婚礼祝酒词策划师

安装指南

1. ClawHub CLI 从源直接安装技能的最快方式。
   npx clawhub@latest install wedding-toast-architect
2. 手动安装 将技能文件夹复制到以下位置之一
   全局模式
   ~/.openclaw/skills/
   工作区
   /skills/
   优先级：工作区 > 本地 > 内置
3. 提示词安装 将此提示词复制到 OpenClaw 即可自动安装。
   请帮我使用 Clawhub 安装 wedding-toast-architect。如果尚未安装 Clawhub，请先安装（npm i -g clawhub）。
   更倾向于下载？
   获取包含原生技能文件的ZIP压缩包。
   下载技能 (.zip)

什么是

婚礼祝酒词策划师将婚礼演讲转化为实用、可审阅的内容。它会收集演讲者和新人双方的一些信息，然后生成六部分大纲，并根据演讲者角色和目标时长分配字数。可用于伴郎、伴娘、父母、兄弟姐妹或朋友的演讲，也适用于较短的婚宴彩排晚宴和订婚派对祝酒词。
扫描器会检查草稿中的 16 类潜在问题，包括提及前任、醉酒故事、离婚笑话、私人姓名和只有圈内人才懂的笑话。检查结果会标记为 CUT、SOFTEN 或 CHECK，并提供安全评分、长度对比、可读性信息和演讲时间估算。这款 Openclaw Skills 工具使用 Python 标准库离线运行，草稿文本会保留在本机。

应用场景

你受邀发表伴郎、伴娘、父母、兄弟姐妹或朋友的演讲，需要一个清晰的起步框架。
你已有草稿，想检查敏感话题、冒险笑话、私人姓名或没有解释的圈内笑话。
你需要估算演讲是否符合目标时长，例如三分钟。
你正在准备彩排晚宴或订婚派对的祝酒词，希望将同一结构调整为较短的演讲。
你希望按照各部分的字数目标进行练习，而不是一次写完整篇演讲。

工作原理

收集演讲者角色、新人姓名、伴侣姓名、相识年数、故事备选、故事体现的品质，以及目标演讲时长。
运行 build 生成六部分大纲：开场、演讲者介绍、两个故事部分、伴侣部分和祝酒词。输出包含字数分配，以及按每分钟 135 个单词估算的各部分时长。
按各部分的字数分配撰写，优先讲好一个故事并真诚赞美伴侣，不要塞进太多轶事。
对草稿运行 scan，并提供受保护姓名和目标时长。查看 CUT、SOFTEN 和 CHECK 结果；修改 CUT，斟酌 SOFTEN，并结合上下文大声读出 CHECK 内容。
对最终字数运行 time，估算每分钟 110、135 和 150 个单词时的演讲时长。
大声排练，并由人最终判断语气是否合适。扫描器能识别模式，但无法替代你对新人和听众的了解。

配置指南

此技能使用 Python 3 和 Python 标准库。无需网络连接或外部服务。在技能目录中，使用演讲相关信息运行脚本：
python3 scripts/toast_architect.py build --role best-man
--couple "Alex & Sam" --partner Sam --years-known 9
--stories "rafting capsize; chili cook-off disaster"
--qualities "loyal, calm in chaos" --minutes 3 将草稿保存为文本文件，然后扫描草稿，并列出扫描器应视为受保护对象的姓名：
python3 scripts/toast_architect.py scan --draft draft.txt
--protected "Jordan,Riley" --minutes 3 根据字数估算演讲时间：
python3 scripts/toast_architect.py time --words 410
技能文档未说明需要单独安装软件包或进行配置。演讲前请大声排练；指南建议使用打印并编号的索引卡，而不要依赖手机。

