跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

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.

AI 与智能体1.4kskills/aging-parent-talks/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/mohitagw15856/pm-claude-skills/aging-parent-talks/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

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

[[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."

相似的 Skill

brand-guidelines
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI 与智能体

internal-comms
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI 与智能体

template-skill
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI 与智能体

mcp-builder
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI 与智能体

algorithmic-art
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI 与智能体

academy-guide
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI 与智能体