SKILLEMALL.ai
GitHub ↗ RU Sign in

CD vox-collage

How to turn ONE topic into a Vox-style paper-collage explainer / ad video — a punchy narrated short where each beat is a torn-paper collage POSTER that comes alive, with VO, music and captions. A craft overlay on the standard pipeline: the look is BORN in the image (a rich layered collage poster per beat — text-to-image, 5-part prompt structure, headline baked in), then a FLAT-SAFE "living poster" motion pass animates it, then hard-cut assembly. Supplies the one mandatory beat-map approval gate, the density rule (6+ separate cut-out pieces filling the frame, NOT one sticker on a plain bg), the flat-safe i2v constraint set (ONE smooth 2D camera move, ~5% amplitude, stability anchors on text/layout, banned warp moves) that is WHY seedance works for flat art, and anti-monotony hard cuts (adjacent beats never share a camera move; static reserved for the payoff). Works for ANY topic / product / person + ANY era-matched aesthetic. Ported from vox-director by Alisa Qian. USE WHEN the user asks for a "vox video", "collage explainer", "paper-collage animation", "motion collage", "sticker explainer", "make a collage ad", "torn-paper animated explainer", "scrapbook-style tribute", or wants to turn a topic / product / person into a punchy narrated collage video — even if they don't say "Vox". This is a niche SKILL (generalized craft overlay), not a remix TEMPLATE. For "remix this exact collage video but swap X", use the remix path in docs/skills-vs-templates.md.

alecs5am/ralphy Agent Skills author: alecs5am 3 files body ≈ 4 680 tokens Open the sourcegithub.com↗ analyzed 11 h ago

How to turn ONE topic into a Vox-style paper-collage explainer / ad video — a punchy narrated short where each beat is a torn-paper collage POSTER that comes…

As a process D 49/100 · Unfinished process — References files that are not bundled: ../carousel/SKILL.md, ../poster/SKILL.md, ../analog-horror-psa/SKILL.md

ProcedureAI and agentsMedia and videotype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
81/100
safety, quality, tests
Safety 60%
100
Quality 40%
52
Run on models
none yet
Process rating
D
49/100
Unfinished process
References files that are not bundled: ../carousel/SKILL.md, ../poster/SKILL.md, ../analog-horror-psa/SKILL.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: ralphy

How to improve

  1. Shorten the description to 1024 characters.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1474 chars, limit 1024
  • warning missing-ref reference to a missing file: ../carousel/SKILL.md
  • warning missing-ref reference to a missing file: ../poster/SKILL.md
  • warning missing-ref reference to a missing file: ../analog-horror-psa/SKILL.md
  • warning missing-ref reference to a missing file: ../../../docs/skills-vs-templates.md
  • warning missing-ref reference to a missing file: ../seedance-prompts/SKILL.md
  • warning missing-ref reference to a missing file: ../../../.agents/skills/art-director/SKILL.md
  • warning missing-ref reference to a missing file: ../../../.agents/skills/editor/SKILL.md
  • warning missing-ref reference to a missing file: ../hyperframes/SKILL.md
  • warning missing-ref reference to a missing file: scripts/*.py
  • note frontmatter-key unknown frontmatter key "namespace"

Process rating: all ten parameters 49/100

Will not run. References files that are not bundled: ../carousel/SKILL.md, ../poster/SKILL.md, ../analog-horror-psa/SKILL.md
  • 0Tools and files. 9 referenced file(s) missing: ../carousel/SKILL.md, ../poster/SKILL.md, ../analog-horror-psa/SKILL.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 8 mutating operations with no state check
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 4680 tokens
  • 100Steps. 47 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1474: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 10 example trigger phrases
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 47 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.