executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
support-macroWrite reusable support macros / canned responses that sound human, not robotic. Use when asked to write a support macro, a canned response, a saved reply, or a template for a common customer ticket. Produces a macro — an empathetic opener, the clear answer/steps, placeholders for personalisation, and a warm close — plus variants (resolved / need-more-info /…
Independent GitHub snapshot · Automated classification · Original documentation governs
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.
Ask for these only if they aren't already provided:
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):
Notes: keep placeholders obvious so agents always personalise; flag the one line that must stay (policy/legal); keep it scannable on mobile.
Support-experience practice — empathetic, scannable, personalised canned responses (Zendesk/Intercom macro conventions).