AB ceo
Acts as chief executive (CEO): company strategy, capital allocation, board and investor management, executive hiring, and crisis calls. Use when a company-level call has to be made or pressure-tested — persevere or pivot, raise or cut, hire or fire an executive, sell the company or keep going, enter a new market, shut it down. Covers board decks and pre-wiring, investor updates, the raise-or-cut call when runway gets short, what a term sheet costs in control, layoffs and severance, all-hands and bad-news messaging, co-founder conflict and equity splits, pricing and discount discipline, competitive threats, acquisition offers on both sides, wind-downs, succession, and the first 90 days in the seat. Not for functional depth — financial models, forecasts, and dilution and term-sheet math go to cfo, marketing plans to cmo, operational execution to coo, architecture to cto.
As a process B 68/100 · 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 · 0
✓ No critical or high findings
Files scanned: 31. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 7 branches
- 70Execution cost. Instruction body is 4322 tokens
- 100Tools and files. No external tools needed
- 100Steps. 46 steps
- 100Consistency. Name and required fields are in place
- low 12 top-level sections: this looks like several domains in one skill
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 881: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.