本文へ移動
cccskills
無料GitHub で公開

aging-parent-talks

Prepare the conversations with aging parents that everyone postpones — the driving talk, the money talk, the care-options talk, the moving talk — each with an opener that doesn't ambush, a dignity-first script, rehearsal against realistic resistance, and the fallback when it goes badly. Use when someone says 'I need to talk to my dad about driving', 'my mum won't discuss her finances', 'we need to talk about care', or is dreading a visit for exactly this reason. Produces the conversation plan, a rehearsal, and the small-steps fallback. A preparation tool, not family therapy — and it says so when the situation needs more.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md7.0 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Aging Parent Talks Skill

These conversations get postponed because both framings feel impossible: saying nothing (and waiting for the crisis to decide) or taking over (and watching a parent's face close). The workable path runs between them — raise it early, small, and with the parent rather than about them; anchor on their goals ("you want to stay in this house — let's make that work") rather than your fears; accept that the first conversation's only job is to make a second one possible. This skill prepares one specific talk: the opener, the script's spine, the rehearsal against the resistance you'll actually meet, and the smallest-step fallback for when the full topic won't land.

What This Skill Produces

  • A conversation plan for the chosen talk (driving, money, care, moving): timing/setting, who should raise it (not always the user), the opener, and the one goal of round one
  • The dignity-first script spine: their-goals anchoring, the specific observations (never accusations), the ask sized to a first conversation
  • A rehearsal: the assistant plays the parent with realistic resistance (deflection, hurt, "I'm fine", role-reversal guilt), then debriefs out-of-character — simulator DNA, pointed at the hardest room there is
  • The small-steps fallback: what to ask for when the big topic won't land, and the crisis-line: which signs mean this stops being gradual
  • Verify-local flags for anything legal/medical (license rules, powers of attorney, care assessments — named as things to look up, never asserted)

Required Inputs

Ask for (if not already provided):

  • Which talk, and what prompted it now — the specific incidents (the scrape, the unpaid bills, the fall), because specifics carry the conversation and vagueness kills it
  • The parent as a person: what they're proudest of, what they fear (the care home? being a burden? losing the car = losing church and friends?), how they've reacted to adjacent topics
  • Family cast: siblings aligned or not ([[sibling-care-summit]] first if not), who the parent actually listens to
  • Honest stakes: inconvenient-worrying, or actively dangerous? (The dangerous branch changes the advice — and names when waiting is no longer an option)

Framework

  1. Pick the moment; drop the ambush. Private, unhurried, one topic, never at a family gathering, never mid-crisis if avoidable. The opener asks permission: "Dad, can we talk about the driving sometime this weekend? Not deciding anything — just talking." Permission converts an ambush into a conversation.
  2. Anchor on their goal, not your fear. Every talk has a their-goal version: driving → "keeping your independence without an accident taking it all at once" · money → "making sure what you want is what happens" · care → "staying home as long as it's safe" · moving → "a place that takes less out of you." The user's fear is real; it's the fuel, not the script.
  3. Observations, specific and few. Two or three concrete incidents, said plainly, no verdicts attached: "the scrape in March, and Tuesday you missed the turn to ours." Then the question, not the conclusion: "how did it feel to you?" Parents defend against verdicts; they can join investigations.
  4. Size the ask to round one. Not "give up the keys" but "a driving assessment, and I'll come with you" · not "show me everything" but "a list of where things are, sealed if you want" · not "a home" but "one visit, just to see." The full destination is reached in steps or not at all.
  5. Rehearse the real resistance. The assistant plays the parent — deflection ("I've driven 50 years"), hurt ("so I'm a child now?"), the counterattack ("worry about your own life") — at the honesty level the user requests. Debrief: which of the user's lines escalated, which opened, the one sentence to keep. The rehearsal's lesson is almost always the same: slower, fewer points, more silence.
  6. Know the stop lines. Signs that gradual is over (dementia-scale confusion, genuine driving danger, exploitation) get the honest response: this needs professionals now — doctor, license authority process, elder-care/legal advice by jurisdiction — flagged as verify-local, and framed as protecting the parent. And the skill's own boundary, stated: entrenched family conflict or grief beyond logistics is therapy's territory, not a script's.

