Name: smartcar
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

smartcar

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

Quality

66%

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/smartcar/SKILL.md

Quality

Content

82%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 executable CLI commands and a clear connection state machine, and it is well organized as a single self-contained document. Minor redundancy and inconsistent step-numbering references keep it just short of top marks.

Suggestions

De-duplicate the action-list command: the 'Popular actions' section repeats the `membrane action list` invocation already given under 'Searching for actions'.

Fix the step cross-references: 'skip to Step 2' and '#### 1b' imply a numbered 'Step 1a'/'Step 2' structure that the headers do not actually define.

Tighten the 'Smartcar Overview' capability bullets so they tie back to the searchable actions rather than sitting as an unused list.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with direct commands and minimal padding, though the 'Popular actions' section repeats the action-list command already shown under 'Searching for actions'.	4 / 5
Actionability	Commands are concrete, executable, and copy-paste ready with flags, a proxy-options table, and a JSON-input example covering the common cases.	5 / 5
Workflow Clarity	The connect -> poll-by-state -> search -> run sequence is clear with an explicit state machine and recovery loop, but cross-references to 'Step 2' and '1b' are not matched by a numbered 'Step 1a/Step 2' heading structure.	4 / 5
Progressive Disclosure	The single self-contained SKILL.md is well-organized into clear sections with no external file references and no nesting; the only gap is the slightly redundant duplicated 'action list' guidance.	4 / 5
	Total	17 / 20 Passed

Description

50%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 correctly includes an explicit 'Use when' trigger and is clearly distinct via the Smartcar product name, but its capability language is generic and it omits the concrete vehicle actions the skill actually supports. It reads as a placeholder rather than a precise trigger.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Smartcar actions, e.g. 'Lock/unlock vehicles, read fuel, battery, odometer, and tire pressure, and control charging.'

Add natural trigger terms users would say, such as 'vehicle data', 'car lock/unlock', 'charge status', or 'odometer'.

Name the integration target explicitly, e.g. 'Use when the user wants to read or control a connected vehicle through Smartcar.'

Dimension	Reasoning	Score
Specificity	The description names the Smartcar domain but uses only generic actions ('Manage data, records, and automate workflows') with no concrete vehicle capabilities (lock/unlock, odometer, battery).	2 / 5
Completeness	Both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Smartcar data') are present, though each could be more specific.	4 / 5
Trigger Term Quality	The only natural trigger is the product name itself ('interact with Smartcar data'); it lacks common task phrases a user would actually say like 'lock my car' or 'check vehicle fuel'.	2 / 5
Distinctiveness Conflict Risk	Tying the skill to a named product (Smartcar) gives it a clear niche with minimal conflict risk against unrelated skills.	4 / 5
	Total	12 / 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/smartcar/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.