AB picasso-tiktok
Full TikTok/Reels video pipeline: script → TTS voiceover (ElevenLabs) → HeyGen talking avatar → auto-subtitles (Whisper) → ffmpeg compose → 1080x1920 final video. Also supports AI B-roll generation with Runway Gen-4.5 when no source video exists. ✅ USE WHEN: - Creating TikTok or Instagram Reels from scratch with voiceover - Turning a news article, topic, or script into a 9:16 video - Adding a talking avatar to any video - Generating AI B-roll clips (Runway Gen-4.5) and editing into a Reel ❌ DON'T USE WHEN: - You only need an image (use nano-banana-pro) - You only need TTS audio (use ElevenLabs directly) Required env vars: ELEVENLABS_API_KEY, ELEVENLABS_VOICE_ID, HEYGEN_API_KEY, YOUR_HEYGEN_AVATAR_ID, OPENAI_API_KEY, REPLICATE_API_TOKEN Required system tools: ffmpeg, yt-dlp, Python 3
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, progress reporting
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 2. 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 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3105 tokens
- 100Running it twice. No mutating operations
- low 12 top-level sections: this looks like several domains in one skill
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
- -5TODO / placeholder text left in the skill
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 796: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (22 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.