Output Format

## The talk: [which one] — round one's only goal: [one line]

## Setting & opener
[When, where, who speaks · the permission-ask opener verbatim]

## Script spine
[Their-goal anchor · the 2-3 observations · the round-one ask ·
the closing line that leaves the door open]

## Rehearsal
[In-character exchange · — out of character — · debrief: escalators,
openers, the keep-sentence]

## If round one doesn't land
[The smaller ask · the retreat line that preserves round two ·
the crisis signs that end gradualism, with verify-local routes]

Quality Checks

  • The opener asks permission and defers the decision
  • Observations are incident-specific and verdict-free
  • The ask is round-one-sized; the full destination appears only in the user's private plan
  • The rehearsal resistance matches this parent (from the inputs), not a generic grumpy elder
  • Legal/medical routes are verify-local flags; the therapy boundary is stated when the inputs smell of more than logistics

Anti-Patterns

  • Do not script the parent into agreement — the rehearsal must be winnable-by-the-parent or it teaches nothing
  • Do not stack all four talks into one conversation
  • Do not use infantilizing language anywhere ("we've decided", "for your own good") — dignity is the strategy, not the garnish
  • Do not assert license rules, POA law, or care procedures — flag and route
  • Do not counsel waiting when the inputs describe active danger — say the hard thing: this one is now

Related

[[sibling-care-summit]] to align the family first; [[caregiver-coordination]] for the logistics after yes; [[the-visa-interview]] shares the rehearsal bones; [[patient-communication]] for the clinical-side cousin.

Example Trigger Phrases

  • "I need to talk to my dad about driving."
  • "My mum won't discuss her finances."
  • "We need to talk about care."

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Design a 360-degree feedback survey or write a structured 360 feedback report. Use when asked to build a 360 feedback process, write 360 feedback for a colleague, design a feedback survey, or produce a feedback report. Produces either a complete survey instrument with rating scales and open-ended questions, or a structured narrative feedback report with themes, strengths, and development areas.

日本語の概要は準備中です。原文の説明を表示しています。

mohitagw15856/pm-claude-skills1,4412026年10月13日 更新

Decode a 401k or workplace retirement plan — the real cost of its funds, the match's fine print, vesting math, and the plan features worth using or avoiding. Use when someone asks 'is my 401k any good', 'decode my 401k plan', 'which funds should I look at', or 'what fees am I paying'. Produces a fee decode in dollars-over-time, match and vesting math, a fund-lineup triage by cost, and the questions for HR or the plan administrator.

日本語の概要は準備中です。原文の説明を表示しています。

mohitagw15856/pm-claude-skills1,4412026年10月13日 更新

Design statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments. Use when asked to set up an experiment, design an A/B test, calculate sample size, or interpret test results. Produces a complete test plan with hypothesis, variant definitions, sample size, duration estimate, guardrail metrics, and a results interpretation guide.

日本語の概要は準備中です。原文の説明を表示しています。

mohitagw15856/pm-claude-skills1,4412026年10月13日 更新

Analyse a finished A/B test and write the readout — the result, whether it's statistically and practically significant, what it means, and the ship/no-ship call. Use when asked to analyse experiment results, write an A/B test readout, interpret test data, or decide whether to ship a variant. Produces a clear verdict with the lift and confidence, segment cuts, the risks (peeking, novelty, sample), and a recommendation. Distinct from planning a test — this reads results.

日本語の概要は準備中です。原文の説明を表示しています。

mohitagw15856/pm-claude-skills1,4412026年10月13日 更新

Build or tailor an academic CV for faculty, postdoc, research or fellowship applications: publications, grants, teaching, supervision and service in the order the field expects, with consistent citations. Use when asked to write my academic CV, update my CV for a lectureship, tenure-track or postdoc application, format my publications list, or adapt my academic CV for an industry research role. Produces the full academic CV, a field-appropriate section order, a clean publications list in one citation style, and a two-page summary version when asked.

日本語の概要は準備中です。原文の説明を表示しています。

mohitagw15856/pm-claude-skills1,4412026年10月13日 更新

Generate a WCAG 2.2 accessibility audit checklist and remediation suggestions for any UI or design. Use when asked to audit for accessibility, check WCAG compliance, review a design for a11y issues, or create an accessibility remediation plan. Produces a prioritised checklist with pass/fail assessments and specific fixes.

日本語の概要は準備中です。原文の説明を表示しています。

mohitagw15856/pm-claude-skills1,4412026年10月13日 更新

mohitagw15856 のスキルをすべて見る

このスキルの問題を報告する