support-macro
Write reusable support macros / canned responses that sound human, not robotic. Use when asked to write a support macro, a canned response, a saved …
它会碰到什么
这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。
技能内容
Support Macro Skill
Macros make support fast — but bad ones make it feel like a wall of copy-paste, which customers hate.
A good macro is a scaffold: empathetic opener, the actual answer in clear steps, obvious personalisation
slots, and a human close — fast for the agent, warm for the customer. This skill writes that, with the
variants a single situation usually needs.
Required Inputs
Ask for these only if they aren't already provided:
- The scenario — the common ticket this macro answers (password reset, refund request, bug report, how-to).
- The resolution — the actual answer or steps.
- Brand voice — formal, friendly, playful (defaults to warm-professional).
- Constraints — anything that must be said (policy, legal, security) or links to include.
Output Format
Macro: [scenario]
Primary macro:
> Opener — acknowledge the person + their issue specifically ("Sorry the export failed — let's get that sorted."). Not "Dear valued customer."
> Answer — the resolution in clear, numbered steps where it's a process. One idea per line.
> Personalisation slots — clearly marked [first name], [order #], [specific detail] the agent fills.
> Close — a warm, human sign-off + an open door ("If that doesn't do it, just reply here and I'll dig in.").
Variants (same scenario, different outcomes):
- Resolved — the answer above, confident it's fixed.
- Need more info — what you need from them and why, framed helpfully (not interrogation).
- Escalating / known issue — honest acknowledgement, what happens next, and a realistic timeframe.
Notes: keep placeholders obvious so agents always personalise; flag the one line that must stay (policy/legal); keep it scannable on mobile.
Quality Checks
- [ ] Opens by acknowledging the person and their specific issue
- [ ] The answer is clear and step-by-step where it's a process
- [ ] Personalisation slots are clearly marked so agents fill them every time
- [ ] Includes the variants the scenario needs (resolved / more-info / escalating)
- [ ] Sounds like a person — contractions, warmth — not a corporate template
Anti-Patterns
- [ ] Do not write "Dear valued customer" / robotic openers — acknowledge the actual person and problem
- [ ] Do not make it un-personalisable — a macro with no slots gets sent cold and feels like spam
- [ ] Do not bury the answer in apology — empathise briefly, then solve
- [ ] Do not over-promise on escalations — give an honest, realistic timeframe
- [ ] Do not write one macro for a scenario with multiple outcomes — give the resolved/more-info/escalating variants
Based On
Support-experience practice — empathetic, scannable, personalised canned responses (Zendesk/Intercom macro conventions).
想直接用这个技能?
本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。
它属于哪个仓库
plugins/pm-support/skills/support-macro/SKILL.md同一个仓库里的其他技能
同名技能的其他版本
有 3 个不同仓库或目录里都有叫 support-macro 的技能。它们内容并不相同,别混用:
- mohitagw15856/pm-claude-skills — Write reusable support macros / canned responses that sound human, not robotic. Use when a
- mohitagw15856/pm-claude-skills — Write reusable support macros / canned responses that sound human, not robotic. Use when a