CtrlK
BlogDocsLog inGet started
Tessl Logo

render-chatgpt-chat

Assemble a ChatGPT chat-reveal video ad from a thread + timeline JSON — one continuous Playwright recording of a ChatGPT mobile chat (user types with the iOS keyboard up → taps send → keyboard slides down + header cluster swaps in one beat → one gray loading dot → the assistant answer streams in word-by-word) crossfaded into a designed end card, with subliminal ChatGPT SFX and an optional ducked music bed. FREE assembly (Playwright + ffmpeg); the recipe supplies the per-brand thread + timeline + end-card config and gates the paid music call to its own capability. The ChatGPT sibling of render-imessage-chat. Use for the chatgpt-chat format.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tightly organized, highly actionable skill body with a clear pipeline, concrete parameters, and a QC checklist, backed by verified bundle files referenced one level deep. The only soft spot is minor verbosity in the gaps/notes section.

Suggestions

Tighten the 'Gaps / routing notes' SFX bullet: drop the lost-Git-LFS backstory and state only that the bundled wavs are synthesized stand-ins swappable for tuned SFX.

Trim a few parenthetical asides (e.g. 'the recipe gates it', 'copied verbatim') that restate info already conveyed in the surrounding sentence.

DimensionReasoningScore

Conciseness

The body is operational and free of concept-explanation padding, but the Git-LFS backstory ('objects 404 on the server… freshly synthesized') and several parenthetical asides add length that could be trimmed without losing guidance.

2 / 3

Actionability

Provides a copy-paste bash run block, a timeline-events table with exact param shapes, concrete SFX levels in dB, and exact dimensions (750×1624) — fully executable.

3 / 3

Workflow Clarity

Clear record → render-end-card → stitch sequence with per-step explanations and a terminal Self-QC checklist acting as verification checkpoints for the rendered master.

3 / 3

Progressive Disclosure

Overview body signals one-level-deep references to real bundle files (scripts/mockup/generate.js, scripts/config.example.json, scripts/end-card.template.html, assets/sfx/*.wav), all verified present, with content appropriately split into the bundle.

3 / 3

Total

11

/

12

Passed

Description

85%

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 dense, highly specific description that names concrete actions and explicit when-to-use guidance while distinguishing itself from a sibling skill. The main weakness is a trigger clause phrased as an internal format label rather than natural user language.

Suggestions

Reframe the trigger as natural user phrasing, e.g. 'Use when creating a ChatGPT chat-reveal video ad or when the user asks for a ChatGPT chat ad / chatgpt-chat format.'

Add a couple of common trigger variations ('ChatGPT ad', 'ChatGPT chat video') so the trigger term coverage matches the strong specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'one continuous Playwright recording', 'crossfaded into a designed end card', 'mux a ducked music bed', 'subliminal ChatGPT SFX' — each tied to specific tooling.

3 / 3

Completeness

Clearly answers 'what' ('Assemble a ChatGPT chat-reveal video ad…') and 'when' with an explicit trigger clause ('Use for the chatgpt-chat format').

3 / 3

Trigger Term Quality

Contains relevant natural terms ('ChatGPT', 'chat-reveal video ad', 'video ad') but the explicit trigger 'Use for the chatgpt-chat format' leans on an internal format label rather than phrasing a user would naturally say, and common variations are thin.

2 / 3

Distinctiveness Conflict Risk

'The ChatGPT sibling of render-imessage-chat' explicitly carves out a distinct niche and contrasts the sibling, making wrong-skill triggering unlikely.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
gooseworks-ai/goose-skills
Reviewed

Table of Contents

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.