BB nex-ghostwriter
Meeting follow-up email drafter. Dump your meeting notes and get a polished follow-up email in seconds. Log the meeting (who attended, what was discussed, action items, next steps, deadlines), then the tool generates a structured follow-up email ready to send. Supports five tone presets: professional, friendly, formal, casual, direct. Regenerate the same meeting as a different tone with one command. Tracks which drafts you sent and which you skipped. Stores contacts with preferred greetings so emails feel personal, not templated. Generates both client-facing follow-up emails and internal team recaps. Handles action items with owners and deadlines, next steps, target dates. Full-text search across all meetings. Statistics on meetings by type, by client, by month. Export to CSV or JSON. Works for agencies (bureaus), consultants, freelancers (freelancers), sales teams (verkoopteams), account managers, project managers, founders (oprichters), and anyone who has meetings and hates writing follow-up emails. Meeting recap, vergaderingsverslag, opvolgmail, follow-up email, meeting summary, notulen, action items, actiepunten, vergadering, klantgesprek, sales call, client call, meeting notes, email drafter, email generator, meeting tracker, follow-up tracker, recap email.
As a process B 72/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1282 chars, limit 1024
Process rating: all ten parameters 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1919 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)
- +3Description length 1282: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 22 headings
- +3Step-by-step instructions: 24 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.