skills/meetings/SKILL.md
Search and query meeting transcripts, summaries, and knowledge base
npx skillsauth add athal7/dotfiles meetingsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Meeting data lives in ~/meetings/ as markdown files with YAML frontmatter.
~/meetings/YYYY-MM-DD-<slug>.md — meeting markdown (frontmatter + summary + transcript in one file)~/meetings/knowledge/people/<slug>.md — person profiles (contact info, current work, style, personal, key decisions)~/meetings/knowledge/projects/<slug>.md — project profiles (Linear/GitHub links, status, key decisions, people)~/meetings/knowledge/decisions/log.md — chronological decision log across all meetings~/meetings/knowledge/names.json — display name → canonical name mapping (people)~/meetings/knowledge/projects.json — project name → canonical name mapping~/meetings/knowledge/product-labels.json — Linear label → product profile mapping~/meetings/knowledge/github-repos.json — GitHub repo → project profile mappingThree categories, updated automatically from meetings, Slack, Linear, and GitHub:
People — distilled reference cards: contact info (Email, Slack ID), current work, communication style, personal details, key decisions. Profiles consolidate automatically when they grow past 40 lines.
Projects — current state with metadata links (Linear project URLs, GitHub repos). Products get Linear label mappings; projects get direct URLs. Name normalization via projects.json prevents duplicates.
Decisions — cross-meeting decision log. Later decisions that supersede earlier ones are reconciled automatically — the log reflects current state, not accumulated contradictions.
Search transcripts and summaries using grep, ripgrep, or file reads. Frontmatter fields: title, type, date, duration, status, source, recorded_by.
New Zoom meetings are processed automatically by launchd when a caption file is saved. Slack DMs and private channels are scanned daily at 6am. To manually process:
python3 -m kb meeting /path/to/caption.txt # new Zoom caption
python3 -m kb meeting /path/to/meeting.md # reprocess existing (KB + reminders only)
python3 -m kb enrich --slack --since 48 # scan last 48h of Slack
python3 -m kb enrich --linear # sync Linear project URLs and labels
python3 -m kb enrich --github # sync GitHub repo URLs
python3 -m kb enrich # all sources
python3 -m kb enrich --dry-run # preview what would change
Requires PYTHONPATH=~/.local/lib (set automatically by the LaunchAgents).
development
Zoom meeting captions — file locations and format
tools
macOS dictation custom vocabulary — sync knowledge base names and terms to the system spelling dictionary
testing
Look up people, projects, products, and decisions locally first: contact info (email, Slack ID, GitHub handle), titles and teams, project/product status, who works on what, and past decisions. Check before searching Slack, email, calendar, or GitHub — this is the first stop for any contact detail, project context, or decision-history question.
testing
Communication style, audience awareness, and AI-authorship markers for human-facing prose — load when composing chat messages, review comments, merge request descriptions, emails, doc bodies, or ticket descriptions