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

shuttle

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/shuttle/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 body is highly actionable with concrete CLI commands and a solid connection-state feedback loop, but it is undermined by a redundant marketing intro, a duplicated example, and broken step cross-references that hurt workflow clarity. No bundle files exist, so the single-file structure carries all detail inline.

Suggestions

Fix the broken workflow numbering: define an explicit 'Step 1 / Step 2' sequence (or remove the 'skip to Step 2' and '#### 1b' references) so the install -> auth -> connect -> act flow is unambiguous.

Cut the marketing opener ('Shuttle is a platform that provides cloud infrastructure...') and deduplicate the action-list example that appears in both 'Searching for actions' and 'Popular actions'.

Move the verbose clientAction state-machine breakdown and the proxy flag table into a references file (e.g., CONNECTION_STATES.md, PROXY_REFERENCE.md) and link from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable commands, but the marketing-style opener ('Shuttle is a platform that provides cloud infrastructure...') and a duplicated action-list example across 'Searching for actions' and 'Popular actions' add padding Claude does not need, fitting the 'mostly efficient but could be tightened' anchor.	3 / 5
Actionability	Provides copy-paste-ready commands with flags, JSON input examples, and a proxy flag table covering common cases, but a broken 'Step 2' reference and sparse real output examples leave minor gaps, landing just below the fully executable level 5.	4 / 5
Workflow Clarity	The connection flow has a real feedback loop (poll state -> handle CLIENT_ACTION_REQUIRED -> re-poll until READY), but broken cross-references ('skip to Step 2' with no Step 2 heading, '#### 1b' with no 1a/Step 1) create sequence gaps, matching the 'steps present but checkpoints/sequence gaps' anchor.	3 / 5
Progressive Disclosure	The ~140-line file is well-sectioned with no nested references (good), but it exceeds the 50-line simple-skill exception, ships no reference files, and inlines content that could be split (the full clientAction state machine, the proxy flag table), matching the 'some structure, content that should be separate is inline' anchor.	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 cleanly states both what the skill does and when to use it, anchored to a specific platform. It is held back by generic action verbs and thin trigger-term coverage rather than concrete capability wording.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete capabilities the integration actually exposes (e.g., 'List and create Trip/Waypoint records, run workflow actions, proxy Shuttle API requests').

Expand the trigger clause with natural synonyms users would say, e.g. 'Use when the user wants to query, create, or update Shuttle data, run Shuttle workflows, or call the Shuttle API.'

Tie the 'when' to the specific entities in the skill (Trip, Waypoint, Vehicle, Driver, Contact) to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the Shuttle domain plus a few actions ('Manage data, records, and automate workflows'), but the verbs are generic ('manage', 'automate') rather than concrete, matching the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Answers both 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Shuttle data'); the 'when' is present but generic, matching the 'both what and when; when could be more specific' anchor rather than the fully concrete level 5.	4 / 5
Trigger Term Quality	Includes 'Shuttle' and 'interact with Shuttle data' as relevant keywords, but lacks common variations or synonyms a user might naturally say, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Tied to a named platform ('Shuttle integration', 'interact with Shuttle data') giving it a clear niche with minor overlap risk, but the broad 'manage data, records, automate workflows' phrasing keeps it just below the minimal-conflict level 5.	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/shuttle/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.