BA Meetings
Designs, runs, records, and closes out meetings: agendas, facilitation, decisions, minutes, and follow-up. Use when preparing or chairing a 1-on-1, standup, retro, planning session, all-hands, kickoff, design review, client or board call, or offsite; when a meeting ends with no decision, runs long, or relitigates last week; when action items vanish, owners are vague, or nobody chased them; when a transcript or raw notes must become a record with owners and dates; when a recap or formal minutes have to go out; when a recurring meeting has outlived its purpose or the calendar is too full to build anything; when an invite should be declined or replaced by a written update; when a remote or hybrid room leaves half the attendees silent; and when bad news, conflict, or an escalation has to be handled live. Not for note apps and vaults (`notes`), day and calendar planning (`calendar-planner`), or the address book itself (`people`).
As a process A 81/100 · Runs to the end — weak spots: inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 6915 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 81/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 19 mutating operations with no state check
- 70Failures and branches. 6 branches
- 70Execution cost. Instruction body is 6915 tokens
- 100Tools and files. No external tools needed
- 100Steps. 48 steps
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +3Description length 938: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 48 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.