BB video-to-markdown
Analyze any YouTube, Facebook, or Instagram video URL and generate a comprehensive Markdown reference document by combining AI vision analysis of extracted frames with full video transcription. Use this skill when a user shares a video URL and wants a summary, notes, breakdown, or reference document from it. Triggers on "analyze this video", "summarize this video", "break down this video", "create notes from this video", "watch this video and explain it", "video to markdown", "pull notes from this", or any request to extract knowledge from a video. Also triggers automatically when a user pastes a YouTube, Instagram, or Facebook URL and asks what it's about or wants to understand its content — even without explicit keywords. Especially valuable for educational content, trading tutorials, technical demos, or any video where charts, diagrams, and on-screen visuals tell a different story than the narration alone.
Analyze any YouTube, Facebook, or Instagram video URL and generate a comprehensive Markdown reference document by combining AI vision analysis of extracted…
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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
-
high Exfiltration
intent-browser-credential-storereferences/platforms.md:17Accesses a browser credential / cookie store**Note:** Chrome cookies are encrypted (app-bound since Chrome 127) and cannot be reliably extracted. Use Firefox.
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 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1135 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 922: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 12 headings
- +3Step-by-step instructions: 12 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.