SKILLEMALL.ai

AC video-metadata-analyzer

Video content analysis pipeline — extract frames, transcribe audio, run LLM visual+audio analysis, synthesize structured Bilibili publish metadata (title, intro, tags, category, cover suggestion). Use when user says '生成投稿元数据', '视频元数据分析', or explicitly requests this skill. ⚠️ API modes send video frames and audio to external LLM providers — see Privacy section.

ClawHub Hermes author: CyberKurry v1.2.0 MIT-0 9 files · 1 script body ≈ 1 728 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice

AnalyzerMedia and videoInfrastructureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
99
Quality 40%
87
Run on models
none yet
Process rating
C
59/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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

✓ No critical or high findings

Medium and low: 1
  • low Secrets in code secret-high-entropy-token README.md:11
    High-entropy token-like string (may be an id, hash or a credential)
    [![ClawHub](https://img.shields.io/badge/ClawHub-video--metadata--analyzer-blue)](https://clawhub.ai/CyberKurry/video-metadata-analyzer) [![GitHub](https://img.shields.io/badge/GitHub-CyberKurry%2Fvid

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 362 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • note frontmatter-key unknown frontmatter key "privacy_notice"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 59/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 5 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Steps. 18 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 1728 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)
  • +2Single-language instructions
  • +3Description length 362: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 18 items
  • +3Output format is stated explicitly
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 5 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

External checks

ClawHub: clean
This is a disclosed video-analysis skill whose main risk is privacy exposure when video frames, audio, transcripts, or generated observations are sent to configured LLM services or another agent.
LLM: benign (high) · 28 May 2026