BD supercall
Make AI-powered phone calls with custom personas and goals. Uses OpenAI Realtime API + Twilio for ultra-low latency voice conversations. Supports DTMF/IVR navigation — the AI can navigate automated phone menus by sending touch-tone digits. Use when you need to call someone, confirm appointments, deliver messages, navigate phone trees, or have the AI handle phone conversations autonomously. Unlike the standard voice_call plugin, the person on the call doesn't have access to gateway agent, reducing attack surfaces.
Make AI-powered phone calls with custom personas and goals.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, failures and branches
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: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 30 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1952 tokens
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 518: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 12 скриптов, ещё 6 не поместились в лимит; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
index.ts | ничего за пределами своей папки |
src/config.ts | ничего за пределами своей папки |
src/dtmf.ts | ничего за пределами своей папки |
src/manager.ts | ничего за пределами своей папки |
src/media-stream.ts | ничего за пределами своей папки |
src/runtime.ts | ничего за пределами своей папки |
src/tunnel.ts | ничего за пределами своей папки |
src/types.ts | ничего за пределами своей папки |
src/utils.ts | ничего за пределами своей папки |
src/voice-mapping.ts | ничего за пределами своей папки |
src/webhook-security.ts | ничего за пределами своей папки |
src/webhook.ts | ничего за пределами своей папки |
29 Oct 2026