Name: marvel
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

marvel

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

Quality

62%

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/marvel/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 strongly actionable, well-structured integration guide with a clear connection state machine and feedback loops. Its main weaknesses are conceptual padding in the intro/overview and a couple of dangling workflow labels that slightly muddy the sequence.

Suggestions

Cut the 'Marvel is a prototyping, design, and collaboration platform...' paragraph and the bare 'Marvel Overview' entity list — assume Claude knows the domain or move detail to a reference file.

Fix the dangling 'Step 2' reference and '1b' header by labeling the action-search/run section as Step 2 so the connection → action flow is unambiguous.

Add one or two Marvel-specific `action run` examples (e.g., listing characters or fetching a comic) so the executable guidance covers the common use cases, not just the generic membrane workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable commands, but it pads with concepts Claude already knows (the 'Marvel is a prototyping, design, and collaboration platform...' intro) and an inert 'Marvel Overview' list of entity names, and repeats `action list --intent=QUERY` in both 'Searching for actions' and 'Popular actions'.	3 / 5
Actionability	It provides copy-paste-ready commands for every workflow stage (install, login, connection ensure, action list/run, request proxy) plus a concrete flag table, with only a minor gap: no Marvel-specific action examples showing what users actually do with Marvel.	4 / 5
Workflow Clarity	The connection setup is a well-sequenced state machine with explicit feedback loops (poll with --wait, handle CLIENT_ACTION_REQUIRED, re-poll until READY), but the flow references a 'Step 2' that is never labeled and uses a dangling '1b' header, leaving minor structural gaps.	4 / 5
Progressive Disclosure	With no bundle files present, content is organized into clearly headed sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) that are easy to navigate; the main gap is mild redundancy between the actions sections rather than misfiled reference depth.	4 / 5
	Total	15 / 20 Passed

Description

57%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 pairs a 'what' with an explicit 'Use when' trigger anchored to a distinct brand, but its capability verbs are generic and it lacks synonym/variant trigger terms. It reads as a serviceable but unspecific trigger description.

Suggestions

Replace generic verbs with concrete Marvel capabilities (e.g., 'List and create characters, comics, and series; fetch creator and event records') to lift specificity.

Add natural trigger synonyms and entity terms users would actually say (e.g., 'Marvel comics, characters, creators, series, or the Marvel API').

Disambiguate which Marvel (the design/prototyping app vs. the Marvel Comics API) since the body lists Comic/Character/Creator entities that conflict with the prototyping intro.

Dimension	Reasoning	Score
Specificity	The description names the Marvel domain and three action phrases ('Manage data, records, and automate workflows'), but every action is generic rather than concrete — it never says what data, which records, or what workflows, matching the anchor where actions are minimal or generic.	2 / 5
Completeness	It states both a 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Marvel data'), but the 'what' is generic and the trigger is a single phrase rather than the comprehensive set required for a 5.	4 / 5
Trigger Term Quality	It surfaces 'Marvel' and 'Marvel data' as natural terms a user would say, but offers no synonyms, variants, or file extensions, fitting the anchor for some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	Binding to the specific Marvel brand gives it a clear niche with minimal conflict risk, though the generic action verbs ('manage data') leave minor overlap with other data-integration skills and the body's Marvel-Comics entities create mild ambiguity about which Marvel.	4 / 5
	Total	13 / 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/marvel/SKILL.md
Commit: f484c82

Reviewed: 6 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.