AB notebooklm-studio
Import sources (URLs, YouTube, files, text) into Google NotebookLM and generate user-selected artifacts: podcast, video, report, quiz, flashcards, mind map, slides, infographic, data table. Use when the user sends content and asks to generate learning materials, podcasts, videos, or study packages.
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice
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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Dangerous commands
cmd-cron-mentionREADME.md:249Mentions editing / listing crontab# crontab -e
-
low Dangerous commands
cmd-cron-mentionREADME.md:265Mentions editing / listing crontab# crontab -e
-
low Dangerous commands
cmd-cron-mentionREADME.zh-TW.md:249Mentions editing / listing crontab# crontab -e
-
low Dangerous commands
cmd-cron-mentionREADME.zh-TW.md:265Mentions editing / listing crontab# crontab -e
Files scanned: 11. 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 67/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 73 steps, 1 vague phrases
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3683 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 299: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 73 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.