AC notion-coworker
An autonomous Notion coworker agent that monitors Gmail for Notion comment mentions (from notify@mail.notion.so), reads the comment to understand what's being asked, researches an answer using memory, conversation history, the Notion workspace, and optionally the web, then replies directly in the Notion discussion thread. All research gathered is documented as a subpage. Use this skill whenever the user says things like "check my Notion mentions", "handle my Notion comments", "process Notion notifications", "act as my Notion coworker", "respond to mentions", "check notify emails", or any variation of wanting an agent to autonomously read and respond to Notion comment threads. Also trigger when the user pastes a Notion page URL and asks you to "reply to the comment", "handle the discussion", or "check what they asked me". Even if the user just says "check my mentions" or "any new comments?" without saying "Notion", trigger this skill if the user has used it before.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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 · 0
✓ No critical or high findings
Files scanned: 2. 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 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 28 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1993 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 978: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.