数据架构

该技能围绕命令输入和生成的文本报告来组织演讲准备，而非使用有文档说明的数据库或持久化项目格式。
项目 用途
构建输入 演讲者角色、新人及伴侣姓名、相识年数、故事备选、品质和目标分钟数。
大纲 六个部分——开场、人物介绍、故事 1、故事 2、伴侣、祝酒词——并为每部分分配字数，按每分钟 135 个单词估算秒数。
草稿文件 通过 --draft 提供给 scan 的纯文本演讲稿；示例使用 draft.txt。
受保护姓名 使用 --protected 传入的逗号分隔姓名，用于检查前任、疏远或已故人士及其他私人对象。
扫描报告 CUT、SOFTEN 和 CHECK 结果、长度与可读性检查、长句检测以及安全评分。
计时结果 按每分钟 110、135 和 150 个单词估算的演讲时长。
评分按 100 分起算：每项 CUT 扣 18 分，每项 SOFTEN 扣 7 分，每项 CHECK 扣 3 分，最低为 0 分。指南建议排练前评分至少达到 85 分。参考资料见 references/toast-craft.md 和 references/scanner-patterns.md。

高级特性

为伴郎、伴娘、父母、朋友和兄弟姐妹提供按角色定制的大纲字数分配。
提供每分钟 110、135 和 150 个单词三种语速的演讲时间估算。
扫描 16 类模式，并按严重程度给出 CUT、SOFTEN 和 CHECK 判定。
通过受保护姓名检查，帮助标记提及前任、关系疏远者、已故人士和其他私人对象的内容。
检查草稿长度、口语演讲的 Flesch 可读性，以及过长句子。
加权安全评分可在修改过程中凸显重复或严重的问题。
使用 Python 标准库离线运行；草稿文本不会离开本机。
参考指南涵盖祝酒词结构、角色字数分配依据、演讲当天准备、模式详情、误报和扫描器扩展。

name: wedding-toast-architect description: "Use when asked to write, revise, time, or safety-check a wedding speech or toast (best man, maid of honor, parents, friends) — builds a role-tuned 5-part outline with per-section word budgets, estimates speaking time at 3 paces, and red-flag scans drafts for the classics that bomb (ex mentions, drunk stories, divorce jokes, inside jokes, backhanded 'finally settled' compliments) with CUT/SOFTEN/CHECK verdicts." version: 1.0.1
author: Denis Voronin
license: MIT
tags: [wedding, speech, toast, public-speaking, writing]

Wedding Toast Architect

Overview

Every year ~2 million US couples marry; nearly every wedding hands a friend or parent a microphone and 3 minutes they are unprepared for. The result is predictable: rambled inside jokes, accidental ex mentions, drunk-story confessions, "ball and chain" humor in front of both grandmothers — and a regretful speaker replaying it for years.

This skill treats the toast as a buildable artifact with a spec:

build — questionnaire → 5-part outline with word budgets per section, tuned by role (best man / maid of honor / parent / friend / sibling).
scan — draft → red-flag report: 16 pattern classes with CUT / SOFTEN / CHECK verdicts, protected-name enforcement, length vs target, Flesch readability for the ear, and long-sentence detection.
time — words → minutes at 110/135/150 wpm.

Pure Python stdlib. Works offline. No draft text ever leaves the machine.

When to Use

"I'm best man in 3 weeks and haven't written anything" (any speech-role panic)
"Is this speech okay? Be honest." — paste draft, run scan
"How long will 500 words take to deliver?"
Parent-of-the-bride/groom, maid of honor, sibling, close-friend toasts
Rehearsal-dinner speeches, engagement-party toasts (same structure, shorter)

Don't use for: vows (intimate, couple-authored — different genre), ceremony readings (pre-existing texts), professional MC scripts, eulogies (see note: structure overlaps but tone rules differ — this tool would over-flag).

