CtrlK
BlogDocsLog inGet started
Tessl Logo

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 2-tone editorial-illustration keyframes 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.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/capabilities/render-editorial-motion-podcast/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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 well-organized, information-dense contract with excellent progressive disclosure to real bundle files, but it lacks assembled executable commands and presents its workflow as rules rather than an explicitly checkpointed step sequence.

Suggestions

Provide at least one complete, copy-pasteable ffmpeg command (e.g. a full ken-burns segment + hard-concat + mux invocation) so the fragments become a runnable unit rather than prose.

Reframe the Contract as a numbered step sequence with explicit validation checkpoints (validate after each stage) instead of a list of rules, to lift workflow clarity above 2.

Move the longer justifications ('Seedance/Kling are photoreal-trained...', 'crossfades ghost two drifting cages...') into PIPELINE.md, keeping only the rule and its trigger inline.

DimensionReasoningScore

Conciseness

The body is dense and largely free of generic padding, but multiple explanatory asides (e.g. 'Seedance/Kling are photoreal-trained and invent naturalistic middle states that collapse the 2-tone look', 'crossfades ghost two drifting cages through each other') push it past minimal, matching 'mostly efficient but could be tightened'.

2 / 3

Actionability

Concrete flags and parameters are scattered throughout (e.g. '-map 0:v:0 -map 1:a:0', '1.0→~1.06×, 24fps', 'end = min(last_word_end + ~0.15, next_start - 0.03)', "enable='between(t,st,en)'") but they are prose fragments rather than assembled executable commands or complete code blocks, matching 'some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

The pipeline order is stated (ken-burns → hard-concat → mux → captions → end card) with a 'check ffmpeg -filters first' checkpoint and a libass/overlay fallback loop, but it is a rules contract rather than a numbered sequence with explicit validation checkpoints, and the full step sequence is deferred to PIPELINE.md — matching 'steps present but checkpoints implicit'.

2 / 3

Progressive Disclosure

Clearly signals three real one-level-deep references — 'scripts/config.example.json is the worked example', 'scripts/PIPELINE.md maps every config block to its source step', 'scripts/README.md documents the free assembly' (all confirmed to exist) — with a concise overview split into well-organized sections.

3 / 3

Total

9

/

12

Passed

Description

85%

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 complete with an explicit use-trigger and a distinct niche, but its heavy reliance on internal/technical jargon limits the quality of natural trigger terms a user would actually say.

Suggestions

Add natural-language trigger phrasings users would actually say (e.g. 'podcast clip ad', 'short video from a podcast quote', 'New- Yorker-style moving illustration') alongside the technical terms.

Trim the dense parenthetical technical detail (e.g. 'NOT by generative i2v but by DETERMINISTIC ffmpeg ken-burns (zoompan)') from the description to improve readability and trigger-term quality.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "carries the narrative", "keyframes are animated... by DETERMINISTIC ffmpeg ken-burns (zoompan) + hard cuts", "audio muxed", "captions burned only mid-sentence", "closed on a PIL brand end card" — matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers what it does (the full assembly chain) and when to use it via "Use for the editorial-motion-podcast format", satisfying the both-what-and-when-with-explicit-triggers anchor.

3 / 3

Trigger Term Quality

Contains some relevant terms ("podcast-clip ad", "editorial-motion-podcast format") but is dominated by internal jargon ("i2v", "zoompan", "ken-burns", "DETERMINISTIC ffmpeg") and lacks common natural-user phrasings, matching 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

Targets a clearly defined niche (editorial-motion podcast format) with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
gooseworks-ai/goose-skills
Reviewed

Table of Contents

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.