Name: radar
Rating: 53.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

radar

Radar integration. Manage Organizations. Use when the user wants to interact with Radar data.

Quality

60%

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/radar/SKILL.md

Quality

Content

57%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 skill is highly actionable with excellent copy-paste CLI guidance and a well-validated connection workflow, but it is undermined by a large padded entity list that wastes tokens and inflates the body without progressive disclosure. Splitting the entity catalog into a reference file and adding verification around destructive operations would materially improve it.

Suggestions

Move the ~100-item 'Radar Overview' entity list into a separate references file (e.g. references/entities.md) and link to it, keeping only Radar-relevant items inline.

Add a verification/confirmation checkpoint before destructive proxy requests (e.g., 'Confirm before -X DELETE; verify the resource is gone after').

Trim generic entities unrelated to location tracking (Spreadsheet, Image, Video, Badge, Vote, Forum Post, etc.) to reduce token waste.

Dimension	Reasoning	Score
Conciseness	The 'Radar Overview' is a ~100-item bullet enumeration of generic business entities (Spreadsheet, Image, Video, Badge, Vote, Forum Post...) largely unrelated to a location platform, which is heavy padding. Not a 3 because the padding is a substantial share of the body rather than a few over-explanations; not a 1 because the Membrane CLI sections are lean and useful.	2 / 5
Actionability	It provides concrete, copy-paste-ready commands across every common case (install, login, headless auth, connection ensure, polling, action list/run, proxy) plus a flag table. Not a 4 because the examples comprehensively cover the common cases with only standard placeholders like CONNECTION_ID.	5 / 5
Workflow Clarity	The connection workflow is clearly sequenced with a real feedback loop (poll BUILDING, handle CLIENT_ACTION_REQUIRED, re-poll), but destructive-capable operations (proxy with DELETE, action run) have no verification checkpoint, triggering the cap-at-3 for destructive workflows lacking validation. Not a 4 because the cap takes precedence over the well-validated connection step.	3 / 5
Progressive Disclosure	The body has clear section structure but the ~100-item entity list is inline content that belongs in a separate reference file, and no external references exist. Not a 2 because section organization is reasonable; not a 4 because content that should be split out is inlined with no references.	3 / 5
	Total	13 / 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 functional and correctly structured with both a 'what' and a 'Use when' clause, but it is thin: a single generic action and one broad trigger phrase. It scores well on structure and distinctiveness but is held back by limited action specificity and keyword coverage.

Suggestions

Replace the single generic action with 2-3 concrete Radar-specific actions (e.g., 'Create geofences, track trips, and fetch location analytics').

Expand the trigger clause with natural domain terms users actually say: 'Use when the user wants to manage geofences, track trips, or query location data in Radar'.

Add file-format or API synonyms (e.g., 'geofencing', 'trip tracking', 'places API') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("Radar integration") and one concrete action ("Manage Organizations"), matching the anchor for 1-2 concrete actions that are not comprehensive. It is not a 2 because a real action verb+object is given, and not a 4 because only a single generic action is listed.	3 / 5
Completeness	It explicitly answers both what ("Radar integration. Manage Organizations.") and when ("Use when the user wants to interact with Radar data"), but the trigger clause is a single generic phrase rather than multiple concrete triggers. Not a 5 because the 'when' lacks concrete trigger variations; not a 3 because both what and when are clearly present.	4 / 5
Trigger Term Quality	It includes relevant keywords ("Radar", "Organizations", "Radar data") but misses the natural domain terms a user would say (geofencing, location tracking, trips). Not a 4 because keyword coverage is thin rather than 'good with a few missing'.	3 / 5
Distinctiveness Conflict Risk	"Radar" is a named platform giving a distinct niche with minimal conflict risk, but "Manage Organizations" / "interact with Radar data" could overlap with generic org-management skills. Not a 5 because the triggers are not distinctive enough to eliminate overlap.	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/radar/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.