SKILLEMALL.ai
GitHub ↗ RU Sign in

CC talking-head

Requires OFOX_API_KEY — create one at https://app.ofox.ai. Turn a portrait plus a short script into a clip of one person speaking those words to camera. You supply the text and the model generates the voice — audio cannot be uploaded, measured. Defaults to alibaba/wan-3.0-prime rather than this repo's usual seedance-2.5, because seedance-2.5 refuses a real person's photo at submission. Use when a user has a face and some words and wants the face to say them, e.g. "make this headshot read my intro", "a spokesperson clip from this portrait", "have her say this line to camera", "use this avatar to read the announcement". Do not use for a scene between two or more people (see seedance-short-drama), a polished brand or product ad (see seedance-ad-creative), a handheld creator clip (see ugc-ads), or when the words still have to be pulled out of an article and no particular face is required (see explainer).

ClawHub Agent Skills author: OFOX AI v2.0.0 MIT-0 3 files body ≈ 13 019 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

Requires OFOXAPIKEY — create one at https://app.ofox.ai. Turn a portrait plus a short script into a clip of one person speaking those words to camera. You…

As a process C 50/100 · Has gaps — References files that are not bundled: ../ofox-video-core/SKILL.md, ../ofox-video-core/references/prompt-structure.md, ../ofox-video-core/references/creative-brief.md

GeneratorAI and agentsSoftware developmentWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
C
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
64
Run on models
none yet
Process rating
C
50/100
Has gaps
References files that are not bundled: ../ofox-video-core/SKILL.md, ../ofox-video-core/references/prompt-structure.md, ../ofox-video-core/references/creative-brief.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  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

  • warning body-long SKILL.md body ≈ 13019 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../ofox-video-core/SKILL.md
  • warning missing-ref reference to a missing file: ../ofox-video-core/references/prompt-structure.md
  • warning missing-ref reference to a missing file: ../ofox-video-core/references/creative-brief.md
  • warning missing-ref reference to a missing file: ../ofox-video-core/references/approval-gate.md
  • warning missing-ref reference to a missing file: ../ofox-video-core/references/api-params.md
  • warning missing-ref reference to a missing file: references/*.md
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 50/100

Will not run. References files that are not bundled: ../ofox-video-core/SKILL.md, ../ofox-video-core/references/prompt-structure.md, ../ofox-video-core/references/creative-brief.md
  • 0Tools and files. 6 referenced file(s) missing: ../ofox-video-core/SKILL.md, ../ofox-video-core/references/prompt-structure.md, ../ofox-video-core/references/creative-brief.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 21 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 13019 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 100Steps. 40 steps
  • 100Failures and branches. 6 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 22 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (9 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

  • +3Description length 913: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +2Single-language instructions
  • +5Description quotes 4 example trigger phrases
  • +4Description says when NOT to use the skill
  • +4Structure: 34 headings
  • +3Step-by-step instructions: 40 items
  • +4Has examples (11 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.

External checks

ClawHub: clean
The skill is a disclosed Ofox integration for generating consent-based talking-head videos, with clear cost approval steps and no hidden persistence or exfiltration behavior found.
LLM: benign (high) · VirusTotal: · 20 Sept 2026