CommunityProductivity & Collaborationgithub.com

MeetingAnalysis

Turn meetings into structured summaries and tracked action items. Transcribes recordings locally (faster-whisper on CUDA, Apple Silicon or CPU), imports Google Meet / Gemini notes through connectors, or takes pasted notetaker transcripts; writes a summary with decisions and an action table; pushes only your own items to the BattlePlan tracker. Includes an unattended inbox ingest (drop a recording, get a summary) and a hard rule that recordings never land in a git repo. USE WHEN analyze meeting, meeting summary, transcribe meeting, transcribe recording, summarize this call, what happened in the meeting, import meeting notes, Gemini notes, Google Meet notes, import meetings to tracker, auto ingest meetings, meeting inbox, process recordings folder, set up meeting analysis.

What is MeetingAnalysis?

MeetingAnalysis is a Claude Code agent skill that turn meetings into structured summaries and tracked action items. Transcribes recordings locally (faster-whisper on CUDA, Apple Silicon or CPU), imports Google Meet / Gemini notes through connectors, or takes pasted notetaker transcripts; writes a summary with decisions and an action table; pushes only your own items to the BattlePlan tracker. Includes an unattended inbox ingest (drop a recording, get a summary) and a hard rule that recordings never land in a git repo. USE WHEN analyze meeting, meeting summary, transcribe meeting, transcribe recording, summarize this call, what happened in the meeting, import meeting notes, Gemini notes, Google Meet notes, import meetings to tracker, auto ingest meetings, meeting inbox, process recordings folder, set up meeting analysis.

Works with✓Claude Code~Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/juanmherrerav/agent-workday-skills/tree/main/skills/MeetingAnalysis

Installed? Explore more Productivity & Collaboration skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

What does MeetingAnalysis do?

Recordings, notes or pasted transcripts in; a short, structured summary and your action items out. Every path, person and account comes from the user's config, never from this skill.

Step 0 — every invocation starts here

MA="${SKILLS_HOME:-$HOME/.claude/skills}/MeetingAnalysis/Tools"
python3 "$MA/meeting_config.py" check            # ok: true, or the list of problems
python3 "$MA/meeting_config.py" show <context>   # the resolved profile for one context

No config, or a problem listed → run Workflows/Setup.md first. Config lives at $MEETING_ANALYSIS_CONFIG, else ${AGENT_SKILLS_CONFIG:-~/.config/agent-skills}/MeetingAnalysis/config.json.

Workflows

TriggerWorkflow
first use, new context, new notes provider, "set up meeting analysis"Setup
a recording path, "analyze this meeting"Analyze: relocate → transcribe → frames → summarize → tracker → archive → verify
"just transcribe"TranscribeOnly
"import meeting notes", Gemini notes, a pasted notetaker transcript, a meeting linkImportNotes
/MeetingAnalysis ingest <context> --unattended, "meeting inbox", schedulingAutoIngest

HARD INVARIANT — no media in a repo

Meeting folders are usually inside a git repository (a notes repo, a second brain). Git keeps every committed blob forever: one 800 MB recording costs 800 MB on every clone, permanently, and deleting the file later does not give the space back.

Allowed in a meeting folderForbidden
.md, .txt, .json, .jsonlvideo: .mp4 .mkv .mov .webm .avi
at most 5 exceptional .jpg keyframes, ≤ 1 MB total (§ Frames)audio: .wav .mp3 .m4a, any extracted audio
.png frames, any file over 20 MB
  1. The source recording is never copied or moved into a meeting folder. The summary names it.
  2. If an input recording sits inside a git work tree, move it to recordings_archive first, then work from the new path.
  3. Scratch audio and frames go to a temp dir and are deleted at cleanup.
  4. § Verification must print nothing before reporting success.

meeting_config.py check refuses a recordings_archive or ingest home inside a git work tree.

Confidential contexts

"confidential": true means the meeting belongs to an employer or client and the meeting folder or tracker is personal. Then: no verbatim transcript or notes copied (the summary links to the source instead), summaries in generic terms (decisions, topics, owners, ticket IDs), no hostnames, IPs, account IDs, credentials, customer names or customer data, and tracker items as TICKET-ID: short generic summary.

Output format

<meetings_dir>/YYYY-MM-DD-<slug>/
├── YYYY-MM-DD-<slug>-summary.md
├── YYYY-MM-DD-<slug>-transcript.txt     # [MM:SS] lines   (not for confidential contexts)
├── YYYY-MM-DD-<slug>-transcript.json    # segments        (not for confidential contexts)
└── frames/                              # rare; ≤ 5 jpg, ≤ 1 MB

<slug> is short kebab-case from the meeting title (weekly-status, pricing-review; add the other person's name for 1:1s). Summary:

# <Meeting title> — YYYY-MM-DD

**Attendees:** …
**Source:** <recording filename (archived outside the repo) | notes doc link | pasted transcript from <tool>>
**Transcript:** <filename | link | not copied>

---

## Context
## Topics Discussed
### 1. <Topic> (MM:SS–MM:SS)
## Decisions
## Immediate Action Items
| # | Action | Owner | Priority | Deadline |
|---|--------|-------|----------|----------|
## Key Takeaways

The action table lists every owner so the record is complete; only yours go to the tracker.

