AC granola-direct-api
Access Granola meeting notes, summaries, transcripts, and attendees via the official Granola public REST API (public-api.granola.ai/v1). Use this skill when the user asks about meetings, meeting notes, Granola, wants to look up what was discussed, find meetings with a specific person, retrieve action items from a meeting, get a transcript, or search recent meeting history. Also trigger when the user mentions "Granola" by name, asks "what did we talk about in [meeting]", "who was in [meeting]", or wants to review meeting summaries. Requires a Granola API key (Business or Enterprise plan).
As a process C 59/100 · 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "permissions" - note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 59/100
- 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. 6 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. 4 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2018 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 594: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.