BC voice-lead-recovery
Turn voicemails and sales-call recordings into recovered revenue. What it does: transcribes each voicemail or call, extracts requested service, urgency, budget signals, objections, and promised follow-up, remembers the caller across every prior contact, and prepares the next action for the agent. Who pays and why: contractors, home-services, and agencies pay because an unanswered voicemail is a quote never sent, and the front desk forgets who called by the time anyone replies. Pilot price: $399 one-time for a 14-day missed-call recovery pilot on your real voicemail inbox. Use when an agent handles inbound call or voicemail leads for contractors, agencies, or service businesses. Requires a BlueColumn API key (bc_live_*).
Turn voicemails and sales-call recordings into recovered revenue.
As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Turn voicemails and sales-call recordings into recovered revenue. … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 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 640 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
- +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 729: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.