Name: amazon-elasticsearch
Rating: 56.8 (1 reviews)
Author: membranedev

amazon-elasticsearch

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

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

67%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, command-driven integration guide with executable examples and a solid connection-readiness feedback loop. Its weaknesses are some background padding Claude already knows, placeholder values instead of worked examples, and slightly fragmented step numbering.

Suggestions

Remove the introductory paragraph explaining what Amazon Elasticsearch Service is and the empty Overview bullet list; assume Claude already knows the product.

Show at least one worked action example with a real-looking actionId and input JSON instead of only "QUERY", <actionId>, and /path/to/endpoint placeholders.

Fix the step labeling: add an explicit "Step 1: Connect" / "Step 2: Discover and run actions" structure so the "1b" and "skip to Step 2" references resolve to real headers.

Dimension	Reasoning	Score
Conciseness	Most of the body is tight, executable CLI examples, but the opening paragraph explains what Amazon Elasticsearch Service is ("lets you deploy, run, and scale... used by developers and organizations") and the bare Overview list plus "Use action names and parameters as needed." are padding Claude does not need; fits the mostly-efficient-with-some-unnecessary-explanation anchor.	3 / 5
Actionability	It gives concrete, executable commands throughout (npm install, membrane login, connection ensure, action run, request) plus a proxy flag table covering the common cases; just short of fully copy-paste-ready because placeholders like "QUERY", <actionId>, CONNECTION_ID, and /path/to/endpoint are not shown with real example values.	4 / 5
Workflow Clarity	The connection workflow has a real feedback loop (poll with --wait, then branch on READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR), giving clear checkpoints; minor gaps come from the confusing step labels (a "1b" and a referenced "Step 2" with no matching header) rather than missing validation.	4 / 5
Progressive Disclosure	No bundle files exist and the body is well-sectioned with clear headers (Authentication, Connecting, Searching, Running actions, Proxy, Best practices); at ~155 lines some reference-style material (the proxy flag table, best practices) could be split out, which keeps it just below the ideal one-level-deep reference structure.	4 / 5
	Total	15 / 20 Passed

Description

62%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 covers a clear, well-scoped niche (Amazon Elasticsearch) and includes an explicit Use-when clause, so it answers both what and when. Its main weakness is generic, non-concrete action verbs and thin trigger-term variation.

Suggestions

Replace generic verbs with concrete Amazon ES operations, e.g. "Index and search documents, manage snapshots and repositories, and run queries against clusters."

Broaden trigger terms to natural synonyms users say, such as "Elasticsearch, ES, OpenSearch, search cluster, indexing, or querying data."

Tighten the Use-when clause to name concrete intents, e.g. "Use when the user wants to index documents, search or query data, or manage snapshots on Amazon Elasticsearch Service."

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names several actions but they are generic categories (manage data, automate workflows) rather than concrete ES operations like indexing or snapshotting; this matches the anchor that lists 1-2 actions without being comprehensive.	3 / 5
Completeness	It states both a "what" ("Manage data, records, and automate workflows") and an explicit "when" ("Use when the user wants to interact with Amazon Elasticsearch data"); not a 5 because the what is vague and the when trigger is generic rather than concrete.	4 / 5
Trigger Term Quality	"Amazon Elasticsearch" is a natural term a user would say, but the only trigger phrase is "interact with Amazon Elasticsearch data" with no synonyms or variations (e.g. ES, OpenSearch, search cluster, .json logs), fitting the anchor with relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	"Amazon Elasticsearch integration" pins a clear niche with low conflict risk, but the generic action phrasing ("manage data, records, automate workflows") leaves minor overlap with broad data-management skills, so it sits just below the fully-distinct anchor.	4 / 5
	Total	14 / 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-elasticsearch/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.