把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。
记忆
call-script-coach
试用Use before any difficult phone call you're anxious about or that has stakes — calling customer service to dispute a fee, negotiating a bill, cold-calling a client, delivering bad news to a vendor, calling a landlord about repairs, insurance disputes, or handling collections calls — builds a branching call script from your situation (goal, leverage, fallback), generates objection→response trees for the specific counter-arguments you'll hear, produces a one-page printable cheat sheet, and includes a practice-drills mode that plays the other side and scores your responses.
它能做什么
Almost everyone hates difficult phone calls — and hatred costs money. People accept wrong fees, skip refund disputes, overpay for years, and avoid negotiating because when the rep says "that's our policy," they have nothing to say. The difference between a resolved dispute and a capitulation is usu…
技能文档
Call Script Coach
Overview
Almost everyone hates difficult phone calls — and hatred costs money. People accept wrong fees, skip refund disputes, overpay for years, and avoid negotiating because when the rep says "that's our policy," they have nothing to say. The difference between a resolved dispute and a capitulation is usually 4 things: knowing your goal, knowing your leverage, having a response ready for the 2–3 predictable objections, and knowing when to escalate instead of arguing.
This skill builds a branching call script for your specific situation:
- Situation intake — what the call is about, what you want, what you can offer or threaten (leverage), what your fallback is.
- Scenario library — 10 pre-built situations (billing dispute, late-fee waiver, rate negotiation, service cancellation, landlord repair demand, insurance denial pushback, collections response, vendor complaint, salary/raise call, sales cold call), each with goals, leverage points, and the objections you will actually hear.
- Objection→response trees — for every "no" the other side can say, a grounded response: acknowledge → restate value/leverage → concrete ask.
- Cheat sheet — a printable one-pager: opening line, asks in order, escalation path, what NOT to say, notes field.
- Practice mode — the script plays the other side with realistic pushback, scores your typed responses against the tree (did you acknowledge? restate leverage? make a concrete ask?), and tells you what to tighten.
When to Use
- Before disputing a charge, fee, or bill increase by phone
- Calling to cancel a service while dodging retention traps
- Negotiating a rate with a provider (internet, phone, insurance, SaaS)
- Demanding a repair from a landlord or contractor
- Responding to a collections call without admitting or paying wrongly
- Any call you're rehearsing in your head for the third time — write it down instead
- Don't use for: emergency calls, legal proceedings (get a lawyer), or HR complaints at work (different rules, written trail matters more).
Commands
# List pre-built scenarios
python3 scripts/call_coach.py scenarios
# Build a script interactively (prompts for goal/leverage/fallback)
python3 scripts/call_coach.py build --scenario billing-dispute
# Build non-interactively
python3 scripts/call_coach.py build --scenario rate-negotiation \
--goal "Cut internet bill to $45/mo" \
--leverage "3 years customer; competitor offers $42" \
--fallback "Accept $55 with 12mo lock; else cancel"
# Add your own objection responses to the tree before printing
python3 scripts/call_coach.py build --scenario cancellation \
--objection "You'll lose your loyalty discount" \
--response "I understand — the total is still higher than my alternative"
# Printable one-pager (also saved to ~/.call-scripts/.txt)
python3 scripts/call_coach.py sheet --scenario billing-dispute --title "ISP $80 overcharge"
# Practice the call — script plays the other side, scores your replies
python3 scripts/call_coach.py practice --scenario billing-dispute
# See the full objection tree for a scenario
python3 scripts/call_coach.py tree --scenario collections
The 5 Rules (baked into every script)
- Open with your name + account + one-sentence goal. Reps triage in the first 15 seconds; make the issue classifiable.
- Ask, then silence. State the concrete ask ("remove the $80 charge") and stop talking. The first person to fill silence usually concedes ground.
- "Policy" is a position, not an answer. Respond: "I understand that's the standard policy — and I'm asking what you can do in this case." Reps have discretionary ranges they never volunteer.
- Escalate on the second no. "I appreciate your help — please transfer me to someone who can approve this." Retention/loyalty desks exist and have bigger limits.
- Know your walk-away. If fallback is "cancel," say it once, calmly, with a date. Empty threats train them to ignore you.
