Name: make
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

make

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

Quality

68%

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/make/SKILL.md

Quality

Content

75%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 highly actionable with executable CLI commands and a well-sequenced, state-driven connection workflow, but it carries some avoidable concept-explanation padding and inlines reference-grade detail that could live in a separate file.

Suggestions

Cut the introductory "Make, formerly Integromat, is a visual platform..." paragraph down to a single sentence; Claude does not need Make explained.

Add a verification checkpoint before running actions or proxy requests (e.g. confirm the matched action's inputSchema, or dry-run destructive methods) to close the workflow validation gap.

Move the proxy flags table and action-run reference into a separate REFERENCES.md and link to it, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the opening paragraph explaining what Make is ("a visual platform that lets users automate workflows... Think of it as a no-code Zapier alternative") over-explains a concept Claude already knows and could be trimmed.	3 / 5
Actionability	Copy-paste-ready commands appear throughout ("npm install -g @membranehq/cli@latest", "membrane connection ensure", "membrane action run", "membrane request") with a complete flags table covering the common cases.	5 / 5
Workflow Clarity	The connection flow is clearly sequenced with explicit state checkpoints (READY, BUILDING, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and a poll-retry feedback loop, though the action/proxy execution path lacks an explicit verification step before destructive calls.	4 / 5
Progressive Disclosure	The content is well-organized into clear sections (Overview, Working with Make, Authentication, Connecting, Searching, Popular actions, Best practices) with no nested references, though all detail is inlined in a 150+ line file that could split out the proxy/action reference.	4 / 5
	Total	16 / 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 both what the skill does and when to use it, but the action list is generic and the trigger phrasing lacks synonyms (e.g. Integromat, scenarios) that real users would say.

Suggestions

Replace generic verbs with concrete Make operations, e.g. "create and run scenarios, manage data stores, and trigger modules".

Add natural trigger synonyms such as "Integromat", "scenarios", or "Make automations" so the skill fires on how users actually phrase the request.

Tighten the "Use when" clause to reference concrete Make artifacts (scenarios, modules, data stores) rather than the generic "interact with Make data".

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Make domain plus a couple of actions, but the actions are high-level and generic rather than concrete like listing specific Make operations.	3 / 5
Completeness	It states both the "what" ("Make integration. Manage data, records, and automate workflows") and a "when" clause ("Use when the user wants to interact with Make data"), but the when-trigger is generic and could be more specific.	4 / 5
Trigger Term Quality	"Use when the user wants to interact with Make data" provides a relevant trigger ("Make", "Make data") but misses common synonyms users would say, notably the former name "Integromat" which the body itself mentions.	3 / 5
Distinctiveness Conflict Risk	"Make integration" targets a specific product niche with a distinct trigger ("Make data"), with only minor overlap risk against general automation/workflow 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/make/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.