mcpbeat Sign in

Minutes Search Agent Skill

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".

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1405
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/silverstein/minutes --skill minutes-search

The instruction itself

8 sections, as written by the author

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

| Flag | Description |

|------|-------------|

| -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.

Other skills for the same job

different authors, same section of the catalogue
Brand Voice Enforcement
by anthropics
vendor ×1

> This skill applies brand guidelines to content creation. It should be used when the user asks to "write an email", "draft a proposal", "create a pitch deck", "write a LinkedIn post", "draft a presentation", "write a Slack message", "draft sales content", or any content creation request where brand voice should be applied. Also triggers on "on-brand", "brand voice", "enforce voice", "apply brand guidelines", "brand-aligned content", "write in our voice", "use our brand tone", "make this sound like us", "rewrite this in our tone", or "this doesn't sound on-brand". Not for generating guidelines from scratch (use guideline-generation) or discovering brand materials (use discover-brand).

5k tokens
Digital Brain
by christophacham
×1

This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.

32k tokens scripts
Chat Motion Overlay
by nexu-io

Generate configurable chat motion overlays from a transcript or screenshot, including plain bubble scenes, app-style chat containers, optional device frames, preset or uploaded avatars, nickname display rules, and transparent-video-ready Remotion bundles. Use when Codex needs to create reusable short-form chat clips for Douyin, demo videos, story reenactments, social-message proof scenes, or embeddable alpha overlays for Hyperframe and Remotion workflows.

335k tokens scripts
Frame Macos Notification
by nexu-io

Realistic macOS notification banner with app icon, title, and body, suited to video overlays or product teasers.

2k tokens zh
Brand Review
by anthropics
vendor

Review content against your brand voice, style guide, and messaging pillars, flagging deviations by severity with specific before/after fixes. Use when checking a draft before it ships, when auditing copy for voice consistency and terminology, or when screening for unsubstantiated claims, missing disclaimers, and other legal flags.

3k tokens
Import Guidelines
by indranilbanerjee

Import brand guidelines. Use when: adding voice guides, style restrictions, or messaging frameworks.

2k tokens
Content Repurposing
by rampstackco

Cross-format content adaptation. Turning one substantial piece into many derivative formats (blog series, email sequences, social posts, webinars, podcasts, video shorts) without losing the original's value or producing AI-slop variants. The discipline of adaptation per medium rather than mass-blast distribution. Triggers on content repurposing, content adaptation, cross-format content, content atomization, content multiplication, content distribution across formats, source-piece-to-derivative, video shorts from blog, email from whitepaper, podcast from article, blog series from research. Also triggers when a flagship piece is shipping but the team has not planned how to extend it across formats, when repurposing is happening but the derivatives feel mass-produced, or when AI-assisted repurposing is producing slop variants of strong source pieces.

31k tokens
Container Scanning
by BagelHole

Scan container images for vulnerabilities using Trivy, Grype, and cloud-native tools. Identify security issues in base images, packages, and configurations. Use when implementing container security, building secure images, or meeting compliance requirements.

2k tokens

How to use it

Copy the folder

Take silverstein/minutes-.opencode-minutes-search from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.