SKILLEMALL.ai
GitHub ↗ RU Sign in

AC transcribee

Transcribe YouTube videos and local audio/video files with speaker diarization. Use when user asks to transcribe a YouTube URL, podcast, video, or audio file. Outputs clean speaker-labeled transcripts ready for LLM analysis.

modbender/skill-library-mcp Agent Skills author: modbender MIT 7 files · 1 script body ≈ 282 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Transcribe YouTube videos and local audio/video files with speaker diarization.

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

AnalyzerYouTubeMedia 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%
93
Quality 40%
87
Run on models
none yet
Process rating
C
63/100
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

    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 · 7

    ✓ No critical or high findings

    Medium and low: 7
    • low Exfiltration read-dotenv CLAUDE.md:16
      Reads a .env file
      cp .env.example .env
    • low Secrets in code secret-high-entropy-token pnpm-lock.yaml:104
      High-entropy token-like string (may be an id, hash or a credential)
      resolution: {integrity: sha5…SN3+hY8mo/i4QX…IGQ==}
    • low Secrets in code secret-high-entropy-token pnpm-lock.yaml:158
      High-entropy token-like string (may be an id, hash or a credential)
      resolution: {integrity: sha5…xyU+j7+tId//iHXU2f/lN5A…1O6+7A==}
    • low Secrets in code secret-high-entropy-token pnpm-lock.yaml:164
      High-entropy token-like string (may be an id, hash or a credential)
      resolution: {integrity: sha5…ylb+vIUV…Mqd/vSbg…Vk4+7Afhw==}
    • low Secrets in code secret-high-entropy-token pnpm-lock.yaml:176
      High-entropy token-like string (may be an id, hash or a credential)
      resolution: {integrity: sha5…ngb+E5aS…5yG/kLKQ==}
    • low Secrets in code secret-high-entropy-token pnpm-lock.yaml:182
      High-entropy token-like string (may be an id, hash or a credential)
      resolution: {integrity: sha512-i1sW+1i+oWvQ…y8U+uuga…xRg==}
    • low Exfiltration read-dotenv README.md:70
      Reads a .env file
      cp .env.example .env

    Files scanned: 7. 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

    • 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
    • 50Failures and branches. 0 branches, has a failure section
    • 60Result and completion. Output format stated, no completion criterion
    • 75Steps. 3 steps
    • 100Tools and files. No external tools needed
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 282 tokens
    • 100Running it twice. No mutating operations

    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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 224: enough signal without eating the budget
    • +4Structure: 6 headings
    • +3Step-by-step instructions: 3 items
    • +3Output format is stated explicitly
    • +4Has examples (2 code blocks)

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