BB chief-of-staff-onboarding-coach
Coach a newly-hired Chief of Staff (CoS) through their first 90 days — a role that is high-leverage but role-ambiguous, where success is determined more by stakeholder navigation, scope-setting with the principal (CEO/founder), and judgment about which problems to own vs. coordinate vs. ignore than by any specific functional skill. Covers role definition (Force Multiplier vs Special Projects vs Strategic Lead vs Body Double archetypes — these are not interchangeable), the principal interview / re-interview after offer (what success looks like at 30/60/90/180 days, what specifically the CEO wants vs hopes for, how decisions get made today, what's broken, what's untouchable), the first 30 days listening tour (exec stakeholder interviews, board-deck history, OKR review, calendar audit, decision-log review), the first 60 days establishing the operating system (staff meeting cadence, exec sync, board prep, founder 1:1, OKR cycle, monthly business review), the first 90 days picking the 2-3 high-leverage initiatives, the awkwardness of the role (no direct reports often, exec-team peers who don't report to you but you need to influence, the CEO's blind spots that you'll inevitably step into, the COO/CFO turf line), how the role typically goes wrong (becomes glorified EA, gets stuck on ad-hoc tasks, makes enemies on exec team, principal doesn't actually need a CoS), and the natural exit ramps (operational role like COO, functional role like VP of Strategy, or move on). Use when CoS says "starting next week", "first 30 days plan", "principal expectations unclear", "exec team confused about my role", "what should I be doing", "OKR cycle starts Monday and I just got here". Triggers on phrases like "Chief of Staff", "CoS onboarding", "founder's CoS", "CEO's CoS", "Force Multiplier role", "Special Projects", "exec team navigation", "first 90 days", "operating cadence", "staff meeting", "exec sync", "1:1 cadence", "board prep", "principal", "primary".
As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1970 chars, limit 1024 - note
description-budgetdescription takes 1970 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 104 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3569 tokens
- 100Progress reporting. Reports progress
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1970: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 21 example trigger phrases
- +4Structure: 31 headings
- +3Step-by-step instructions: 104 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.