create-chatgpt-mockup

Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed 9:16 viewport. Outputs HTML + PNG.

Quality

80%

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/ads/packs/video-ad-formats/create-chatgpt-mockup/SKILL.md

Quality

Content

77%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 a clear, validated workflow, but suffers from duplicated Quality Checks / Failure Modes sections and a bundle-integrity problem where most referenced files are missing and the existing reference images are orphaned.

Suggestions

Merge the duplicate 'Quality checks'/'Quality Checks' and 'Failure modes'/'Failure Modes' sections into one of each to remove the redundancy.

Resolve the bundle mismatch: either include the referenced render.js/generate.js/templates/examples/ files in the bundle, or correct the '## Files' table and inline references to match what is actually shipped.

Reference references/*.png from the body (or remove them) so the existing bundle files are not orphaned.

Dimension	Reasoning	Score
Conciseness	The content is mostly concrete and useful, but it duplicates two whole sections — '## Quality checks' (checklist) vs '## Quality Checks' (prose) and '## Failure modes' vs '## Failure Modes' — covering the same material, which should be consolidated.	3 / 5
Actionability	Fully executable guidance: copy-paste CLI commands ('node render.js --thread examples/01-sunscreen-image.json'), a complete thread JSON schema, a field reference, flags table, setup steps, and exact values (#F4F4F4, 28px, 999px, 44×44, 2250×4872) covering the common cases.	5 / 5
Workflow Clarity	A clear sequenced workflow (receive brief → compose thread.json → run render.js → open PNG → edit and re-render) with an explicit validation/re-render feedback loop and accompanying checklists; rendering is non-destructive so no cap applies.	5 / 5
Progressive Disclosure	Sectioning is good and the '## Files' table signals a multi-file bundle, but the actual bundle only contains references/1-7.png — the referenced render.js, generate.js, templates/, examples/.json, and tests/run-all.sh do not exist, and the present references/.png are never referenced in the body.	3 / 5
	Total	16 / 20 Passed

Description

75%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 specific, third-person, and clearly distinct, with strong capability coverage. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating ChatGPT iOS screenshots for ad creatives, social posts, or product mockups.'

Include common synonyms users might say, such as 'screenshot' or 'fake ChatGPT screen', to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities and output formats — 'Render pixel-accurate ChatGPT mobile (iOS) screen mockups', 'Supports user text bubbles, user image attachments, assistant markdown prose, citation chips...', 'Outputs HTML + PNG' — covering the feature surface comprehensively.	5 / 5
Completeness	The 'what' is explicit ('Render... mockups... Outputs HTML + PNG') but there is no 'Use when...' or equivalent trigger guidance in the description, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural terms a user would say are present ('ChatGPT', 'mobile (iOS) screen mockups', 'HTML', 'PNG'), but common synonyms like 'screenshot' or 'fake ChatGPT' are missing, so it falls short of comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The niche is very specific — pixel-accurate ChatGPT iOS mockups from a thread JSON — with distinct triggers and minimal realistic overlap with other skills.	5 / 5
	Total	17 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/ads/packs/video-ad-formats/create-chatgpt-mockup/SKILL.md
Commit: cc3e518

Reviewed: 7 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.