BB nex-crm
Chat-native Customer Relationship Management system designed for one-person agencies, freelancers, and small Belgian businesses managing multiple client relationships and complex sales pipelines. Track all prospects and leads through the complete sales funnel with stage progression (lead, contacted, demo scheduled, demo completed, proposal sent, negotiation, won, lost, churned) along with activity logging, follow-up reminders, and comprehensive interaction history. Automatically remember conversation context and activity details from natural language input, store lead source information with categorization (web scraping, referrals, inbound inquiries, outreach, events, website submissions), and assign priority levels (hot, warm, cold) to prospects. Monitor your sales pipeline with visual ASCII bar charts showing deal counts and revenue potential per stage, track win rates and average deal sizes, identify revenue forecasts, and discover stale prospects who haven't been contacted in over two weeks. Log all activities (calls, emails, meetings, demos, proposals) with timestamps and detailed summaries, set follow-up reminders with configurable dates or day counts, manage interaction channels (Telegram, email, phone), export prospect data for external reporting. Perfect for Belgian SMEs, web agencies, and service providers who need lightweight CRM without expensive subscriptions.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-redirectable-api-keylib/config.py:112Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Dangerous commands
cmd-shell-rcsetup.sh:110Writes to a shell startup fileecho " Add this to your ~/.bashrc or ~/.zshrc"
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1395 chars, limit 1024
Process rating: all ten parameters 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash) 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. 32 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2127 tokens
- 100Running it twice. Mutating operations check current state
- 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 1395: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 22 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.