render-value-prop

Render a designed 'value prop' video from a config — 3-5 noun-phrase benefit claims (<=4 words each) revealed sequentially over per-SKU product visuals, one crisp editorial frame per claim (hook sticker -> N claim beats -> brand end card). Deterministic PIL/HTML beat renderer frame-stepped via Playwright and encoded with FFmpeg, sound-off legible, hard cuts, uniform pacing. FREE (no paid calls); music is added separately (create-music-elevenlabs). Use for the value-prop format.

Quality

73%

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-value-prop/SKILL.md

Quality

Content

77%

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

A tight, highly actionable config-driven overview with an executable command and concrete contract rules, but it lacks an explicit validation checkpoint for its batch render step and under-organizes its bundled-script references.

Suggestions

Add a validation step to the Run section, e.g. after rendering verify '<dir>/finals/master-clean.mp4' exists and has non-zero size, and on failure re-run with the frame-stepped renderer before retrying encode.

Surface the bundled scripts as a short one-level reference list (e.g. 'build_storyboard_preview.py — free preview gallery; build_text_overlays.py — transparent text-zone PNGs') so their roles and navigation are clear.

Dimension	Reasoning	Score
Conciseness	Lean and dense — every line earns its place (config-driven schema reference, env overrides, contract bullets) with no explaining of concepts Claude already knows; it assumes competence throughout.	3 / 3
Actionability	Gives an executable run command with concrete output path ('render_master.py --config config.json --project <dir>' -> '<dir>/finals/master-clean.mp4'), names bundled scripts, and specifies env overrides (RENDER_PYTHON, FFMPEG) — copy-paste ready.	3 / 3
Workflow Clarity	The single render step is clear, but this batch/encode operation has no explicit validation checkpoint (e.g. verify the mp4 exists and is non-empty, or re-render on a frame-stepping failure), which the rubric caps at 2 for destructive/batch operations.	2 / 3
Progressive Disclosure	Structure is minimal (Run + Contract sections) and the inline schema reference points to a bundled config.example.json / ad_sample.recipe.config rather than well-signaled one-level-deep reference files; navigation between the bundled scripts is implied but not clearly organized.	2 / 3
	Total	10 / 12 Passed

Description

70%

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 highly specific, third-person description that crisply defines the capability and differentiates it from sibling skills, but its trigger guidance is minimal and lacks natural keyword coverage. It is strong on what and distinctiveness, weaker on when.

Suggestions

Expand the 'Use when...' clause with natural phrasings a user would say, e.g. 'Use when the user asks for a value-prop video, a product benefit ad, or a sound-off product spot with rotating SKU visuals.'

Add a couple of common trigger variations (e.g. 'value prop video', 'benefit claims ad') so the description matches how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('revealed sequentially over per-SKU product visuals', 'frame-stepped via Playwright and encoded with FFmpeg', 'hard cuts, uniform pacing') with specific format constraints (<=4 words each, 3-5 claims).	3 / 3
Completeness	The 'what' is detailed, but the 'when' clause is only the bare 'Use for the value-prop format' — an explicit trigger but minimal; it lacks the natural-keyword guidance the rubric's anchor for a 3 requires.	2 / 3
Trigger Term Quality	'value prop' is a niche format term users would say, but natural trigger variations are thin — only 'Use for the value-prop format' is offered, missing common phrasings like 'value prop video', 'product benefit ad', or 'ad spot'.	2 / 3
Distinctiveness Conflict Risk	A very specific niche (deterministic value-prop video rendering) with a distinct sibling-skill boundary ('music is added separately (create-music-elevenlabs)'), making overlap with other skills unlikely.	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: gooseworks-ai/goose-skills
Path: skills/ads/capabilities/render-value-prop/SKILL.md
Commit: 8866b2a

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.