Name: amazon-advertising
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

amazon-advertising

Amazon Advertising integration. Manage data, records, and automate workflows. Use when the user wants to interact with Amazon Advertising data.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/amazon-advertising/SKILL.md

Quality

Content

76%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 content is highly actionable with executable commands and a well-sequenced connection workflow, but it lacks validation/confirmation checkpoints around destructive operations and could offload the large actions table to a reference file.

Suggestions

Add an explicit validation/confirmation step before destructive actions (delete-campaign, delete-ad-group, delete-keyword, delete-product-ad) — e.g. confirm with the user or list affected resources before archiving.

Move the 20-row "Popular actions" catalog into a references/ file and keep only a representative few inline with a pointer, improving token efficiency and progressive disclosure.

Trim the platform-intro paragraph ("Amazon Advertising is a platform used by businesses...") since it explains a concept Claude already knows.

Dimension	Reasoning	Score
Conciseness	The body is efficient with concrete commands, a flag-options table, and minimal padding; only minor over-explanation (the platform-intro paragraph and the 20-row actions table that partly duplicates action-search) keeps it from a 5.	4 / 5
Actionability	It provides copy-paste-ready membrane commands with --json flags, explicit JSON parameter passing via --input, and a proxy-request flag table covering the common cases, matching the anchor for fully executable guidance.	5 / 5
Workflow Clarity	The connection setup is clearly sequenced with state branches and polling feedback loops, but destructive/batch operations (delete-campaign, delete-ad-group, delete-keyword, delete-product-ad) appear in the actions table with no validation or confirmation checkpoint, which caps workflow clarity at 3 per the destructive-operations rule.	3 / 5
Progressive Disclosure	The skill is a single well-organized file with clear section headers and no bundle files present; the only gap is the inlined 20-row action catalog that could arguably be split into a reference file, leaving minor organization gaps rather than a monolithic wall.	4 / 5
	Total	16 / 20 Passed

Description

57%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 mostly complete with explicit what/when guidance and a clearly bounded domain, but its capability language is vague and abstract and it lacks concrete trigger terms users would naturally say.

Suggestions

Replace generic verbs ("Manage data, records, and automate workflows") with concrete capabilities such as "create and manage campaigns, ad groups, keywords, and product ads".

Add natural trigger terms users would say, e.g. "Use when the user wants to manage Amazon Advertising campaigns, ad groups, keywords, or Sponsored Products targeting".

Tighten the "when" clause to reference specific objects (campaigns, budgets, reports) rather than the abstract phrase "interact with Amazon Advertising data".

Dimension	Reasoning	Score
Specificity	The description names the domain ("Amazon Advertising integration") but the stated actions — "Manage data, records, and automate workflows" — are generic and abstract, with no concrete capabilities like campaigns, ad groups, or keywords that the body actually exposes.	2 / 5
Completeness	It has both a clear "what" (Amazon Advertising integration; manage data, records, automate workflows) and an explicit "Use when..." clause, though the "when" trigger ("interact with Amazon Advertising data") is somewhat generic rather than tied to concrete phrases.	4 / 5
Trigger Term Quality	"Amazon Advertising data" is a relevant keyword, but there are no synonyms or concrete natural terms users would say (e.g. campaigns, ad groups, Sponsored Products), matching the anchor for some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	"Amazon Advertising" is a clear, bounded niche with minimal conflict risk; the only minor weakness is the generic "interact with Amazon Advertising data" trigger that slightly weakens distinction.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/amazon-advertising/SKILL.md
Commit: f484c82

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.