screenshots-marketing

Generate marketing screenshots with Playwright. Useful for landing-page hero shots, App Store screenshots, and changelog visuals.

Quality

51%

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/screenshots-marketing/SKILL.md

Quality

Content

35%

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 brief catalogue entry that defers essentially all real guidance to an external GitHub repo rather than providing executable instructions. It is tidy and avoids over-explanation, but it lacks concrete commands and local reference materials.

Suggestions

Replace the abstract install instruction with a concrete, copy-pasteable command (e.g., git clone / symlink / file copy into the skills directory) so the guidance is actionable.

Either bundle the upstream scripts/references locally so the referenced 'full upstream workflow' actually exists in the skill, or explicitly state which subset the agent should perform in-session without the external bundle.

Trim the verbatim restatement of the description and the planning-rationale prose to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is short and does not explain concepts Claude already knows, but it restates the description verbatim and pads with prose ('advertises the skill in Open Design so the agent discovers it during planning') that earns little of its tokens.	2 / 3
Actionability	Guidance is abstract rather than executable: 'install the upstream bundle into your active agent's skills directory' with no commands, and the only code block is a comment plus an `open <url>` instruction. It describes rather than instructs.	1 / 3
Workflow Clarity	There is a light sequence (inspect upstream, install bundle, invoke by name/trigger), but no concrete commands, no validation checkpoints, and key install steps are deferred to the upstream README.	2 / 3
Progressive Disclosure	Content is organized into short sections and points one level deep to the upstream repo, but there are no local bundle files (references/, scripts/, assets/ absent), so the 'full upstream workflow' referenced in the body is not actually present in the bundle.	2 / 3
	Total	7 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, specific third-person description that names concrete actions and a distinct niche. It stops short of an explicit 'Use when...' trigger clause and keeps natural trigger keywords mostly in a separate frontmatter field rather than the description text.

Suggestions

Add an explicit 'Use when...' clause to the description (e.g., 'Use when creating marketing screenshots, App Store listings, or changelog visuals') so the 'when' is not merely implied.

Fold one or two natural trigger phrases into the description text itself rather than relying solely on the separate triggers field, improving trigger_term_quality coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and outputs: 'Generate marketing screenshots with Playwright' plus 'landing-page hero shots, App Store screenshots, and changelog visuals'.	3 / 3
Completeness	Clearly states what it does, but the 'when' is only implied via 'Useful for...' rather than an explicit 'Use when...' trigger clause, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Names relevant natural terms ('marketing screenshots', 'hero shots', 'App Store screenshots') but the explicit trigger list lives in a separate frontmatter field rather than in the description, so common variations within the description itself are thin.	2 / 3
Distinctiveness Conflict Risk	The marketing-screenshot niche with Playwright plus distinct deliverables (hero shots, App Store, changelog) is clearly distinguishable and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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: nexu-io/open-design
Path: skills/screenshots-marketing/SKILL.md
Commit: a2ba3ee

Reviewed: 1 day 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.