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

Blog Docs Log in Get started

dext

Dext integration. Manage Organizations, Users, Goals, Filters. Use when the user wants to interact with Dext 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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

67%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 a strong, executable guide to driving Dext via the Membrane CLI, with a well-sequenced connection workflow and clear command examples. It loses points mainly to light padding and a few minor organization/placeholder gaps rather than any structural failure.

Suggestions

Trim Claude-obvious context (the 'Dext is a bookkeeping automation platform...' overview and 'This is the fastest way to get a connection') to tighten conciseness.

Replace placeholder tokens like CONNECTION_ID and actionId with a one-line note on where to obtain them so commands are fully copy-paste ready.

Add a brief validation/verify step after proxy `membrane request` calls and fix the dangling 'Step 2' / '1b' numbering for cleaner workflow navigation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable commands and tables, but it includes some padding Claude does not need (e.g. explaining what Dext is, the 'This is the fastest way to get a connection' line, and re-explaining that Membrane handles auth) — 'mostly efficient but includes some unnecessary explanation that could be tightened'.	3 / 5
Actionability	Provides concrete, executable CLI commands with flags (e.g. `membrane action run ... --input '{...}' --json`) and a proxy table, with only minor gaps (e.g. placeholders like CONNECTION_ID and actionId left implicit), fitting 'mostly executable; minor gaps' rather than fully copy-paste ready (5).	4 / 5
Workflow Clarity	The connection flow is sequenced with explicit state checks (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a feedback loop (poll again after user action), though the doc skips some validation for destructive proxy writes, landing at 'clear sequence with most checkpoints present; minor gaps' rather than explicit validation throughout (5).	4 / 5
Progressive Disclosure	Well-organized into clear sections (Install, Authentication, Connecting, Searching, Popular actions, Proxy, Best practices) with no bundle files present and references are external URLs; structure is good with minor organization gaps (e.g. a stray 'Step 2' reference and '1b' sub-numbering) rather than perfectly clean one-level navigation (5).	4 / 5
	Total	15 / 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 cleanly states what the skill does and when to use it, and the Dext-specific naming keeps it distinct. It is held back by listing entities rather than concrete actions and by a generic trigger clause.

Suggestions

Replace the entity list with concrete actions (e.g. 'List, create, and update Organizations, Users, Goals, and Filters') to lift specificity.

Expand the trigger clause with natural variations users would say (e.g. 'Use when the user wants to query or manage Dext data, pull client activity stats, or work with Dext organizations').

Make the 'when' more specific by tying it to the named entities rather than the generic 'interact with Dext data'.

Dimension	Reasoning	Score
Specificity	Names the domain (Dext) and a few concrete entities ('Organizations, Users, Goals, Filters') but lists no concrete actions, so it sits at the 'names domain, 1-2 concrete actions but not comprehensive' level rather than listing several specific operations (4).	3 / 5
Completeness	Has a clear 'what' ('Manage Organizations, Users, Goals, Filters') and an explicit 'when' ('Use when the user wants to interact with Dext data'); the 'when' is present and serviceable but generic, fitting 'both what and when; when could be more explicit or specific' rather than the fully concrete level (5).	4 / 5
Trigger Term Quality	Includes a reasonable natural phrase ('interact with Dext data') but lacks common variations/synonyms and file-extension-style triggers, so it has 'some relevant keywords but missing common variations' rather than good keyword coverage (4).	3 / 5
Distinctiveness Conflict Risk	The Dext name and its named entities give it a clear niche with low conflict risk, but the trigger phrasing is somewhat generic so it is 'mostly distinct; minor overlap risk' rather than minimal conflict (5).	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/dext/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.