How It Works — Numbered Steps
Interview the speaker briefly: role, couple names, partner name, years known, 1-2 story candidates, 1-2 qualities those stories prove, target minutes (default 3).
Build the skeleton:

python3 scripts/toast_architect.py build --role best-man \

--couple "Alex & Sam" --partner Sam --years-known 9
--stories "rafting capsize; chili cook-off disaster"
--qualities "loyal, calm in chaos" --minutes 3

Output: 6 sections (hook / who / story1 / story2 / partner / toast) with per-section word budgets and second-durations at 135 wpm.
Draft against the budgets — one story told well beats three told fast.
Scan the draft:

python3 scripts/toast_architect.py scan --draft draft.txt \

--protected "Jordan,Riley" --minutes 3

Fix every CUT finding. Decide on SOFTENs. Read CHECKs aloud.
Time the final cut: python3 scripts/toast_architect.py time --words 410.
Rehearse 3× out loud, standing, holding a full glass. Print 18pt+, one section per index card, cards numbered.
What the Scanner Catches (16 pattern classes)

Class Severity Why

ex-partner references CUT exes never belong in toasts
drunk/intoxication stories CUT all-ages room
strip club / vegas CUT bachelor content bombs
divorce / "ball and chain" jokes CUT reads as doubt about the marriage
"finally settled" backhanded frames CUT insults both partners
pregnancy mentions CUT not your news to announce
profanity SOFTEN shrinks the room
money / prenup jokes SOFTEN divides the room
looks-only compliments SOFTEN compliment choices instead
dating-app jokes CHECK only if couple approves the story
inside-joke markers ( ... ) CHECK translate or cut
religion assumptions CHECK match the couple's faith
"However" early digs CHECK usually introduces a slight
cliché openers SOFTEN "Good evening, for those who don't know me..."
filler words on paper SOFTEN filler out loud too
protected names CUT exes, estranged, deceased, private people

Scoring: 100 − 18·CUT − 7·SOFTEN − 3·CHECK, floored at 0. Ship at ≥85.

Common Pitfalls

Treating it as a comedy set. Funny is fine, funny-only flops. The room wants warmth + one laugh, not ten laughs and no heart.
Three stories in three minutes. Budget says ~120 words for story1 — that's ONE story with a scene, complication, payoff.
Ignoring the partner section. Maid-of-honor speeches about the bride with 10 seconds for the groom read as a rejection of the marriage. Budget 14-24% of words for the partner (role-dependent).
Reading from a phone. Lock screen, glare, notifications. Index cards.
Not timing it. 500 words = 3.7 min normal, 4.5 min with adrenaline pauses. The couple scheduled you for 3.
Trusting the scanner as the only pass. It catches patterns, not tone. The final gate is the question printed at the end: would you say this to the couple's face with both grandmothers listening?
Writing the night before. The outline takes 20 minutes; the stories need a week of "which detail do I keep" walks.

Example

Speaker: best man, 9 years of friendship, worried about an ex mention.
$ toast_architect.py build --role best-man --couple "Alex & Sam" --partner Sam
--years-known 9 --stories "rafting capsize; chili cook-off disaster"
--qualities "loyal, calm in chaos" --minutes 3 → 405-word budget: hook 48 / who 40 / story1 121 / story2 89 / partner 56 / toast 48

$ toast_architect.py scan --draft draft.txt --protected "Jordan" --minutes 3
→ 5 CUT / 2 SOFTEN / 1 CHECK, safety score 0/100:
CUT ex-partner reference (1x)
CUT drunk/intoxication story (1x)
CUT divorce/pessimism joke (1x)
CUT 'finally settled' framing (1x)
CUT protected name 'Jordan' (1x)
SOFTEN money joke, cliché opener CHECK inside-joke parenthetical

Rewrite fixes all CUTs; rescan: 92/100 — ready for rehearsal.

References

references/toast-craft.md — structure theory, role budget rationale, delivery-day protocol (mic, glass, cards), and the repair guide for each flag class with before/after rewrites.
references/scanner-patterns.md — the full pattern table with regexes, severity weighting, known false-positive notes, and how to extend.
深度清洁作战规划器

EV Charge Planner