Name: kontentai
Rating: 53.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

kontentai

Kontent.ai integration. Manage Assets, Workflows, Users. Use when the user wants to interact with Kontent.ai data.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/kontentai/SKILL.md

Quality

Content

57%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 genuinely actionable — packed with real, runnable Membrane CLI commands and a useful connection-state handling flow. Its weaknesses are a broken 'Step 2' cross-reference, missing validation around destructive actions, intro verbosity, and a large inlined reference table that should be split into a separate file.

Suggestions

Fix the dangling "skip to Step 2" references by either adding a numbered Step 2 section or rewording to point at the actual section (e.g. "Searching for actions").

Add an explicit validation/checkpoint before destructive and batch actions — e.g. "Before delete/unpublish, list and confirm the target item with the user, then re-read it after the call to verify."

Move the 19-row 'Popular actions' table into a references file (e.g. references/actions.md) and link to it, and trim the opening marketing paragraph and 'Overview' filler to tighten token use.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete command examples, but it opens with a product-marketing paragraph ("Kontent.ai is a headless CMS that provides a central hub..."), a thin Overview section of bare bullets, and filler like "Use action names and parameters as needed.", matching the anchor for mostly-efficient content with some unnecessary explanation.	3 / 5
Actionability	Provides many concrete, executable CLI commands (install, login, connection ensure, action list/run, request) covering the common cases, but they rely on unresolved placeholders (CONNECTION_ID, <actionId>, <code>) and there is no complete end-to-end worked example, placing it at mostly-executable with minor gaps rather than fully copy-paste ready.	4 / 5
Workflow Clarity	A clear install→authenticate→connect→search→run sequence exists with good connection-state feedback loops, but the text repeatedly says "skip to Step 2" with no Step 2 section present, and destructive actions (delete-content-item, delete-asset, unpublish-language-variant) have no validation checkpoints; the destructive-operation cap holds this at 3.	3 / 5
Progressive Disclosure	The body has reasonable section headers but is a single ~150-line monolith with a 19-row 'Popular actions' reference table inlined that belongs in a separate file, and there are no bundle files or one-level-deep references, fitting the anchor for content that should be split out but is kept inline.	3 / 5
	Total	13 / 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 solid: it states what the skill does and gives an explicit 'Use when' trigger tied to a named product, and it correctly uses third-person voice. Its main weakness is generic action language ('Manage') and omission of the core content entities that users actually reference.

Suggestions

Replace the generic verb "Manage" with specific concrete actions, e.g. "Create, list, upsert, and publish content items, assets, and language variants."

Add the core entity terms users most often name — "content items", "content types", "languages", and "language variants" — to the trigger clause so it surfaces for the common cases.

Expand the 'when' clause into concrete trigger phrases, e.g. "Use when the user wants to manage Kontent.ai content, assets, workflows, or users."

Dimension	Reasoning	Score
Specificity	"Manage Assets, Workflows, Users" names the domain and three concrete entities but uses one generic verb ("Manage") rather than several specific actions (e.g. create, list, publish, upsert), matching the anchor that lists 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	Has an explicit "what" ("Kontent.ai integration. Manage Assets, Workflows, Users.") and an explicit "when" ("Use when the user wants to interact with Kontent.ai data."), but the trigger is a single generic phrase rather than the concrete enumerated triggers of the top anchor, so it sits at the both-present-but-could-be-more-specific level.	4 / 5
Trigger Term Quality	Includes "Kontent.ai", "Assets", "Workflows", and "Users" as natural keywords, but omits the most-used entities a user would actually name (content items, content types, languages, language variants), fitting the anchor for relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	The named product "Kontent.ai" gives a clear niche and distinct trigger, but "Assets, Workflows, Users" are terms shared with sibling headless-CMS skills (Contentful, Sanity), so it is mostly distinct with minor overlap risk rather than minimal conflict risk.	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/kontentai/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.