meeting-prep
Comprehensive pre-meeting briefing that gathers all relevant context from Slack, email, Google Docs, Notion, and calendar. Produces a structured prep document so the manager walks into every meeting fully prepared. Supports thorough meeting preparation.
git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit /tmp/meeting-prep && cp -r /tmp/meeting-prep/plugins/people-management/skills/meeting-prep ~/.claude/skills/meeting-prepSKILL.md
# Meeting Prep > **Principle: "Narrow scope, high impact."** One meeting, one thorough brief. No guessing, only sourced context. Gathers context from all connected sources for a specific upcoming meeting and produces a structured briefing. ## When to Use - Before any meeting (1:1s have their own skill, use `/prep-one-on-one` instead) - When the manager says "prep me for [meeting]", "what do I need to know for [meeting]" - Can be invoked for the next upcoming meeting or a specific one by name/time ## Instructions If any MCP connector is unavailable, follow the connector unavailability protocol in `references/operating-principles.md`. ### 1. Identify the Meeting If not specified, check Google Calendar for the next upcoming meeting. If specified by name or time, search calendar for the matching event. Extract from the calendar event: - **Title** - **Time and duration** - **Attendees** (names and emails) - **Location/link** - **Description/agenda** (if present) - **Attached documents** (if any) If no matching meeting is found: ``` I couldn't find a meeting matching "[query]" on your calendar. Could you clarify which meeting you mean? Your upcoming meetings are: - [list next 5 meetings with times] ``` ### 2. Load Manager Context Read from `manager-context/` (created by /setup): - `manager-profile.md` for team members and stakeholders - `terminology.md` for decoding any internal terms - `sources.md` for known data locations If manager-context doesn't exist, note this: ``` ⚠️ No manager context found. Run /setup first for richer meeting prep. Proceeding with what I can find from sources directly. ``` ### 3. Gather Attendee Context For each attendee, search across sources: **Slack:** - Recent messages from/by this person (last 7 days) - Threads they've been active in that relate to meeting topics - Any messages that mention the meeting topic **Gmail:** - Recent email threads with this person (last 14 days) - Especially any threads that include multiple meeting attendees **Google Drive:** - Shared documents with this person - Docs recently edited by them that relate to meeting topics **Notion:** - Pages authored or edited by them recently - Any decision logs or project pages relevant to the meeting **From manager-context** (if available): - Their role, team, and relationship to the manager - Any known context from previous interactions ### 4. Gather Topic Context Based on the meeting title, description, and agenda: **Identify key topics** from the meeting title and description. For each topic, search: - **Slack** for recent discussions (last 14 days) - **Notion** for related pages, decisions, project status - **Google Drive** for related documents (pre-reads, previous meeting notes) - **Gmail** for related threads ### 5. Find Previous Meeting Notes Search for prior instances of this meeting: - **Google Drive:** Search for docs matching the meeting name + "notes", "minutes", "recap" - **Notion:** Search for pages matching the meeting name If found, extract: - Action items from the last meeting - Decisions made - Open questions carried forward ### 6. Produce the Briefing Read `references/output-template.md` for the full output template structure. ### 7. Present to Manager Share the briefing and offer follow-up: ``` Here's your prep for [meeting]. Anything you'd like me to dig deeper on? ``` ## Important Notes Read `references/operating-principles.md` for shared operating principles (data scope, DM flagging, signals vs diagnoses, connector unavailability). Additional notes specific to this skill: - **Don't draft talking points as scripts.** Frame as prompts: "You might want to discuss..." not "Say this..." - **If context is thin**, say so: "I found limited context for this meeting." - **1:1 meetings:** Redirect to `/prep-one-on-one` which has deeper team-member-specific logic.
Find context from past Claude Code (CLI) and Claude Cowork (desktop) sessions on this Mac. Use when the user wants to recall something they did before but can't find it , phrasings like "where did I work on X", "find that session where I…", "when did I last do Y", "pull up the conversation about Z", "that time I built/tried/discussed …". Searches by kind (code/cowork), time range, title, working directory, or free-text content across all transcripts.
Mine the user's Claude Code + Cowork session history into a structured task profile, what they do with AI, how often, how successfully where friction lives, then propose atomic skills that would reduce iteration. Use when the user asks to "analyse my Claude use", "build a task profile", "what tasks do I do with Claude", "where am I spending tokens", "what skills would help me", or mentions reviewing past sessions for patterns. Produces profile.csv (shareable), explorer.html (personal coaching view with AI-first principle comparison + token-spend chart), and skill-proposals.md.
Personal diagnosis of where your Claude Code + Cowork spend goes. Reads local transcripts, prints your conversation length distribution, marathon share, cache rebuild costs, and per-project diagnosis (good projects and problem projects) right in the terminal. Then offers a deeper dive that fans out parallel Haiku subagents over your most expensive (and most efficient) sessions and writes a tight Markdown report. Use when the user asks "why is my Claude spend so high", "where am I burning tokens", "diagnose my Claude habits", "audit my Claude usage", or asks for a personal token-cost diagnosis.
Analyze, re-engineer, or bootstrap projects to align with AI-first design principles. Use when asked to review, audit, improve, 'ai-firstify', or start a new project. Performs deep analysis across 7 dimensions, actively restructures existing projects, or guides new project setup through discovery questions. Based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp.
Analyze engagement patterns across published posts to identify what works. Use when asked to review performance, find successful patterns, or optimize future content.
Generate LinkedIn post ideas from external sources (files, URLs, research). Use when the user provides source material (PDFs, URLs, articles) to brainstorm topics. NOT for writing or developing drafts - use write-linkedin-post instead.
Generate opinion piece ideas from recent LinkedIn posts (last 30 days). Use when asked to find opinion topics, brainstorm article ideas, or cross-pollinate content between LinkedIn and opinion pieces.
Entry point for the TechWolf content-studio plugin. Use to understand the workflow, pick the right content skill, or start setup for a new author/repository.