菜单
Find a specific Plaud recording by name keyword, date range, or topic. Use when the user says 'find the Weekly Sync', 'the meeting from Monday', 'the call about Q2', 'recordings last week', or describes what they're looking for rather than listing.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/CleanExpo/skills-library --skill plaud-find命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Dispatch the eight operational roles against a task, each grounded in the vault before it reads any code, with a live view of what is running. Use for work that wants several independent lenses at once — map, plan, build, verify, review, security, CI, release — rather than one agent doing everything.
Thin wrapper around the Pi-CEO Hour-1 provisioner. Given a client slug + email, invokes `swarm/inbox/provisioner.py` to spin up the full Linear project + Supabase portal_content + ContextBot Telegram intake bot + welcome email + Phill ping. Use when the user says "onboard {client}", "spin up portal for", "new client setup", or right after `stripe-milestone-invoice` confirms a deposit cleared.
PM-Core — the first autonomous execution agent. Claims the highest-priority agent-ready ticket from the Unite-Group Linear board, clones the repo, implements the fix on a feature branch, runs CI, and opens a PR. Model: claude-sonnet-5 (senior agent tier). Trigger: /pm-core [ticket-id] or autonomous via Hermes cron.
正在显示 SKILL.md
| name | plaud-find |
| version | 1.0.0 |
| description | Find a specific Plaud recording by name keyword, date range, or topic. Use when the user says 'find the Weekly Sync', 'the meeting from Monday', 'the call about Q2', 'recordings last week', or describes what they're looking for rather than listing. |
| metadata | {"requires":{"bins":[]}} |
Read plaud-shared first.
Plaud's list_files API does not accept query / date_from / date_to server-side — unknown params are silently ignored. Filtering happens client-side.
The MCP list_files tool accepts the same three optional params and performs the filter for you: pass the user's keyword and/or date window and let the tool paginate up to 5 pages.
list_files with the filter params you gathered:
query=<keyword> — case-insensitive substring match on name.date_from=YYYY-MM-DD, date_to=YYYY-MM-DD — inclusive window on created_at.created_at desc and mention the total.plaud-read.| User phrase | Filter |
|---|---|
| "today" | date_from = today, date_to = today |
| "yesterday" | both = yesterday |
| "this week" | Monday of this week → today |
| "last week" | Monday of last week → Sunday of last week |
| "this month" | 1st of this month → today |
| "last month" | 1st → last day of previous month |
| "from Monday" | date_from = the most recent Monday, no date_to |
Resolve relative dates against the current date (from conversation context), not the model's training cutoff.
User: "find the customer onboarding call from last week"
Agent:
list_files(query="onboarding", date_from="2026-04-13", date_to="2026-04-19")abc123 Customer Onboarding — Acme (2026-04-15, 42m), def456 Onboarding Q&A (2026-04-17, 18m). Which one?"