Name: insightoai
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

insightoai

Insighto.ai integration. Manage Organizations, Users. Use when the user wants to interact with Insighto.ai data.

Quality

61%

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/insightoai/SKILL.md

Quality

Content

61%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 actionable and well-structured with concrete CLI commands and a clear connection lifecycle, making it easy for Claude to execute. Its weaknesses are a token-wasting marketing intro and the absence of validation/confirmation steps before the destructive actions it exposes.

Suggestions

Add an explicit validation/confirmation checkpoint before destructive actions — e.g. "Before running delete-assistant/delete-contact/disconnect-call, confirm the target ID with the user and prefer a get-* call first."

Trim the opening overview paragraph and the agent-types aside; Claude does not need the product's market positioning or the enumerated harness list.

Consider moving the Popular actions reference table into a separate references/actions.md and linking to it, keeping the SKILL.md overview lean.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but opens with a marketing-style overview paragraph ("helps businesses understand and improve their customer experience... make data-driven decisions") and an aside on agent types ("claude, openclaw, codex, warp, windsurf, etc. Those will be used to adjust tooling...") that Claude does not need, so it is not fully lean.	3 / 5
Actionability	Provides copy-paste-ready commands for install, login, connection ensure/get, action list/run, and request, plus a flags table — mostly executable with only minor gaps (the CONNECTION_ID placeholder and absent inputSchema examples for parameterized actions).	4 / 5
Workflow Clarity	There is a clear install→auth→connect→search→run flow with a polling/CLIENT_ACTION_REQUIRED feedback loop for connection state, but the skill surfaces destructive operations (delete-assistant, delete-contact, disconnect-call, delete-conversation) with no validation or confirmation checkpoint before running them, which caps workflow_clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Well-organized into clear sections with a concise getting-started path and a well-signaled external link to official docs; no bundle files exist so depth is fine, though the 20-row Popular actions table is inlined reference data that could live in a separate file.	4 / 5
	Total	14 / 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 is third-person, concise, and includes an explicit "Use when..." trigger tied to a specific product, which keeps it distinct and mostly complete. Its main weakness is thin capability specificity — "Manage Organizations, Users" undersells the rich action surface (widgets, assistants, conversations, calls) documented in the body.

Suggestions

Expand the "what" with concrete action verbs matching the body's surface, e.g. "Manage organizations, users, assistants, conversations, contacts, and voice/SMS widgets."

Broaden trigger phrases beyond the brand name to feature-level terms a user might say, e.g. "Use when the user wants to list or update Insighto.ai contacts, send messages, or manage assistants and conversations."

Avoid the single-word capitalization drift ("Organizations, Users") which reads as entity names rather than actions; lowercase verbs improve naturalness.

Dimension	Reasoning	Score
Specificity	Names the domain ("Insighto.ai integration") and one concrete action grouping ("Manage Organizations, Users"), but the actions are minimal and not comprehensive — no mention of widgets, assistants, conversations, contacts, or calls that the body later reveals.	3 / 5
Completeness	Has both a clear "what" ("Manage Organizations, Users") and an explicit "when" ("Use when the user wants to interact with Insighto.ai data"), but the "what" is thin and the trigger is product-bound rather than concrete task phrases, so it does not reach the fully explicit anchor 5.	4 / 5
Trigger Term Quality	Includes the natural trigger phrase "Use when the user wants to interact with Insighto.ai data" and the brand term, but coverage relies almost entirely on the product name with no synonyms, feature-specific phrases, or file/extension variations a user might say.	3 / 5
Distinctiveness Conflict Risk	Tightly bound to the named product Insighto.ai, giving a clear niche and low conflict risk with other skills, though the generic "Manage Organizations, Users" phrasing leaves minor overlap risk with general user/org 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/insightoai/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.