Name: apiary
Rating: 56.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

apiary

Apiary integration. Manage Organizations, Users, Goals, Filters. Use when the user wants to interact with Apiary 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/apiary/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 body provides concrete, executable Membrane commands and a reasonable sequenced workflow, but opens with unnecessary background, lacks validation checkpoints for destructive proxy operations, and leaves the actions table under-documented. It is actionable but not fully tight or verified.

Suggestions

Remove the introductory "Apiary is a collaborative API design..." paragraph and other background Claude already knows to improve token efficiency.

Add an explicit validation/verification step after running actions or proxy requests (e.g., check the JSON output for errors or confirm the resource changed) to support destructive and batch operations.

Fill the empty Description column in the Popular actions table so Claude can pick the right action without trial and error.

Dimension	Reasoning	Score
Conciseness	The opening paragraph ("Apiary is a collaborative API design and documentation platform...") and asides like "so you can focus on the integration logic rather than auth plumbing" explain background Claude already knows, fitting anchor 3 (mostly efficient with some unnecessary explanation); the command docs themselves are tight, keeping it above 2.	3 / 5
Actionability	Concrete copy-paste commands appear throughout ("membrane search apiary --elementType=connector --json", "membrane action run --connectionId=CONNECTION_ID ACTION_ID --json") with a clear flag table, matching anchor 4; not 5 because the Popular actions table has an empty Description column and placeholders need substitution.	4 / 5
Workflow Clarity	The connect/run workflow has a numbered sequence ("Create a new connection", "Check existing connections", "Searching for actions", "Running actions") but no validation checkpoints, and proxy requests expose destructive verbs (DELETE/PUT); per the rubric cap this destructive/batch context without validation cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is well-organized into clear sections (Install, First-time setup, Connecting, Searching for actions, Popular actions, Proxy requests), fitting anchor 4 (good structure, minor organization gaps); not 5 because at ~120 lines some reference-worthy material (action catalog, proxy details) could be split into separate files.	4 / 5
	Total	14 / 20 Passed

Description

70%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 answers both what and when with a clear product niche and decent trigger keywords, but relies on a single generic action verb and a somewhat generic "when" clause. It is solid but not fully specific or comprehensive.

Suggestions

Replace the generic verb "Manage" with several specific concrete actions (e.g., "Create and update Organizations, invite Users, set Goals, configure Filters").

Make the "Use when" clause more concrete with natural trigger phrases users would say (e.g., "Use when the user wants to create Apiary organizations, invite users, or manage goals and filters").

Dimension	Reasoning	Score
Specificity	Quotes "Manage Organizations, Users, Goals, Filters" name the domain and several concrete objects, but the single generic verb "Manage" is the only action named, matching anchor 3 (domain + limited concrete actions) rather than 4 (several specific actions).	3 / 5
Completeness	It has a clear "what" ("Manage Organizations, Users, Goals, Filters") and a "when" ("Use when the user wants to interact with Apiary data"), matching anchor 4; not 5 because the "when" clause is generic rather than a concrete trigger phrase.	4 / 5
Trigger Term Quality	The trigger "Use when the user wants to interact with Apiary data" plus object keywords (Organizations, Users, Goals, Filters) give good natural-term coverage a user would say, fitting anchor 4; not 5 because common synonyms and phrasings beyond the product name are missing.	4 / 5
Distinctiveness Conflict Risk	"Apiary integration" names a specific product niche with distinct triggers, but the object list (Organizations, Users, Goals) is generic enough to risk minor overlap with other productivity skills, fitting anchor 4 rather than 5.	4 / 5
	Total	15 / 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/apiary/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.