Name: kong
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

kong

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

Quality

61%

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/kong/SKILL.md

Quality

Content

61%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 a strong, actionable CLI guide with well-organized sections and a solid connection-state feedback loop, held back by a redundant intro paragraph, a dangling "Step 2" reference, and missing validation guidance for destructive proxy/action calls.

Suggestions

Remove or condense the opening paragraph explaining what Kong is, since Claude already knows this; lead directly with the integration workflow.

Fix the step numbering: label the connection steps consistently (e.g. Step 1 / Step 2) so the "skip to Step 2" reference resolves, replacing the loose "1b" labeling.

Add an explicit validation/checkpoint for destructive operations, e.g. confirm or dry-run before `membrane request` calls using DELETE/POST, and verify the response status before proceeding.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete CLI guidance, but the opening paragraph ("Kong is a cloud-native API gateway designed to manage and secure APIs and microservices...") explains a concept Claude already knows, and lines like "Use action names and parameters as needed." are filler that could be trimmed.	3 / 5
Actionability	It provides many copy-paste-ready, executable commands (login, connection ensure/get, action list/run, request) with a flags table covering common cases, with only minor gaps such as inconsistent use of `membrane` vs `npx @membranehq/cli` across examples.	4 / 5
Workflow Clarity	The connection setup has a clear sequence with a real feedback loop (poll after CLIENT_ACTION_REQUIRED until READY), but the "skip to Step 2" reference points to no labeled step, and destructive proxy/action runs (e.g. DELETE via `membrane request`) have no validation checkpoint, which caps workflow clarity per the destructive-operations guidance.	3 / 5
Progressive Disclosure	The body is organized into clear, navigable sections (Overview, Authentication, Connecting, Searching, Running actions, Proxy, Best practices) with content appropriately placed for a CLI skill; there are no external bundle files, and only minor inline detail (the full clientAction state machine) that could optionally be split out.	4 / 5
	Total	14 / 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 is well-formed with an explicit trigger clause and a clear product tie-in, but its action language is generic and undersells Kong-specific capabilities. Tightening the "what" with concrete Kong actions would lift specificity and completeness.

Suggestions

Replace generic verbs ("Manage data, records, and automate workflows") with Kong-specific actions such as managing services, routes, consumers, plugins, and certificates.

Add natural trigger synonyms users say, e.g. "Use when the user wants to manage Kong API gateway configuration, services, routes, or consumers."

Keep the explicit "Use when..." clause but pair it with a more comprehensive, concrete "what" list to approach the top completeness anchor.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Kong integration") and lists actions ("Manage data, records, and automate workflows"), but those actions are generic rather than Kong-specific concrete capabilities, matching the anchor for naming a domain with non-comprehensive actions.	3 / 5
Completeness	Both "what" ("Manage data, records, and automate workflows") and "when" ("Use when the user wants to interact with Kong data") are present and the when is explicit, but the what is generic rather than comprehensive, fitting the anchor where both exist with room to be more specific.	4 / 5
Trigger Term Quality	It surfaces relevant terms ("Kong", "Kong data", "Kong integration") and a natural trigger ("Use when the user wants to interact with Kong data"), but lacks common variations such as "API gateway" or "APIs" that a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	The explicit Kong tie-in ("Kong integration", "interact with Kong data") gives it a clear niche with minimal conflict risk, though the generic verbs ("manage data", "records") create minor overlap with other data-management skills.	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/kong/SKILL.md
Commit: f484c82

Reviewed: 6 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.