render-imessage-chat

Assemble an iMessage chat-reveal video ad from a thread JSON — one continuous Playwright recording of the conversation animating in (typing dots, composer typing, bubble pops, auto-scroll) crossfaded into a designed end card, with iMessage send/receive SFX and an optional ducked music bed. FREE assembly (Playwright + ffmpeg); the recipe supplies the per-brand thread + product + end-card config and gates the paid product-image/music calls to their own capabilities. Use for the imessage-chat format.

Quality

75%

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/ads/capabilities/render-imessage-chat/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.

A well-structured, actionable body with executable commands and a clear render pipeline. Some redundancy between the opening, defects, and Contract sections and the lack of verification checkpoints keep it from the top band.

Suggestions

De-duplicate the opening paragraph, the 'three defects' section, and the 'Contract' craft rules, which restate the same rich-link/short-bubble/end-card points.

Add an explicit verification checkpoint (e.g., confirm master-chat.mp4 and scene-end-endcard.mp4 exist and probe duration with ffprobe) before running stitch.sh.

Consider moving the QA-defects detail into a references file and keeping SKILL.md as a lean overview with one-level navigation links.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the opening paragraph re-describes the skill already covered by the description, and the 'Contract' craft rules repeat the 'three defects' section, so it could be tightened.	3 / 5
Actionability	Provides copy-paste-ready bash commands with real flags (npm install, record-chat.js --config, stitch.sh --chat/--end/--sfx) and a per-script breakdown, with only minor placeholders like <work>.	4 / 5
Workflow Clarity	The record → end-card → stitch sequence is concrete and explicit with each script's output feeding the next; validation checkpoints are absent but the render pipeline is non-destructive, so gaps are minor.	4 / 5
Progressive Disclosure	Well-organized into intro/defects/Run/Contract/Gaps sections with detail delegated to bundled scripts (record-chat.js, render-end-card.js, stitch.sh, mockup/, assets/sfx); references are mostly clear though cited inline in prose rather than as clean one-level navigation links.	4 / 5
	Total	15 / 20 Passed

Description

83%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.

A specific, well-scoped description that names concrete assembly actions and an explicit format trigger. The 'when' clause is present but terse, leaving room for richer trigger phrasing.

Suggestions

Expand the 'Use for...' clause with concrete natural-language triggers (e.g., 'Use when creating an iMessage-style texting-thread reveal video ad for a brand').

Add common synonyms a user might say ('iMessage text conversation ad', 'chat bubble reveal video') to broaden trigger matching.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'one continuous Playwright recording', 'crossfaded into a designed end card', 'iMessage send/receive SFX', 'optional ducked music bed' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Clearly states the 'what' (assemble the chat-reveal ad with listed features) and gives an explicit 'when' ('Use for the imessage-chat format'), but the trigger clause is minimal and could be more specific about when Claude should reach for it.	4 / 5
Trigger Term Quality	Includes natural terms like 'iMessage chat-reveal video ad', 'thread JSON', and 'imessage-chat format', but the trigger vocabulary is somewhat narrow and technical ('ducked music bed', 'Playwright recording') with a few common phrasings missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche tied to the 'imessage-chat' format with distinct triggers, making conflict with other skills unlikely.	5 / 5
	Total	18 / 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: gooseworks-ai/goose-skills
Path: skills/ads/capabilities/render-imessage-chat/SKILL.md
Commit: 2523432

Reviewed: 13 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.