Name: ghost-inspector
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

ghost-inspector

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ghost-inspector/SKILL.md

Quality

Content

71%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 commands and a clear connection workflow including error-state feedback loops, though it is padded with concept explanations and inlines reference material that could be split out.

Suggestions

Trim the opening paragraph explaining what Ghost Inspector is and who uses it; assume Claude knows the service and lead with the integration steps.

Move the proxy flag-options table and extended connection-state details into a separate reference file, keeping SKILL.md a lean overview with clearly signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable command reference, but it opens with concept explanations Claude already knows ('Ghost Inspector is an automated website testing service... used by developers and QA teams') and some padded phrasing, matching the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	It provides copy-paste-ready commands throughout (install, login, connection ensure, action list/run, request) plus a flag-options table, fully covering the common cases as the score-5 anchor requires.	5 / 5
Workflow Clarity	The connection lifecycle is sequenced with explicit polling and state branches (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) as feedback loops, but section ordering is slightly jumbled ('Popular actions' precedes 'Running actions'), landing just below the score-5 anchor.	4 / 5
Progressive Disclosure	At ~140 lines the content is well-sectioned but entirely inline with no bundle files or external references, and the flag-table / proxy reference material could live in a separate file, matching the 'some structure but content that should be separate is inline' anchor.	3 / 5
	Total	15 / 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 has a clear, distinct trigger tied to a named service and answers both what and when, but its action list is generic rather than concrete, capping specificity and trigger-term quality.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Ghost Inspector actions such as 'run UI tests, view test results, and organize suites'.

Add natural synonyms and trigger variations users actually say (e.g., 'test results', 'suites', 'regression tests') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (Ghost Inspector) but the listed actions — 'Manage data, records, and automate workflows' — are generic rather than concrete, matching the anchor for minimal/generic actions rather than the score-3 'concrete actions' anchor.	2 / 5
Completeness	Both a 'what' (manage data, records, automate workflows) and a 'when' (Use when the user wants to interact with Ghost Inspector data) are present; the trigger is explicit but the 'what' is vague enough to fall short of the score-5 anchor.	4 / 5
Trigger Term Quality	It surfaces the natural term 'Ghost Inspector' in an explicit 'Use when...' trigger, but offers no synonyms or file extensions, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Naming a specific SaaS service (Ghost Inspector) with a scoped trigger ('interact with Ghost Inspector data') gives it a clear niche with minimal conflict risk, matching the score-5 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/ghost-inspector/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.