BB mindmap-generator
Generates visual mindmap images from conversations, goals, decisions, and daily priorities — delivered as PNG images viewable directly in Telegram. Use when asked to visualize, map out, or break down topics, priorities, decisions, meeting notes, or weekly reviews.
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Exfiltration
exfil-webhook-urlscripts/generate_and_send.sh:61Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \placeholder -
low Exfiltration
net-credential-usescripts/generate_and_send.sh:61Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \vendor-host -
low Dangerous commands
cmd-privilegescripts/render_mindmap.sh:41Privilege escalation / world-writable permissions (string literal in code, not executed)"--disable-setuid-sandbox",
code literal -
low Exfiltration
exfil-webhook-urlscripts/send_telegram_photo.sh:51Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)TELEGRAM_API="https://api.telegram.org/bot${BOT_TOKEN}/sendPhoto"placeholder -
low Exfiltration
exfil-webhook-urlskill-card.md:33Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)- [Telegram Bot API sendPhoto Endpoint](https://api.telegram.org/bot${BOT_TOKEN}/sendPhoto) <br>placeholder
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 37 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1809 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)
- -42 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 264: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 37 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.