excalidraw
Generate an Excalidraw whiteboard in Sean's hand-drawn video style (Excalifont, roughness 1, green signature, socials +…
Schedule, book or set up a meeting, call, coffee, lunch, dinner, event or appointment on my calendar.
Claude Code
$ npx -y skills add ShenSeanChen/waku-agent --skill schedule-meeting --agent claude-code
Codex
$ npx skills add ShenSeanChen/waku-agent --skill schedule-meeting -a codex -y
Cursor
$ npx skills add ShenSeanChen/waku-agent --skill schedule-meeting -a cursor -y
Gemini CLI
$ npx skills add ShenSeanChen/waku-agent --skill schedule-meeting -a gemini-cli -y
GitHub Copilot
$ npx skills add ShenSeanChen/waku-agent --skill schedule-meeting -a github-copilot -y
OpenCode
$ npx skills add ShenSeanChen/waku-agent --skill schedule-meeting -a opencode -y
Windsurf
$ npx skills add ShenSeanChen/waku-agent --skill schedule-meeting -a windsurf -y
name: schedule-meeting description: Schedule, book or set up a meeting, call, coffee, lunch, dinner, event or appointment on my calendar.
1. Resolve relative dates ("next Tuesday", "tomorrow morning") into ISO 8601 using today's date from the system prompt. Morning = 09:00, afternoon = 14:00, evening = 18:00 unless the user says otherwise. 2. Check memory context for the attendee's preferences (e.g. "prefers morning meetings") and apply them — mention it when you do ("since Alex prefers mornings, I booked 9am"). 3. Call `create_event` with a short, specific title: "Coffee with Alex", not "Meeting". 4. If the user mentioned an agenda or context, put it in `notes`. 5. After creating, confirm in one sentence: what, when, with whom.
| Situation | Do | |---|---| | No time given | Propose a concrete time instead of asking an open question — if memory shows the attendee's preference, lead with it ("Alex prefers mornings — Friday 9am?"). Only ask openly when memory gives you nothing | | Past date requested | Point it out, suggest the next occurrence | | Attendee unknown to memory | Schedule anyway; offer to `save_note` who they are |
Your own AI assistant. On your laptop. In code you can read in an afternoon. Meet Waku — a local-first personal assistant that shows the four pillars behind every serious agent: Harness · Loop · Memory · Eval/LLM-Ops. No frameworks hiding the good parts.
Generate an Excalidraw whiteboard in Sean's hand-drawn video style (Excalifont, roughness 1, green signature, socials +…
Add a new tool to Waku the right way — schema, safe execution, deterministic eval, honest output. Use when adding or modifying…
Create and tear down the throwaway git worktrees used to test community PRs for waku-agent, without leaking API keys or leaving…
Cut a waku-agent release when main is ahead of the last tag. Check the gap, bump the version, tag, confirm PyPI, announce. Use…
Walk Sean through an incoming waku-agent PR or issue and present it his way — four fixed sections: what this is, why it matters,…
Commit and push the current work properly — lint, run the release gate, write a detailed commit message, push to GitHub. Use…
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress…
Set up the owner profile so a personal agent knows who it works for (first-run setup, \"get to know me\"), or distill colleague,…