Agent Skills
› mohitagw15856/pm-claude-skills
› onboarding-buddy-plan
onboarding-buddy-plan
GitHub设计新员工入职伙伴制度，明确伙伴负责提供背景信息与心理安全感而非培训。生成角色定义、30天接触计划、首周脚本及升级机制，避免角色错配，解决新人孤立与隐性困难问题。
Trigger Scenarios
设置入职伙伴项目
我是新人的伙伴该做什么
入职仅靠文档缺乏人际互动
新人陷入沉默困境
Install
npx skills add mohitagw15856/pm-claude-skills --skill onboarding-buddy-plan -g -y
SKILL.md
Frontmatter
{
"name": "onboarding-buddy-plan",
"homepage": "https:\/\/mohitagw15856.github.io\/pm-claude-skills\/skill\/onboarding-buddy-plan.html",
"metadata": {
"openclaw": {
"emoji": "🧠"
}
},
"description": "Design the buddy system that makes new-hire onboarding human — the buddy's actual job (context and safety, not training), the 30-day touchpoint plan, the ask-me-anything contract, and the buddy selection that avoids the two classic miscasts. Use when asked set up an onboarding buddy program, I'm buddying the new hire what do I do, our onboarding is docs with no humans, or the new person is drowning quietly. Produces the buddy role definition, the touchpoint schedule, the first-week script, and the escalation line."
}
Onboarding Buddy Plan Skill
Onboarding docs answer the documented questions; the buddy exists for the undocumented ones — "who actually decides this," "is it normal that nobody replied," "can I ask the VP directly or is that weird" — the questions new hires won't ask their manager because every one feels like an admission. The buddy's job is context and psychological safety, explicitly not training (that's the manager's and the docs' job — miscasting the buddy as trainer burns them out and confuses accountability). The plan makes the role concrete: selection, the touchpoint arc, the safety contract, and the line where buddy concerns route onward.
What This Skill Produces
- The role definition — what the buddy owns (context, norms, safety-net), what they don't (tasks, evaluation, training)
- The touchpoint arc — day 1, daily-ish week one, weekly to day 30, with each conversation's actual purpose
- The first-week script — the walkthroughs that matter: the unwritten norms, the who's-who, the working-agreements tour
- The escalation line — what the buddy notices and where it goes (struggling ≠ snitching; the line is drawn carefully)
Required Inputs
Ask for these if not provided:
- The new hire's shape — role, seniority, remote/local; a senior remote hire needs org-context density, a junior local one needs more safety-net
- The buddy candidates — the selection rules screen for the two miscasts: not the manager (kills the safe-questions channel), not the busiest star (no time = guilt on both sides); the right buddy is adjacent-team-or-same-team, tenured 1–3 years (remembers being new), and genuinely willing
- What onboarding already covers — the docs/training that exist; the buddy fills around them, not instead of them
- The team's honest quirks — the unwritten rules a newcomer would violate innocently ("the 9am 'standup' is optional but the Thursday one isn't") — this list is the buddy's curriculum
Framework: The Plan Rules
- Context, not training: the buddy explains how things actually work — the org's real decision paths, the personalities, the norms nobody wrote — and never owns task competence. The split stated to everyone: manager owns performance, docs own process, buddy owns "the water you're swimming in."
- The safety contract is explicit: day one, said out loud: "No stupid questions to me — I'm not evaluating you, and what you ask me stays between us [with the safety-critical exception noted]." The contract is what unlocks the questions that actually block new hires; implied safety unlocks nothing.
- Touchpoints front-loaded, then tapering: day 1 (the tour: people, norms, tools, the where-things-live map) → short daily-ish check-ins week one ("what was confusing today?" — the best question in onboarding) → weekly through day 30 → then organic. Each check-in's purpose is surfacing confusion early, not status.
- The buddy teaches the askable map: who to ask what (and who not to ping directly), which channels are alive, how office-hours-design-style access works here — converting the org from a directory into a navigable social graph. This map is the single highest-value transfer of the whole program.
- The escalation line, drawn in advance: the buddy will notice things — drowning, mis-set expectations, a manager mismatch. The rule: patterns that block success go to the manager as advocacy ("she needs access nobody's granted; three days blocked"), personal confidences don't, and the new hire knows the rule too. A buddy who reports everything is a spy; one who reports nothing wastes the early-warning position.
Output Format
Buddy Plan: [new hire] × [buddy] — 30 days
The Role Split
[Buddy owns: … · Manager owns: … · Docs own: … — stated to all three]
The Arc
| When | Touchpoint | Its purpose |
|---|---|---|
| [Day 1 tour → week-1 dailies → weekly to 30 · the what-was-confusing question standing] |
First-Week Curriculum
[The unwritten norms list · the askable map · the agreements/handbook tour]
The Safety Contract + Escalation Line
[The day-one words · what routes to the manager (patterns-blocking-success, as advocacy) · what never does]
Quality Checks
- The buddy is neither the manager nor the overloaded star
- The safety contract is spoken, with its exception honest
- Touchpoints front-load and each has a purpose beyond "checking in"
- The unwritten-norms list and askable map are actually written for the buddy
- The escalation line is known to both buddy and new hire
Anti-Patterns
- Do not cast the manager as buddy — it deletes the safe channel the role exists for
- Do not make the buddy the trainer — accountability blurs and the buddy burns out
- Do not run buddyship on vibes — the arc and curriculum are what separate it from "lunch once"
- Do not let the buddy report confidences — one leak ends the contract for the whole program
- Do not stop at day 5 — week three is when the real questions arrive, to whoever's still showing up
Version History
- 471c606 Current 2026-07-22 13:33
