SKILLEMALL.ai
GitHub ↗ RU Sign in

AB lipsync

Drive a face's mouth from a separate audio track, built into Genspark — no API key, no external account. Two native lip-sync routes on the Genspark sandbox: animate a portrait still into a talking head from an audio file (OmniHuman), or mouth-swap a voiceover onto an existing video while preserving the rest of the frame (Sync Labs sync v2). Turn a headshot + a voiceover into a virtual presenter, dub a brand video into another language, or build a UGC ad from one photo. Runs via the `gsk video_generation` CLI. Triggers on "lip sync video", "lipsync", "make this video speak", "match audio to mouth", "dub a video", "drive avatar from audio", "sync lips to voice", "talking head from photo", "voiceover sync", or any explicit ask to drive a face's mouth from an audio track.

genspark Agent Skills author: Genspark 1 file body ≈ 2 246 tokens Open the sourcegenspark.ai↗ analyzed 3 d ago

As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting

IntegrationMedia and videotype and topics are labelled automatically from the skill text
Runs in: Genspark 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
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
88
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    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: 1. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "displayName"
    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 66/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 65Failures and branches. 3 branches
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 31 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2246 tokens
    • 100Running it twice. No mutating operations
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 10 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (4 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)
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +5Description quotes 9 example trigger phrases
    • +3Description length 778: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 31 items
    • +4Has examples (3 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.