examples, Error Handling) with no nested references, and the content is appropriately self-contained since no bundle files exist. It falls short of 5 because the inline response-field reference and the buried, duplicative <details> block could be streamlined, and the redundant Examples section adds organization gaps.

4 / 5

Total

17

/

20

Passed

Description

66%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.

The description is concise and specific, naming the Amazon domain and three concrete capabilities in third-person voice. Its main weakness is the complete absence of any "when to use" guidance, which caps completeness and limits trigger-term coverage. Adding an explicit trigger clause would lift it substantially.

Suggestions

Add a "Use when..." clause, e.g., "Use when the user asks to find, compare, or check reviews of products on Amazon."

Include common natural trigger phrases users would say, such as "shopping", "buy online", or "price comparison", to broaden keyword coverage.

Reinforce distinctiveness by mentioning Amazon-specific signals (product names, ASINs, Prime) so it does not compete with generic web-search skills.

DimensionReasoningScore

Specificity

"find items, compare prices, read reviews" lists three specific concrete actions with only minor gaps in coverage (e.g., no mention of filtering or recommendations). It falls short of anchor 5 because coverage is not comprehensive, but exceeds anchor 3's 1-2 actions.

4 / 5

Completeness

The "what" is clear (search Amazon products, find items, compare prices, read reviews), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the "what" is concrete rather than vague.

3 / 5

Trigger Term Quality

Natural phrases users would say are present ("Search Amazon products", "compare prices", "read reviews"), giving good keyword coverage. A few natural terms are missing (e.g., "shopping", "buy", "price comparison"), so it does not reach anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"Search Amazon products" carves out a clear niche with distinct triggers, with only minor overlap risk against generic web-search or shopping skills. It does not reach 5 because "find items" is somewhat generic and the description lacks reinforcing trigger phrases that would make it unmistakable.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
gooseworks-ai/goose-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.