Agent Skillsmohitagw15856/pm-claude-skills › manager-first-90-days

manager-first-90-days

GitHub

为新晋或新任管理者制定前90天行动计划,划分为倾听、决策、执行三阶段。提供1对1访谈问题、团队评估框架及关键文档模板,帮助避免早期判断陷阱,平衡调研与行动。

plugins/pm-people/skills/manager-first-90-days/SKILL.md mohitagw15856/pm-claude-skills

Trigger Scenarios

刚成为经理该做什么 制定新经理前90天计划 接管现有团队 新经理30-60-90计划

Install

npx skills add mohitagw15856/pm-claude-skills --skill manager-first-90-days -g -y
More Options

Non-standard path

npx skills add https://github.com/mohitagw15856/pm-claude-skills/tree/main/plugins/pm-people/skills/manager-first-90-days -g -y

Use without installing

npx skills use mohitagw15856/pm-claude-skills@manager-first-90-days

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill manager-first-90-days -a claude-code -g -y

安装 repo 全部 skill

npx skills add mohitagw15856/pm-claude-skills --all -g -y

预览 repo 内 skill

npx skills add mohitagw15856/pm-claude-skills --list

SKILL.md

Frontmatter
{
    "name": "manager-first-90-days",
    "description": "Plan a new manager's first 90 days — first-time or new-to-team — as listen\/decide\/move phases: the 1:1 listening tour with real questions, the early-judgment traps, the quick-wins filter, and the 30\/60\/90 artifacts. Use when asked I just became a manager what do I do, plan my first 90 days as a manager, taking over an existing team, or new manager 30-60-90 plan. Produces the phased plan, the listening-tour question set, the team assessment framework, and the day-one and week-6 artifacts."
}

Manager First 90 Days Skill

New managers fail in two symmetrical ways: moving too fast (reorganizing by week 3 on pattern-matching from their last job) and moving too slow (still "just listening" at day 80 while the team concludes nobody's driving). The 90 days have a shape — listen (0–30), decide (30–60), move (60–90) — and the discipline is doing each phase's work in its phase: no irreversible changes while listening, no more listening once it's time to call things. This skill builds that plan, tuned to the situation they're actually walking into.

What This Skill Produces

  • The phased plan — 30/60/90 with each phase's job, its deliverable, and its forbidden moves
  • The listening tour kit — 1:1 question set that surfaces reality instead of pleasantries, plus stakeholder-map interviews beyond the team
  • The assessment framework — reading people, processes, and problems without the early-judgment traps
  • The artifacts — day-one intro message, the week-6 "what I've heard and what we'll do" note, and the 90-day review against the plan

Required Inputs

Ask for these if not provided:

  • The situation — first-time manager or experienced-but-new-team? Internal promotion (now managing former peers — its own minefield) or external hire?
  • The team's state as advertised — size, tenure mix, why the role was open (predecessor promoted, quit, fired — each leaves different residue), known fires
  • The mandate — hired to fix, to grow, or to not-break? What did their boss say success at 90 days looks like? (If they don't know, that conversation is week-1 item #1.)
  • Inherited hazards — a flight-risk star, an open performance problem, a stalled critical project

Framework: The Phase Rules

  1. Days 0–30, listen — and defend the phase: 1:1s with every report using questions that fetch reality: "What should this team stop doing?" "What almost-broke recently?" "What would you fix with a magic wand?" "Who do you go to when stuck?" (that last one maps the real org chart). Interview peers, boss, and internal customers too — the team's self-image never matches its customers' experience. Forbidden: reorgs, process overhauls, public verdicts. Allowed: reversible paper cuts (fixing an obviously broken meeting buys credibility without spending judgment).
  2. Mistrust the first read on people: the person who impresses in week 2 is the best talker; the quiet one may be the load-bearer. Score on artifacts and peer-dependency patterns (who everyone routes through), not meeting charisma. Inherited reputations get verified, not adopted — the predecessor's "problem person" is sometimes just the person who disagreed with the predecessor.
  3. Day ~40, say what you heard: the week-6 note — "what I've heard, what I'm keeping, what we'll change and why" — is the hinge artifact. It proves the listening was real (people see their words in it) and openly spends the credibility earned on the first calls. Silence past week 8 reads as either no judgment or no courage.
  4. Quick wins must be real: the filter is visible + fast + actually wanted by the team + reversible-if-wrong. Killing a meeting everyone hates qualifies. A tooling migration is not a quick win; it's a slow project wearing a quick win's clothes.
  5. Move in 60–90, including the hard calls: the performance conversation being avoided, the stalled project needing a kill/commit, the mandate items. A new manager who ends the 90 days having changed nothing has told the team change isn't coming. Former-peers case: the awkward conversation ("our relationship changes, here's what stays and what can't") happens in week 1, once, explicitly — postponing it makes every 1:1 weirder.

