跳到正文
cccskills
免费在 GitHub 公开

minutes-search

Search past meeting transcripts and voice memos for specific topics, people, decisions, or ideas. Use this whenever the user asks "what did we discuss about X", "find that meeting where we talked about Y", "what did Alex say", "did we decide on", "what was that idea about", or any question that could be answered by searching their meeting history. Also use for "do I have any notes about" or "check my meetings for".

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md4.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

/minutes-search

Find information across all meeting transcripts and voice memos.

Usage

# Basic search
minutes search "pricing strategy"

# Filter to just voice memos
minutes search "onboarding idea" -t memo

# Filter to just meetings
minutes search "sprint planning" -t meeting

# Date filter + limit
minutes search "API redesign" --since 2026-03-01 --limit 5

Flags

FlagDescription
-t, --content-type <meeting|memo>Filter by type
--since <date>Only results after this date (ISO format, e.g., 2026-03-01)
-l, --limit <n>Maximum results (default: 10)

Output

Returns JSON to stdout with an array of matches. Each result includes:

  • title — Meeting or memo title
  • date — When it was recorded
  • content_type — "meeting" or "memo"
  • snippet — The line containing the match
  • path — Full path to the markdown file

Human-readable output goes to stderr. A result path is only a hint. To read the full transcript, run minutes get "<exact path>" --json, require exit status 0, and use only that response. Never pass the path to cat or the host Read tool.

How search works

Search is case-insensitive and matches against both the transcript body and the YAML frontmatter title. It walks all .md files in ~/meetings/ (including the memos/ subfolder).

For richer semantic search, users can configure QMD as the search engine in ~/.config/minutes/config.toml:

[search]
engine = "qmd"
qmd_collection = "meetings"

Search coaching

When the user's search query is vague or too broad, push back before running it:

  • "who said X" or "what did Alex say" → If the meeting has speaker_map in frontmatter, use it to identify who said what. speaker_map maps SPEAKER_X labels to real names. High confidence = reliable, Medium = "likely" (suggest minutes confirm to lock it in).
  • "everything" or "all meetings" → "That'll return hundreds of results. What specifically are you looking for? A person, a topic, or a decision?"
  • Single common word like "meeting" or "project" → "That's too broad. Can you narrow it — a person's name, a specific topic, or a date range?"
  • "that meeting" or "the one where" → "Help me narrow it down. Do you remember who was in the meeting, roughly when it was, or a specific thing that was said?"

Suggest search strategies based on what the user is looking for:

  • Finding a person's input → Search their name: minutes search "Alex"
  • Finding a decision → Search decision keywords: minutes search "decided" or minutes search "agreed"
  • Finding an idea → Search voice memos: minutes search "idea" -t memo
  • Finding something from a time range → Use --since: minutes search "pricing" --since 2026-03-01

Tips for good searches

  • Search for what people said, not document titles: "we should postpone the launch" not "launch delay meeting"
  • Search for names to find the policy-authorized normal history involving someone: "Alex" or "Case"
  • Search for decisions: "decided", "agreed", "committed to"
  • Reauthorize a selected result with minutes get "<exact path>" --json before loading full context

Gotchas

  • Search is substring, not fuzzy — "price" matches "pricing" and "price", but "prcing" (typo) matches nothing. Try multiple terms if you're not sure of the exact wording.
  • --since requires ISO date format — Use 2026-03-01, not "last week" or "March 1st". For relative dates, compute the ISO date first: date -v-7d +%Y-%m-%d.
  • Large result sets flood stdout — Always use --limit when searching broad terms. The default limit is 10, but common words can match hundreds of files.
  • QMD semantic search requires separate setup — If config.toml sets engine = "qmd" but the QMD collection isn't indexed, search will fail silently. Run qmd update && qmd embed first.
  • Voice memos vs meetings — Both are searched by default. Use -t memo or -t meeting to narrow results. Voice memos live in ~/meetings/memos/, meetings in ~/meetings/.
  • Empty results don't mean it wasn't discussed — If the meeting wasn't transcribed (e.g., recording was stopped before processing), it won't appear in search. Check minutes list to see what's been processed.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Fast non-interactive briefing before any meeting — auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds. Use this whenever the user says "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "brief me on Sarah", "I have a call in 10 min", "quick rundown", or right before walking into a meeting. Different from /minutes-prep — brief is the fast hook-fireable version that doesn't ask questions and doesn't set goals. Use brief when speed matters; use prep when the user wants to think hard about goals first.

中文简介正在准备中。当前显示原文说明。

silverstein/minutes15642026年10月22日 更新

Manage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings", "archive meetings", "manage meeting storage", or asks about disk space from minutes.

中文简介正在准备中。当前显示原文说明。

silverstein/minutes15642026年10月22日 更新

Start and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal. Use only for explicit Coach or HUD lifecycle requests such as "start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "resume Minutes Coach", "Minutes Coach status", or "stop Minutes Coach". Do not use for requests that explicitly ask the current terminal agent to watch or strategize; those belong to minutes-live-sidekick. An ambiguous request such as "coach me live" requires one short surface clarification and must not automatically start Coach.

中文简介正在准备中。当前显示原文说明。

silverstein/minutes15642026年10月22日 更新

Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording.

中文简介正在准备中。当前显示原文说明。

silverstein/minutes15642026年10月22日 更新

Policy-safe relationship rankings, commitments, aliases, person profiles, and topic research. Always use Minutes' bounded native CLI surfaces; never build or read a durable graph cache.

中文简介正在准备中。当前显示原文说明。

silverstein/minutes15642026年10月22日 更新

Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.

中文简介正在准备中。当前显示原文说明。

silverstein/minutes15642026年10月22日 更新

查看 silverstein 的全部技能

报告此技能的问题