Name: vendasta
Rating: 50.4 (1 reviews)
Author: membranedev

vendasta

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

Quality

56%

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/vendasta/SKILL.md

Quality

Content

38%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 CLI guide is genuinely actionable and the connection-state workflow has a real feedback loop, but these are buried under ~1000 lines of irrelevant duplicated padding that destroys conciseness and structure. The result is a skill that is mostly noise with a small usable core.

Suggestions

Delete the entire 'Vendasta Overview' bullet list (lines ~21-1048): the entries are unrelated to Vendasta and the repeated 'App' suffixes are pure padding that wastes the context window.

Add a validation/verification note before destructive proxy calls (POST/PUT/DELETE), e.g. confirm the endpoint and method with the user or dry-run a GET first, so the destructive workflow is not uncapped.

Replace placeholder action examples with one concrete Vendasta action id and a real input JSON payload so the actionability reaches copy-paste-ready coverage of common cases.

Dimension	Reasoning	Score
Conciseness	Roughly a thousand lines of the 'Vendasta Overview' are unrelated, duplicated padding (Yoga, Religion, Philanthropy, and escalating 'App App App App' suffixes) that Claude already knows or that is irrelevant, which is severely verbose and heavily padded.	1 / 5
Actionability	The 'Working with Vendasta' section gives copy-paste-ready bash commands (install, login, connection ensure, action list/run, request proxy) with a flags table, but uses placeholder actionIds/inputs and leaves minor gaps, fitting just below a fully comprehensive 5.	4 / 5
Workflow Clarity	The connection flow is well sequenced with a poll/handle-state feedback loop, but the proxy supports destructive HTTP methods (POST/PUT/DELETE) with no validation guidance, so the destructive-operation cap holds it at 3.	3 / 5
Progressive Disclosure	With no bundle files, all content is inlined into SKILL.md, and the giant overview bullet wall is a monolithic block with no navigation or signaling, matching minimal structure with bulk content that should not be inlined.	2 / 5
	Total	10 / 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 is short, third-person, and supplies an explicit 'Use when' trigger tied to a distinct named integration, so completeness and distinctiveness are strong. Specificity is only mid-tier because the stated actions ('manage data, records') are generic rather than concrete.

Dimension	Reasoning	Score
Specificity	It names the domain and a few action areas ('Manage data, records, and automate workflows'), but the verbs are generic rather than concrete, matching the anchor that lists 1-2 actions without being comprehensive.	3 / 5
Completeness	Both 'what' (Vendasta integration managing data/records/workflows) and an explicit 'Use when...' 'when' clause are present, but the 'what' is generic and the trigger could be more specific, fitting the anchor just below a perfect 5.	4 / 5
Trigger Term Quality	The phrase 'Use when the user wants to interact with Vendasta data' supplies the natural product-name trigger plus 'data', 'records', and 'workflows'; good coverage with only minor variation gaps.	4 / 5
Distinctiveness Conflict Risk	It is scoped to a named platform ('Vendasta') with a product-specific trigger, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	16 / 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 (1175 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/vendasta/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.