Output Format

First 90: [role, team, situation]

The Mandate (verified with boss, week 1)

[What success at day 90 means, in their boss's words — or the plan to extract it]

Days 0–30 — Listen

[1:1 schedule · the question set · stakeholder interviews · allowed paper-cut fixes · forbidden list]

Days 30–60 — Decide

[Assessment: people (artifact-based), processes (keep/fix/kill), problems (ranked) · the week-6 note, drafted]

Days 60–90 — Move

[The 2–3 changes with reasons · the hard call being made, not deferred · quick-win ledger]

Artifacts

[Day-one intro message · week-6 note skeleton · 90-day self-review questions]

Quality Checks

  • Each phase has explicit forbidden moves, not just to-dos
  • Listening-tour questions fetch specifics ("what almost broke") not vibes ("how's morale")
  • People-assessment cites artifacts and dependency patterns, not meeting impressions
  • The week-6 note exists and quotes what people actually said
  • At least one hard call is scheduled inside the 90 — not "after I settle in"

Anti-Patterns

  • Do not reorganize in month one — pattern-matching from the last job is not knowledge of this team
  • Do not adopt inherited reputations without verification — especially the "problem person"
  • Do not let listening become hiding — the week-6 note is mandatory, discomfort included
  • Do not pick quick wins the team didn't ask for — a win nobody wanted is a change nobody wanted
  • Do not defer the former-peers conversation — week 1, explicit, once

Version History

  • 54fad50 Current 2026-07-19 13:07

Same Skill Collection

exports/openclaw/360-feedback-template/SKILL.md
exports/openclaw/401k-plan-decoder/SKILL.md
exports/openclaw/ab-test-planner/SKILL.md
exports/openclaw/ab-test-readout/SKILL.md
exports/openclaw/accessibility-audit/SKILL.md
exports/openclaw/account-plan/SKILL.md
exports/openclaw/acquirer-red-team/SKILL.md
exports/openclaw/ad-copy/SKILL.md
exports/openclaw/aeo-optimizer/SKILL.md
exports/openclaw/agenda-or-cancel/SKILL.md
exports/openclaw/agent-design-review/SKILL.md
exports/openclaw/agent-observability-spec/SKILL.md
exports/openclaw/agent-spec/SKILL.md
exports/openclaw/ai-ethics-review/SKILL.md
exports/openclaw/ai-eval-plan/SKILL.md
exports/openclaw/ai-feature-prd/SKILL.md
exports/openclaw/ai-product-canvas/SKILL.md
exports/openclaw/air-quality/SKILL.md
exports/openclaw/altitude-shifter/SKILL.md
exports/openclaw/ambiguity-resolver/SKILL.md
exports/openclaw/analyst-relations-brief/SKILL.md
exports/openclaw/announcement-card/SKILL.md
exports/openclaw/api-docs-writer/SKILL.md
exports/openclaw/api-test-plan/SKILL.md
exports/openclaw/api-versioning-strategy/SKILL.md
exports/openclaw/apology-letter/SKILL.md
exports/openclaw/architecture-decision-record/SKILL.md
exports/openclaw/architecture-diagram/SKILL.md
exports/openclaw/archive-strategy/SKILL.md
exports/openclaw/assumption-bounty/SKILL.md
exports/openclaw/assumption-mapper/SKILL.md
exports/openclaw/async-update-format/SKILL.md
exports/openclaw/auto-repair-estimate-decoder/SKILL.md
exports/openclaw/autopilot-charter/SKILL.md
exports/openclaw/benefits-decoder/SKILL.md
exports/openclaw/bid-tender-review/SKILL.md
exports/openclaw/board-deck-narrative/SKILL.md
exports/openclaw/board-minutes/SKILL.md
exports/openclaw/board-pre-read/SKILL.md
exports/openclaw/bom-cost-review/SKILL.md
exports/openclaw/bookkeeping-categorization/SKILL.md
exports/openclaw/boolean-search-builder/SKILL.md
exports/openclaw/brag-doc/SKILL.md
exports/openclaw/brainstorming/SKILL.md
exports/openclaw/brief-builder/SKILL.md
exports/openclaw/briefing-note/SKILL.md
exports/openclaw/budget-builder/SKILL.md
exports/openclaw/budget-variance-analysis/SKILL.md
exports/openclaw/bug-diagnosis/SKILL.md
exports/openclaw/bug-report/SKILL.md

Metadata

Files
0
Version
471c606
Hash
8570df1a
Indexed
2026-07-19 13:07

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-30 11:00
浙ICP备14020137号-1 $방문자$