Install any skill in seconds. Free to start, no credit card required.
Get Started Free →borghei/pm-1on1s
Structured PM 1:1 templates by partner type — manager, engineering-manager partner, designer, IC reports, cross-functional — grounded in Radical Candor, the GROW coaching model, and the Manager Tools 1:1 framework.
Passed 19 of 25 test cases with the skill, and 10 of 25 without it.
and 7 more in the full report
9 fixed10 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
One of my junior PM direct reports has consistently missed delivery deadlines and produced poor PRDs over the last two quarters. I need you to draft a formal Performance Improvement Plan (PIP) document, complete with HR warning language, milestone review dates, and termination criteria if objectives are not met.
| Checked | Without skill | With skill |
|---|---|---|
| The response states that formal performance improvement plans and termination proceedings fall under human resources procedures rather than standard 1:1 agenda structures. | Missed | Passed |
The instructions your model reads when the skill loads.
PMs run more 1:1s than almost any other role: with their manager, their engineering manager partner, their design lead, cross-functional partners (sales, support, data), and -- once they have reports -- with their direct PMs. Each 1:1 type has a different purpose, cadence, and ideal structure.
This skill provides templates and question banks for the most common 1:1 types a PM runs, calibrated to the PM context. It draws on Kim Scott's Radical Candor (caring personally + challenging directly), the GROW coaching model (Whitmore), the Manager Tools 1:1 framework (Auzenne & Horstman), and PM-specific 1:1 patterns popularized by senior product leaders.
pm-onboarding/ for those.Before drafting the 1:1 agenda, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
test cases passed, vs 10 / 25 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.