Objection Tree Shape
THEIR LINE YOUR RESPONSE (pattern)
────────────────────────────── ─────────────────────────────────────────
"That's our policy" → acknowledge → policy ≠ this case → repeat ask
"I can't do that" → "can't" or "not allowed"? → ask for who can
"It's already billed" → dispute window + billing error rights → ask
"Manager is busy" → hold or callback with name + timeframe
"Offer: partial credit" → compare vs goal → accept/counter explicitly
"You agreed to terms" → terms ≠ this situation → mischarge facts → ask
Every response follows acknowledge → bridge → concrete ask. Practice mode scores exactly those three elements.
Common Pitfalls
- Arguing instead of asking. Venting feels productive; only concrete asks ("remove X", "credit Y", "transfer me") move a call. The cheat sheet's ask list keeps you on target.
- Threatening without a fallback. If you say "I'll cancel" and won't, you've spent your only card. Decide the fallback before dialing — it's an intake field.
- Accepting the first "no" as final. Front-line reps have the smallest authority by design. Second no → escalate (Rule 4).
- Admitting/paying on a collections call. The collections script's first branch is validation-before-payment: never acknowledge the debt or make a partial payment before written validation — both can restart statutes of limitations.
- Getting angry at the rep. The person on the phone didn't cause the problem and can't fix what they can't classify. Scripts work because they're calm and specific.
- No notes during the call. The cheat sheet has a notes field — write rep name, times, promises, and ticket numbers. That's your paper trail if the promise evaporates.
Verification Checklist
- Scenario chosen (or custom goal/leverage/fallback written out in full sentences)
- Sheet printed/saved and visible during the call
- Fallback decided and realistic — would you actually do it?
- Practice mode run at least once; your responses hit acknowledge+bridge+ask
- Account number, billing dates, and any confirmation numbers written on the sheet
One-Shot Recipes
ISP charged $80 for a "tech visit" that the rep said was free
python3 scripts/call_coach.py build --scenario billing-dispute \
--goal "Remove the $80 tech-visit charge" \
--leverage "Chat log where rep said visit was free; 3yr customer" \
--fallback "File FCC + state AG complaint (5 min, free)"
python3 scripts/call_coach.py sheet --scenario billing-dispute --title "ISP $80"
Canceling a gym/app/SaaS subscription with retention pushback
python3 scripts/call_coach.py practice --scenario cancellation
相关技能
以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。
在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。
诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。
从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。
为自然搜索排名提供站点审计、内容撰写与竞品分析。
voronindenis5 的更多技能
浏览全部技能Pryamoy Russkiy (Straight Russian) — AI assistant that tells it like it is. Direct answers, no fluff, occasional profanity. Specializes in honest analysis, t...
Prepare salary negotiations with a structured toolkit: market-rate anchoring math, walk-away floor calculation, total-compensation evaluation (equity, bonuses, benefits), negotiation scripts for offers, raises, and counter-offers, and BATNA analysis. Use when the user has a job offer, is preparing a raise conversation, wants to know if their pay is competitive, or needs scripts and a strategy for negotiating compensation.
Use when your calendar is eating your week and you want to know exactly where the time goes, when planning recurring meetings for a team, before proposing a new recurring meeting, when someone says 'we should sync weekly' and you want data, or when auditing which meetings to kill — imports ICS calendar files, measures meeting hours per week/person/meeting-series (including double-bookings and fragmentation), computes focus-time destruction from meeting placement, scores the true cost of each series (hours × attendees × frequency), flags specific meetings to kill/shorten/make-async using explicit rules, and simulates the recovered hours before anyone has to argue about it.
Audit password vault exports (Bitwarden, 1Password, KeePass, Chrome, Firefox) for reuse, weakness, staleness, breach exposure, and 2FA gaps without ever storing or transmitting a plaintext password. Use when the user asks to audit passwords, check password strength/reuse, review vault health, or verify whether credentials appeared in breaches.
Turn flat resume bullets ('Responsible for X') into quantified STAR-method achievement narratives, score resumes against job descriptions for ATS keyword coverage and weak-phrase hazards, and expand each bullet into interview-ready stories with likely follow-up questions. Use when the user is writing or updating a resume/CV, preparing bullets for a job application, tailoring a resume to a specific job posting, or preparing interview stories from their experience.
Agent self-awareness of cognitive states — context fatigue, attention drift, memory debt, confidence erosion, and skill staleness. Detect, report, and mitigate degrading conditions before they cause failures.