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

lexoffice

Lexoffice integration. Manage Organizations, Leads, Pipelines, Users, Goals, Filters. Use when the user wants to interact with Lexoffice data.

Quality

66%

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/lexoffice/SKILL.md

Quality

Content

52%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 operational sections are executable and well-sequenced with validation feedback, but the skill is dominated by a padded 300-line inlined noun list that hurts both conciseness and progressive disclosure. Splitting that list into a references file would materially improve both dimensions.

Suggestions

Move the ~300-item 'Lexoffice Overview' noun list into a separate references file (e.g. references/entities.md) and link to it from SKILL.md, keeping only the resource types that map to real actions.

Prune the noun list to entities Lexoffice actually exposes or that the popular-actions table references; remove generic dictionary words (Award, Bookmark, Cookie, Gallery) that add no signal.

Add a brief validation step after 'membrane action run' (e.g. checking the output/error fields) to round out the workflow feedback loop and push workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The ~300-line 'Lexoffice Overview' bullet list of generic nouns (Account, Award, Bookmark, Call...) is heavily padded auto-generated content that competes with the context window; the working-with sections are leaner but the bulk noun dump pulls it to the 'noticeably verbose / padded' anchor.	2 / 5
Actionability	Concrete, executable commands ('membrane login', 'membrane connection ensure', 'membrane action run', 'membrane request') with flags and JSON examples provide mostly copy-paste-ready guidance with only minor gaps.	4 / 5
Workflow Clarity	The connection workflow has a clear sequence with explicit state polling (BUILDING -> READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a feedback loop (poll again after user action); minor validation gaps keep it just below 5.	4 / 5
Progressive Disclosure	No bundle files exist and the entire 300-line entity dictionary is inlined in SKILL.md rather than split into a reference file, matching the 'content that clearly belongs in separate files is inlined' anchor.	2 / 5
	Total	12 / 20 Passed

Description

80%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 clear and well-scoped to Lexoffice with explicit 'what' and 'when' guidance and low conflict risk. Its main weakness is trigger-term breadth and a single generic verb covering a noun list rather than distinct actions.

Dimension	Reasoning	Score
Specificity	Quotes 'Manage Organizations, Leads, Pipelines, Users, Goals, Filters' name several concrete resource types, but the single generic verb 'Manage' applied to a noun list falls short of the multiple distinct concrete actions required for a 5.	4 / 5
Completeness	Clearly states the 'what' ('Manage Organizations, Leads, Pipelines, Users, Goals, Filters') and an explicit 'when' ('Use when the user wants to interact with Lexoffice data'), directly matching the anchor-5 example.	5 / 5
Trigger Term Quality	Natural terms 'Lexoffice' and 'Lexoffice data' cover the primary phrasing a user would say, but no synonyms, variants, or file extensions are offered; matches the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Lexoffice integration' scoped to a single named SaaS product with a Lexoffice-specific trigger gives it a clear niche with minimal overlap risk, matching the anchor-5 example.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (523 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: membranedev/application-skills
Path: skills/lexoffice/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.