BD deep-research-to-notebooklm
End-to-end orchestration: Deep Research → NotebookLM content generation. Chains gemini-deep-research and notebooklm-content-creation skills. Supports choosing which NotebookLM artifacts to generate (Audio/Video/Infographics/Slides) and whether to download. Triggers on: deep research podcast, research and generate podcast, 研究并生成播客, deep research notebooklm, research then notebooklm, 做个深度研究再生成播客. Requires: gemini-deep-research skill installed, notebooklm-content-creation skill installed.
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-background-processSKILL.md:248Starts a background / autostarted processnohup bash dr-poll.sh > /dev/null 2>&1 &
-
low Dangerous commands
cmd-background-processSKILL.md:501Starts a background / autostarted processnohup bash nlm-poll.sh > /dev/null 2>&1 &
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (deep-research-to-notebooklm) differs from the folder (jclaw-deep-research-to-notebooklm)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4080 tokens
- 100Steps. 5 steps
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 490: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 5 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.