BB meeting-autopilot
Turn meeting transcripts into operational outputs — action items, decisions, follow-up email drafts, and ticket drafts. Not a summarizer. An operator. Accepts VTT, SRT, or plain text. Multi-pass LLM extraction.
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
GeneratorInfrastructureAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Instruction override
en-ignore-previousSECURITY.md:50Instruction-override phrase ("ignore previous instructions") (negated — the text forbids it)| Malicious transcript content triggers LLM injection | **Medium** | LLM prompts are structured with clear system/user separation. User content is clearly delineated as "TRANSCRIPT:" block. Cannot ove
negated
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 46 steps
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1245 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
- -31 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 210: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 46 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.
External checks
ClawHub: clean
This skill does what it says: it processes meeting transcripts with Anthropic or OpenAI and saves extracted meeting history locally, with those behaviors disclosed.
LLM: benign (high) · VirusTotal: benign · 28 May 2026