Name: iauditor-by-safetyculture
Rating: 55.2 (1 reviews)
Author: membranedev

iauditor-by-safetyculture

IAuditor by SafetyCulture integration. Manage Organizations. Use when the user wants to interact with IAuditor by SafetyCulture data.

Quality

63%

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/iauditor-by-safetyculture/SKILL.md

Quality

Content

65%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 content is highly actionable with executable CLI commands and a well-sequenced connection workflow, but it is weighed down by an 80-line padded entity enumeration, lacks validation steps for destructive actions, and inlines material that would benefit from separate reference files. Trimming the taxonomy and adding a verify-before-delete checkpoint would meaningfully raise the score.

Suggestions

Trim or relocate the 80-line entity taxonomy to a separate reference file, keeping only entities the skill actually operates on.

Add explicit validation/verification steps for destructive actions such as delete-inspection (e.g., confirm by ID, verify the inspection is the intended target, fetch-after-delete).

Move the full popular-actions table and entity catalog into a one-level-deep reference file with a clearly signaled link from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The 80-line entity taxonomy ("Audit", "Issue", "Media" ... "Violation") is a padded enumeration largely unused elsewhere, matching 'mostly efficient but includes some unnecessary explanation'; not 4 because the padding is substantial rather than minor, not 2 because the core CLI sections are lean and actionable.	3 / 5
Actionability	Concrete copy-paste commands throughout ("membrane connection ensure", "membrane action run", "membrane request") with real flag tables and JSON examples cover the common cases, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	The connect workflow is sequenced with state checks and polling loops, but destructive actions like "Delete an inspection permanently" appear with no validation/verification, triggering the destructive-ops cap of 3 per the guidelines.	3 / 5
Progressive Disclosure	Single monolithic file with no bundle references and the entity catalog plus popular-actions table inlined rather than split out, matching 'some structure but content that should be separate is inline'; not 4 because no one-level-deep references exist.	3 / 5
	Total	14 / 20 Passed

Description

61%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 distinct and includes an explicit Use-when trigger, but its 'what' is reduced to a single generic action ('Manage Organizations') and trigger keywords are limited to the brand name without natural synonyms. Expanding concrete actions and adding inspection/audit/safety terms would lift it.

Suggestions

Replace 'Manage Organizations' with several concrete actions reflecting the body (e.g., search inspections, list/create/update issues and assets, export inspection reports).

Add natural trigger terms users actually say — inspections, audits, checklists, safety, issues — alongside the product name.

Reflect the full capability set so the 'what' matches the breadth demonstrated in the skill body.

Dimension	Reasoning	Score
Specificity	Quotes "Manage Organizations" — a single generic action paired with the domain name, matching the 'names the domain but actions are minimal or generic' anchor; not 3 because only one action is named rather than 1-2 distinct concrete actions.	2 / 5
Completeness	Both a 'what' ("Manage Organizations") and an explicit 'Use when...' trigger are present, matching 'has both what and when'; not 5 because the 'what' is narrow and understates the breadth of capabilities shown in the body.	4 / 5
Trigger Term Quality	The trigger "interact with IAuditor by SafetyCulture data" surfaces the product name but omits natural synonyms like inspections, audits, checklists, or safety, matching 'some relevant keywords but missing common variations'; not 4 because keyword coverage is thin beyond the brand name.	3 / 5
Distinctiveness Conflict Risk	The product-specific name "IAuditor by SafetyCulture" gives a clear niche with minimal overlap risk, matching the 'clear niche with distinct triggers' anchor.	5 / 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/iauditor-by-safetyculture/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.