render-podcast-skit

Assemble a two-host fake-podcast skit ad from a config — per-line lipsync clips hard-concatenated in script order, scaled/padded to 1080×1920, WHITE bottom-center captions (up to 5 words per cue, broken on sentence punctuation, word-wrapped to stay in-frame, held at least 0.9s) built from each line's OWN ElevenLabs char-level timestamps (offset by cumulative clip start, never Whisper), and closed on a Playwright/PIL brand end card composited from the real wordmark — never AI-rendered text. This is the FREE deterministic assembly stage (concat + white captions + end card + crf28 encode); the per-line VOs, photoreal gpt-image-2 base stills, expression variants, and lipsync clips come from create-vo-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the podcast-skit 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-podcast-skit/SKILL.md

Quality

Content

61%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 a tight, well-structured contract with concrete specs and good file-based progressive disclosure, but it lacks inline executable code and explicit validation checkpoints for the batch assembly workflow.

Suggestions

Add a short copy-paste runnable ffmpeg command (or a one-line script invocation) so the core encode/concat step is executable directly from SKILL.md.

Insert an explicit validation checkpoint (e.g. verify concatenated length and caption timing against words.json before final encode) to lift workflow clarity above the batch-operation cap of 3.

Consolidate the repeated FREE/deterministic and 'not Whisper' notes into a single statement to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (no explanations of ffmpeg/PIL/Playwright), but repeats the FREE/deterministic framing and the 'not Whisper' point several times, which could be trimmed.	4 / 5
Actionability	Gives concrete parameters (crf28, aac 96k, #FFFFFF, ≤5-word cues, ≥0.9s, 1080×1920) but provides no copy-paste executable code block; actual runnables are deferred to scripts/ rather than shown inline.	3 / 5
Workflow Clarity	The sequence (walk scenes → build caption timeline → render captions → hard-concat → append end card → final-encode) is present, but there are no explicit validation/verification checkpoints for this batch multi-clip operation, capping it at 3.	3 / 5
Progressive Disclosure	Well-signaled one-level-deep references to real files (scripts/config.example.json, scripts/PIPELINE.md, scripts/README.md) with the body acting as an overview/contract; references are embedded in prose rather than a dedicated navigation section, a minor organization gap.	4 / 5
	Total	14 / 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.

The description is highly specific and distinctive, naming concrete assembly actions and a clear niche. Its main weakness is the narrow, single-phrase trigger guidance ('podcast-skit format') rather than a richer set of natural trigger terms.

Suggestions

Broaden the 'Use for...' clause with synonyms users might say, e.g. 'Use for the podcast-skit format, two-host podcast ads, or short-form 9:16 dialogue ad assembly.'

Add the output container/format (e.g. '1080×1920 h264+aac master') as an explicit natural trigger so users searching by deliverable can find it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — hard-concat per-line lipsync clips scaled/padded to 1080×1920, WHITE captions from ElevenLabs char-level timestamps, Playwright/PIL end card, crf28 encode — with comprehensive coverage and no vague language.	5 / 5
Completeness	Clearly states what it does (assemble the skit ad from a config) and gives an explicit 'Use for the podcast-skit format' trigger, but the when-clause is terse and could be more specific about variant triggers.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ('fake-podcast skit ad', 'podcast-skit format') but coverage is narrow with few synonyms or format variations beyond the single 'podcast-skit' phrasing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (two-host fake-podcast skit assembly with deterministic captions/end-card) with distinct triggers and minimal overlap risk against general video or image skills.	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-podcast-skit/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.