SKILLEMALL.ai
GitHub ↗ RU Sign in

AB glmv-caption

Generate captions (descriptions) for images, videos, and documents using ZhiPu GLM-V multimodal model series. Use this skill whenever the user wants to describe, caption, summarize, or interpret the content of images, videos, or files. Supports single/multiple inputs, URLs, local paths, base64 (images only), and optional structured JSON output via response_format + system prompt.

ClawHub Agent Skills author: TriDefender v1.0.2 MIT-0 5 files body ≈ 3 273 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 71/100 · Nearly there — weak spots: consistency, running it twice, progress reporting

GeneratorCloudflareGitHubMedia and videoInfrastructureAI and agentstype 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
92/100
safety, quality, tests
Safety 60%
98
Quality 40%
82
Run on models
none yet
Process rating
B
71/100
Nearly there
Progress reporting w 2
0
Running it twice w 4
30
Consistency w 8
40
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Exfiltration exfil-webhook-url README.md:30
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      3. `cloudflared tunnel` (Cloudflare's free quick-tunnel, no account needed) exposes the server as a public HTTPS URL like `https://some-words.trycloudflare.com/your…mp4`
      placeholder
    • low Exfiltration exfil-webhook-url SKILL.md:137
      Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
      > 3. 获得一个形如 `https://xxx-xxx.trycloudflare.com/your…mp4` 的临时公网 URL
      placeholder

    Files scanned: 5. 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 71/100

    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 5 mutating operations with no state check
    • 40Consistency. Frontmatter name (glmv-caption) differs from the folder (glmv-caption-tunnel)
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 38 steps
    • 100Failures and branches. 3 branches, has a failure section
    • 100Execution cost. Instruction body is 3273 tokens

    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)
    • -212 emoji in the instructions: noise for the model
    • -31 of 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 382: enough signal without eating the budget
    • +4Structure: 25 headings
    • +3Step-by-step instructions: 38 items
    • +3Output format is stated explicitly
    • +4Has examples (21 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

    External checks

    ClawHub: suspicious
    This captioning skill is mostly coherent, but local videos and documents can be automatically exposed through a temporary public Cloudflare tunnel without a strong per-use consent gate.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026