render-editorial-motion-podcast

Assemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat limited-palette editorial-illustration keyframes (one look pack) are animated NOT by generative i2v but by DETERMINISTIC ffmpeg ken-burns (zoompan) + hard cuts (no crossfades, which expose geometric drift), each beat snapped to its spoken line, the real audio muxed, Whisper-driven captions burned only mid-sentence, and closed on a PIL brand end card — never AI-rendered text. This is the FREE deterministic assembly stage (ffmpeg ken-burns + hard concat + audio mux + captions + end card); the real audio is clipped from source and the keyframes come from create-image-fal. Use for the editorial-motion-podcast format.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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 strong, dense operational contract: nearly every line is a production-earned gotcha with concrete ffmpeg/PIL parameters, and bundle references are real, clearly signaled, and one level deep. It loses points for repeated 'FREE/$0' framing, a duplicated crossfade rationale, and the lack of any complete runnable command in the body itself.

Suggestions

Consolidate the 'FREE / deterministic / $0' framing into one statement (e.g., the Run section) and cut its repetition from the intro and Contract, and drop the second crossfade explanation — the rationale appears both in the intro and the Contract bullet.

Include one complete copy-paste ffmpeg command in the body (e.g., a single-beat ken-burns + concat example) so the most common case is runnable without opening the bundle files.

Move the caption rule specifics (NON-OVERLAP formula, PIL subject-shift recipe) into a referenced file and keep a one-line rule per bullet in the Contract to cut token cost.

Dimension	Reasoning	Score
Conciseness	Mostly dense operational gotchas Claude would not know (the '-loop 1' + 'zoompan d=N' trap, the caption clamp formula, the libass fallback), but the 'FREE, deterministic / $0' framing is repeated across the intro, Run, and Contract sections and the crossfade rationale appears twice — minor padding to trim.	4 / 5
Actionability	Concrete, near-executable guidance throughout ('-map 0:v:0 -map 1:a:0', zoompan 1.0→~1.06× with '-t' + 'trim', 'enable=\'between(t,st,en)\'', 'end = min(last_word_end + ~0.15, next_start - 0.03)'), but the body contains no single complete runnable command — full examples are delegated to the bundle files.	4 / 5
Workflow Clarity	The Run section gives a clear sequence (ken-burns each keyframe → hard-concat → mux → burn captions → end card) with a validation checkpoint ('check ffmpeg -filters first' before libass) and an error-recovery rule (shift the subject up if it intrudes into the caption band), but the fully ordered steps live in PIPELINE.md and some checkpoints (e.g., verifying beat timing) are implicit.	4 / 5
Progressive Disclosure	The body is a well-organized overview pointing to verified, clearly signaled, one-level-deep bundle files (scripts/config.example.json, scripts/PIPELINE.md, scripts/README.md), each with a stated role — easy navigation and an appropriate content split.	5 / 5
	Total	17 / 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 highly specific, well-bounded description that comprehensively names every assembly action and pre-empts confusion with adjacent capabilities. Its weaknesses are the terse single-phrase trigger clause and the absence of common user-facing synonyms, plus notable verbosity/density that works against scannability.

Dimension	Reasoning	Score
Specificity	The description enumerates the full pipeline concretely: 'ffmpeg ken-burns (zoompan) + hard cuts', 'Whisper-driven captions burned only mid-sentence', 'PIL brand end card', 'the real audio muxed' — comprehensive, multiple specific concrete actions with no vague filler.	5 / 5
Completeness	Both 'what' (detailed deterministic assembly pipeline) and 'when' ('Use for the editorial-motion-podcast format') are explicitly stated; the 'when' clause is explicit but terse and could name concrete user scenarios, which keeps it below a 5.	4 / 5
Trigger Term Quality	Natural domain keywords are present ('podcast-clip ad', 'podcast MP3', 'captions', 'ken-burns', 'end card'), but the only explicit trigger is the narrow 'Use for the editorial-motion-podcast format', missing common user phrasings like 'podcast video' or 'video ad'.	4 / 5
Distinctiveness Conflict Risk	A clear niche with distinct triggers: it explicitly draws boundaries ('NOT by generative i2v but by DETERMINISTIC ffmpeg', 'keyframes come from create-image-fal', 'never AI-rendered text'), minimizing overlap with sibling render or image-generation 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-editorial-motion-podcast/SKILL.md
Commit: cc3e518

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.