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

riskadvisor

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/riskadvisor/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 copy-paste CLI commands and a well-structured connection state machine, scoring top marks for actionability. It loses points for some redundant/over-explained prose and inconsistent step numbering that weakens conciseness and workflow clarity.

Suggestions

Remove the redundant "Popular actions" section that repeats the discovery command, and delete explanatory filler like "so you can focus on the integration logic rather than auth plumbing".

Fix the step numbering/labels (label the initial connection step as Step 1, renumber the polling step, and resolve the orphaned "1b" / "Step 2" references).

Add a brief validation/confirm step before running actions against live RiskAdvisor data (e.g., verify the connection is READY and inspect outputSchema before action run).

Dimension	Reasoning	Score
Conciseness	The body is mostly command-driven and efficient, but it over-explains concepts Claude already knows (what RiskAdvisor is, that Membrane handles auth "so you can focus on the integration logic") and repeats the action-list command in both "Searching for actions" and "Popular actions".	3 / 5
Actionability	It provides copy-paste-ready commands for install, login, connection ensure/get, action list, action run (with JSON params), and proxy requests, with a flag reference table covering the common cases.	5 / 5
Workflow Clarity	The connection flow is clearly sequenced with a READY/BUILDING/CLIENT_ACTION_REQUIRED decision tree and explicit poll-after-user-action guidance, but the step numbering is inconsistent (jumps to "Step 2" with no Step 1 label, "1b" orphaned) and there is no validation checkpoint before running actions against live data.	4 / 5
Progressive Disclosure	Content is well-organized into clear sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) with no bundle files to reference, so it appropriately stays inline; minor gaps are the duplicated action-discovery section and missing step labels.	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 names the product and lists its core domain objects with an explicit "Use when" trigger, giving it solid completeness and distinctiveness. It is held back by generic verbs ("Manage") and limited natural trigger-term coverage.

Suggestions

Replace the generic verb "Manage" with specific actions (e.g., "Create and update leads, build pipelines, set goals, apply filters").

Add natural user phrasings and synonyms to the trigger clause (e.g., "Use when the user mentions leads, pipelines, goals, or risk/compliance records").

Dimension	Reasoning	Score
Specificity	Quotes "Manage Organizations, Leads, Pipelines, Users, Goals, Filters" name the domain and several concrete entities, but they are objects rather than actions and "Manage" is generic, leaving coverage non-comprehensive.	3 / 5
Completeness	It has a clear "what" ("Manage Organizations, Leads, Pipelines, Users, Goals, Filters") and an explicit "when" ("Use when the user wants to interact with RiskAdvisor data"), though the "when" could be more specific.	4 / 5
Trigger Term Quality	Natural user-facing terms like "Leads", "Pipelines", and "Goals" appear, but the description lacks common synonyms or the product's natural phrasings a user would say, so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	The RiskAdvisor niche and its named domain objects are fairly distinct, with only minor overlap risk against generic CRM or data-management 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/riskadvisor/SKILL.md
Commit: f484c82

Reviewed: 5 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.