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

complianceai

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

Quality

65%

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/complianceai/SKILL.md

Quality

Content

67%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 a solid, command-driven integration guide with executable examples and a real state-polling feedback loop for connection setup. Its main weaknesses are non-essential background padding and a couple of dangling step references that break the otherwise clear workflow numbering.

Suggestions

Delete the marketing overview paragraph and the "Official docs: I am sorry..." line; Claude does not need this context to run the integration.

Fix the workflow numbering: label the action-search/run section as "Step 2" so the "skip to Step 2" references resolve, and renumber "1b" to follow an explicit "1a".

Merge the redundant "Popular actions" and "Searching for actions" sections, or move the discovery command into one place to remove duplication.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient command-focused content, but includes unnecessary padding Claude does not need — the marketing overview ("Compliance.ai is a regulatory change management platform... reducing risk and improving efficiency") and the odd "Official docs: I am sorry, but I cannot find a publicly accessible API..." line — plus awkward filler like "Use action names and parameters as needed."	3 / 5
Actionability	Concrete, copy-paste-ready commands are provided throughout (npm install, membrane login, connection ensure, action list/run, request) with a clear flag table, covering the common cases; it stops short of a 5 only because parameters like CONNECTION_ID and intent queries are left as placeholders without a fully-worked end-to-end example.	4 / 5
Workflow Clarity	The connect-to-Compliance.ai flow is clearly sequenced with a genuine validation/polling loop (READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR with re-poll after action), which is strong; it loses a point because "skip to Step 2" references a Step 2 that is never labeled, and the "1b" sub-step has no matching "1a".	4 / 5
Progressive Disclosure	No bundle files exist, so the skill is self-contained in one well-organized document with clear section headers (Install, Authentication, Connecting, Searching, Running actions, Proxy, Best practices); it is not a 5 because the "Popular actions" section overlaps with "Searching for actions" and could be consolidated, and there is minor structural redundancy.	4 / 5
	Total	15 / 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 cleanly states both what the skill does and when to use it, anchored to a distinct named product, so it clears the completeness and distinctiveness bars. Its weakness is that the capability list leans on generic verbs rather than concrete Compliance.ai-specific operations, limiting specificity and trigger richness.

Suggestions

Replace generic verbs with concrete Compliance.ai capabilities, e.g. "Search regulations, rules, and documents; browse regulatory entities; organize items into folders" instead of "Manage data, records, and automate workflows".

Expand the "Use when" clause with multiple natural trigger phrases users would say, such as "when the user asks about regulatory updates, compliance rules, or wants to search Compliance.ai records".

Add file-format or entity keywords (regulations, rules, documents, entities, folders) to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Compliance.ai domain plus three actions, but those actions are generic verbs rather than the concrete, capability-level actions (e.g. specific records/entities operations) seen in the anchor-4/5 examples.	3 / 5
Completeness	Both a "what" ("Compliance.ai integration. Manage data, records, and automate workflows.") and an explicit "when" ("Use when the user wants to interact with Compliance.ai data.") are stated; the "when" is explicit but limited to a single trigger, not the concrete multi-phrase trigger set required for a 5.	4 / 5
Trigger Term Quality	The natural trigger "Compliance.ai" and the phrase "interact with Compliance.ai data" are present, but beyond the product name there are few natural synonyms or variations a user would actually say, leaving common terms missing.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to the named product "Compliance.ai" gives it a clear niche with a distinct trigger and minimal conflict risk; it is not quite a 5 because the surrounding actions ("manage data, records") are generic enough to overlap loosely with other data-integration 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/complianceai/SKILL.md
Commit: f484c82

Reviewed: 4 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.