Name: satuit
Rating: 60.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

satuit

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

Quality

71%

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/satuit/SKILL.md

Quality

Content

68%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 well-organized, executable guide to driving Satuit through the Membrane CLI with a solid connection-setup feedback loop. Its main gaps are missing verification for destructive proxy/action calls and minor verbosity in the prose.

Suggestions

Add a verification/confirmation step before destructive proxy or action calls (e.g., 'For -X DELETE or PUT, confirm the target id with the user and re-check the response output field before proceeding').

Tighten or remove marketing-flavored prose such as 'so you can focus on the integration logic rather than auth plumbing' to improve token efficiency.

Fix the loose step numbering (the 'skip to Step 2' reference points to no labeled Step 2) to make the workflow sequence unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command reference with well-organized sections, but contains minor over-explanation such as 'so you can focus on the integration logic rather than auth plumbing' and some marketing-flavored best-practice prose that could be trimmed.	4 / 5
Actionability	It provides concrete, copy-paste-ready commands for install, login, connection ensure, action list/run, and proxy requests with flags, with only minor gaps (CONNECTION_ID and <agentType> placeholders, thin 'Popular actions' section).	4 / 5
Workflow Clarity	The connection setup has an explicit poll-and-retry feedback loop (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR), but the action-running and proxy paths support destructive operations (DELETE, PUT) with no verification or confirmation step, invoking the destructive-operations cap at 3.	3 / 5
Progressive Disclosure	The single SKILL.md is well-structured with clear section headers and no broken references, but at ~165 lines with inline content like the proxy flag table and entity list, it has minor organization gaps versus a cleanly split reference layout.	4 / 5
	Total	15 / 20 Passed

Description

73%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 clearly identifies the Satuit niche with an explicit 'Use when' trigger and both what/when coverage. Its main weakness is generic, abstract action verbs ('manage', 'automate') rather than concrete capabilities.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete capabilities a user would request, e.g. 'Create and update client records, search contacts, and run Satuit CRM actions'.

Expand the trigger phrase with more natural variations users might say, such as 'Satuit CRM', 'client records', or 'portfolio data'.

Dimension	Reasoning	Score
Specificity	Names the Satuit domain and a few action verbs ('Manage data, records, and automate workflows'), but the actions are generic and abstract rather than concrete operations, fitting the 'names domain and 1-2 concrete actions but not comprehensive' anchor.	3 / 5
Completeness	It states both a 'what' ('Satuit integration. Manage data, records, and automate workflows.') and an explicit 'when' ('Use when the user wants to interact with Satuit data.'), but the trigger could be more specific, matching the 'has both what and when; when could be more explicit' anchor.	4 / 5
Trigger Term Quality	The product name 'Satuit' is repeated as the primary natural keyword alongside 'data', 'records', and 'workflows', giving good coverage of terms a user would say, though a few natural variations are absent.	4 / 5
Distinctiveness Conflict Risk	The trigger centers on the unique named product 'Satuit', creating a clear niche with minimal conflict risk against other generic CRM or data skills.	5 / 5
	Total	16 / 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/satuit/SKILL.md
Commit: f484c82

Reviewed: 4 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.