AB vibe-notion
Interact with Notion using the unofficial private API - pages, databases, blocks, search, users, comments
As a process B 69/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5912 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5912 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 29 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 105: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 32 headings
- +3Step-by-step instructions: 29 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.
External checks
ClawHub: suspicious
This Notion skill is clearly about Notion automation, but it needs Review because it uses the user's desktop session token and can perform broad or bulk workspace changes without strong confirmation boundaries.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026