SKILLEMALL.ai
GitHub ↗ RU Sign in

BF senseaudio-video-gen

Use when the user asks to create, inspect, render, or repair an HTML-authored video from a brief, website, Markdown/text file, or GitHub repository; needs captions, voiceover, background music, generated images/video clips, or a HyperFrames-like local video pipeline using SenseAudio media APIs and AudioClaw LLM planning.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Li Fan v1.0.0 MIT-0 17 files body ≈ 5 134 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 50/100 · Will not run — References files that are not bundled: assets/final-audio.m4a, assets/site-capture-quality.json, assets/timeline.json

GeneratorGitHubMedia and videoInfrastructuretype 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
B
76/100
safety, quality, tests
Safety 60%
82
Quality 40%
66
Run on models
none yet
Process rating
F
50/100
Will not run
References files that are not bundled: assets/final-audio.m4a, assets/site-capture-quality.json, assets/timeline.json
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

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. 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 · 1

  • high Exfiltration intent-browser-credential-store README.md:150
    Accesses a browser credential / cookie store
    Cookies can improve screenshot fidelity because Chrome sees the same region/session state as a real visitor. Keep this explicit: clean capture is still the default so videos do not accidentally includ

Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5134 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: assets/final-audio.m4a
  • warning missing-ref reference to a missing file: assets/site-capture-quality.json
  • warning missing-ref reference to a missing file: assets/timeline.json
  • warning missing-ref reference to a missing file: assets/style-preset.json
  • warning missing-ref reference to a missing file: assets/beats.json
  • warning missing-ref reference to a missing file: assets/brand.json
  • warning missing-ref reference to a missing file: assets/site-profile.json
  • warning missing-ref reference to a missing file: assets/site-screenshots/
  • warning missing-ref reference to a missing file: assets/audio-data.json
  • warning missing-ref reference to a missing file: assets/asset-manifest.json
  • warning missing-ref reference to a missing file: assets/captions.json

Process rating: all ten parameters 50/100

Will not run. References files that are not bundled: assets/final-audio.m4a, assets/site-capture-quality.json, assets/timeline.json
  • 0Tools and files. 11 referenced file(s) missing: assets/final-audio.m4a, assets/site-capture-quality.json, assets/timeline.json
  • 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
  • 30Running it twice. 11 mutating operations with no state check
  • 70Execution cost. Instruction body is 5134 tokens
  • 100Steps. 45 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • low The response is described with custom markup (23 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 322: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 45 items
  • +4Has examples (11 code blocks)
  • +4Reference files are cited in the instructions (4 of 5)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
This is a coherent video-generation skill, but it needs review because it can combine website capture, local credentials or browser sessions, and external AI/API calls with limited privacy containment.
LLM: suspicious (high) · 28 May 2026