AB booking-manager
AI-powered booking manager that connects to any existing booking system and lets business owners manage appointments through their phone (Telegram, WhatsApp, etc.). Use when: setting up an AI assistant to monitor bookings, notify owners of new enquiries, confirm/reschedule/cancel appointments conversationally, send professional customer emails with calendar invites, and provide schedule summaries. Works with any data source: SQL databases (PostgreSQL, SQLite/Turso, MySQL), REST APIs (Calendly, Square, Fresha), Google Sheets, or webhooks. Triggers on: "booking assistant", "appointment manager", "manage bookings via phone", "AI receptionist", "booking notifications", "salon booking system".
As a process B 73/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting
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: 6. 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 "repository"
Process rating: all ten parameters 73/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 51 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2892 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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 6 example trigger phrases
- +3Description length 697: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.