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

72%

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

68%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 compact, action-oriented body that points cleanly to real bundled scripts and a config example. Its weakness is the absence of an output-validation step for a batch render, which limits workflow clarity.

Suggestions

Add an explicit verify step after render, e.g. 'Verify: ffprobe the output, confirm duration is 10-20s and resolution is 1080x1920; re-run if claims are dropped or pacing is off.'

De-duplicate the 'FREE / no paid calls' note so it appears once (either intro or contract) to tighten conciseness toward a 5.

Clarify the minimal required config fields inline (skus, value_props, palette) so a user can assemble a valid config without opening config.example.json first.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — never explains what FFmpeg/Playwright/PIL are — with only minor restatement (the 'FREE / no paid calls' note appears in both the intro and the contract).	4 / 5
Actionability	Gives an executable run command with concrete output path and environment overrides (RENDER_PYTHON, FFMPEG), plus a real config.example.json; fully config-driven so the lack of an inline snippet is justified, leaving only minor gaps.	4 / 5
Workflow Clarity	The render is a batch output-producing operation but the workflow has no validation/verification checkpoint (e.g. confirm the mp4 plays, check duration lands in the 10-20s window), which per the rubric caps this dimension at 3.	3 / 5
Progressive Disclosure	Well-organized into Run and Contract sections with clearly signaled, one-level-deep references to bundled scripts; all referenced files (render_master.py, render_hyperframe.py, build_storyboard_preview.py, build_text_overlays.py, config.example.json) are real and present, with only minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

76%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 clearly conveys a distinct capability and concrete pipeline. Its main weakness is a tautological trigger clause and jargon-heavy language that under-serves natural user phrasing.

Suggestions

Replace 'Use for the value-prop format' with concrete trigger phrasing such as 'Use when the user asks for a value-prop / product-benefit promo video, or to render a designed value-prop spot from a config.'

Add user-natural synonyms (e.g. 'value proposition video', 'benefit-claim promo') alongside the internal term so the skill surfaces for real-world phrasing.

Move pipeline jargon ('PIL/HTML beat renderer', 'hyperframes') out of the first sentence so the leading clause stays readable as a trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Render a designed value prop video from a config', '3-5 noun-phrase benefit claims (<=4 words each) revealed sequentially', 'frame-stepped via Playwright and encoded with FFmpeg' — with comprehensive coverage of inputs, format, and pipeline.	5 / 5
Completeness	Clearly states what it does and includes an explicit 'Use for the value-prop format' when-clause, but the trigger is circular/generic rather than a concrete user-facing phrase, so it stops short of a 5.	4 / 5
Trigger Term Quality	Has relevant terms ('value prop video', 'value-prop format') but is jargon-heavy ('PIL/HTML beat renderer', 'hyperframes') and misses natural synonyms like 'value proposition' or 'product benefit video' a user might actually say.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (the value-prop video format) and explicitly distinguishes itself from the separate create-music-elevenlabs capability, giving minimal conflict risk.	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
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: 2523432

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.