AC kallyai-api
KallyAI Executive Assistant — AI that handles phone calls (outbound + inbound), email, bookings, research, errands, multi-channel messaging, and phone number management on your behalf. Use when users want to: make/receive calls, manage inbound rules, handle voicemails, provision phone numbers, send email, book restaurants/hotels, search for services, manage calendar, check inbox/messages, handle bills, order food/rides, run errands, check credits/budget, coordinate goals, manage channels (WhatsApp/Telegram/social), run outreach campaigns, referrals, or any delegation task. Triggers on: call, phone, reservation, appointment, email, search, book, find, schedule, cancel, inbox, messages, research, assistant, coordinate, goal, credits, budget, ride, food, errand, bill, dispute, calendar, KallyAI, inbound, receptionist, voicemail, phone number, forward, transfer, takeover, channels, WhatsApp, Telegram, outreach, referral, subscription.
As a process C 58/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, 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: 5. 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 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 4 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2985 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
- +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 944: 120–800 characters recommended
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 29 headings
- +3Step-by-step instructions: 4 items
- +3Output format is stated explicitly
- +4Has examples (23 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.