Action items → tracker

tracker: "BattlePlan" in the config sends your items through BattlePlan's idempotent batch-add ("none" skips the step). Yours means: owner is you or one of your owner_aliases, you are one of several owners, or "we/the team" in a meeting you attended. Sub-context: first matching tracker_sub_context_rules regex on the action, else the context's tracker_sub_context. Resolve relative deadlines against the meeting date. Source: Meeting: <title> YYYY-MM-DD (recording|notes|pasted), stable across runs because dedupe keys on it. Show a --dry-run and get a yes unless running unattended.

Names

Speech recognition and notetakers mangle names. Correct them against the roster file (roster_file: one person per line, Name: alias, misspelling, …) and the attendee list (calendar event or notes header). Mark low-confidence corrections Name (?); never guess.

Frames (video only; scratch only)

Frames are analysis input, not a deliverable. Extract to a temp dir, read them, write what they show into the summary (slides → key text; screen shares → what was shown; structure → a mermaid diagram), then delete them.

ffmpeg -i <video> -vf "select='gt(scene,0.3)',showinfo" -vsync vfr "$TMP/frames/part1_%03d.png"   # 0.15 if < 2 frames

Keep a frame only if all hold: its content cannot be expressed as text, a table or mermaid; it is dense (not a gallery view or title slide); the summary's conclusions depend on it; and the summary references it by name. Save kept frames as ffmpeg -i in.png -vf scale=1280:-2 -q:v 4 frames/partN_MMmSSs.jpg. When unsure, discard: the recording and the timestamp remain.

Verification

find "<meeting folder>" -type f \( -iname '*.mp4' -o -iname '*.mkv' -o -iname '*.mov' -o -iname '*.webm' -o \
  -iname '*.avi' -o -iname '*.wav' -o -iname '*.mp3' -o -iname '*.m4a' -o -iname '*.png' -o -size +20M \) -print
find "<meeting folder>" -path '*/frames/*' -type f | wc -l      # must be ≤ 5

Empty output is the only pass. Anything listed: move it out, tell the user, do not report success.

Tools

ToolDoes
meeting_config.py check|show|env|contextsLoad and validate the config; resolve one context
transcribe.py REC --out-base DIR/transcript [--lang auto|en|es] [--model turbo|large-v3]Local transcription, writes .txt + .jsonl, prints stats JSON. Backends: CUDA → Apple MPS → CPU int8
run_ingest.sh --context NAME [--install|--check|--status|--force|--local]The unattended inbox runner and its scheduler

Dependencies

uv (scripts declare their own Python deps). ffmpeg only for frame extraction. A GPU is optional: on CPU, a one-hour meeting takes about two hours with turbo. Notes import needs the agent's Google Drive / Docs (and optionally Gmail, Calendar) connectors for the right account.

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

BattlePlan

Daily execution plan from a task tracker (local CSV, Excel workbook, or Google Sheet). Groups open tasks by context and sub-context, estimates time, finds parallel threads, and writes ready-to-paste starting prompts per thread. Starts from yesterday instead of from zero — recaps the previous day's agent sessions and git commits, pre-fills the audit, and offers resume commands. Includes an end-of-day handoff (--close), an unattended morning draft (--draft), and task management (add, done, cancel, restore, sweep, batch import). USE WHEN plan my day, daily plan, battle plan, what should I work on, close the day, end of day handoff, morning draft, task overview, standup prep, prioritize tasks, add a task, mark task done, set up battleplan, configure task tracker.

CodeQuality

Code quality loop for any repo, seen through two lenses — a tool lens (linters, type checkers, security, dead-code and duplication scanners; fix by P0 security → P1 correctness → P2 maintainability) and a principle lens (SOLID + Clean Code smells; one principle at a time, propose → confirm → apply behind characterization tests). One manifest of free local tools, one scan, one fix loop, one mandatory Quality Improvement Report. USE WHEN improve code quality, analyze code, fix linting, reduce duplication, add types, security scan, test coverage, refactor, improve code design, apply SOLID, clean code refactor, reduce complexity, kill code smells, make code maintainable, refactor legacy code, single responsibility, dependency inversion, remediation sprint, install quality tools, quality baseline, smell report, refactoring roadmap, what should we fix first. NOT FOR the issue lifecycle, branches, PRs or merging (use IssueFlow; its Remediation workflow calls this skill to pick and scope the w

Related Skills