AB notebooklm-skill-factory
Orchestrate NotebookLM research into SKILL.md generation and Claude Code validation in a single automated pipeline. Use when user asks to create a new Claude Code skill from source materials (PDFs, articles, YouTube, URLs), batch-produce skills, or convert domain knowledge into reusable skills. Trigger phrases -- create a skill for X, make me a skill that does X, turn this into a skill, generate a skill from these sources, build a skill factory pipeline. NOT for manual skill editing (use skill-creator) or NotebookLM-only tasks (use notebooklm directly).
As a process B 70/100 · Nearly there — weak spots: result and completion
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: 6. 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
- 0Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 37 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1168 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 559: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.