SKILLEMALL.ai
RU Sign in

AC varg-ai

Generate AI videos, images, speech, and music using varg. Use when creating videos, animations, talking characters, slideshows, product showcases, social content, or single-asset generation. Supports zero-install cloud rendering (just API key + curl) and full local rendering (bun + ffmpeg). Triggers: "create a video", "generate video", "make a slideshow", "talking head", "product video", "generate image", "text to speech", "varg", "vargai", "render video", "lip sync", "captions".

ClawHub Agent Skills author: Alex v2.0.9 MIT-0 14 files · 1 script body ≈ 2 979 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorMedia and videotype 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
A
91/100
safety, quality, tests
Safety 60%
91
Quality 40%
91
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: varg-ai (ClawHub)

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash(curl:*)
      allowed-tools: Bash(bun:*) Bash(bunx:*) Bash(npx:*) Bash(curl:*) Bash(mkdir:*) Bash(echo:*) Bash(chmod:*) Read Write Edit
    • low Dangerous commands cmd-background-process references/local-render.md:120
      Starts a background / autostarted process
      nohup bunx vargai render video.tsx --verbose > output/render.log 2>&1 &
    • low Dangerous commands cmd-background-process references/templates.md:479
      Starts a background / autostarted process
      nohup bunx vargai render template.tsx --verbose > output/render.log 2>&1 &
    • low Dangerous commands cmd-pipe-to-shell-known-host scripts/setup.sh:187
      Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
      dim "    curl -fsSL https://bun.sh/install | bash"
      code literal
    • low Exfiltration net-credential-use SKILL.md:103
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -s -H "Authorization: Bearer $VARG_API_KEY" https://api.varg.ai/v2/billing/balance
      vendor-host

    Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 63/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 4 mutating operations with no state check
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 18 steps
    • 100Failures and branches. 3 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2979 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • 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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -32 of 2 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +5Description quotes 11 example trigger phrases
    • +3Description length 484: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (15 code blocks)
    • +4Reference files are cited in the instructions (10 of 10)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: suspicious
    This media-generation skill is mostly coherent, but it should go through Review because it handles long-lived API credentials, payment-adjacent account flows, and third-party uploads with insufficient user control and privacy warnings.
    LLM: suspicious (high) · 24 Aug 2026