granola
Access and process Granola meeting notes and transcripts via the granola CLI (MCP-backed). Use when pulling meeting data, analyzing transcripts, backfilling meetings, or any task involving Granola meeting content.
What this skill does
# Granola Meeting Intelligence
Access Joel's Granola meeting notes via the `granola` CLI, which wraps the Granola MCP server through `mcporter`.
## Setup
- **Binary**: `~/.local/bin/granola`
- **Source**: `~/Code/joelhooks/granola-cli`
- **Config**: `~/.config/granola-cli/mcporter.json`
- **Transport**: MCP via mcporter (NOT direct API, NOT npm package)
- **Auth**: Uses Granola's local credentials automatically
## CLI Commands
### List meetings
```bash
granola meetings [--range this_week|last_week|last_30_days|custom] [--start YYYY-MM-DD] [--end YYYY-MM-DD]
```
### Get meeting details (summary, participants)
```bash
granola meeting <meeting-id>
```
### Get full transcript
```bash
granola meeting <meeting-id> --transcript
```
### Search meetings
```bash
granola search "<query>"
```
### Check auth/connection
```bash
granola --help
```
Returns `"connected": true` if MCP transport is working.
## Output Format
All commands return agent-first JSON with HATEOAS `next_actions`:
```json
{
"ok": true,
"command": "granola meetings",
"result": { ... },
"next_actions": [
{ "command": "granola meeting <id>", "description": "Get details" }
]
}
```
## Important Notes
- **Timestamps are UTC.** Granola returns all dates in UTC. A meeting showing "5:01 PM" on Feb 26 is actually 9:01 AM PST. Always convert when displaying to Joel or writing to Vault files.
- **Codex cannot run Granola.** The MCP transport (mcporter) requires a local socket that Codex sandboxes can't open (`EPERM`). Always pull transcripts from pi/gateway sessions, not codex tasks.
## Known Limitations
- **Rate limiting**: `get_meeting_transcript` endpoint rate-limits aggressively. Don't batch transcript pulls — space them out.
- **Concurrency**: Keep concurrency at 1 for transcript fetches. Original concurrency of 3 overwhelmed the API.
- **Granola app not required locally**: The MCP server handles auth via stored creds, Granola desktop app does NOT need to be running.
## MCP Tools (underlying)
The granola CLI wraps these MCP tools:
1. `query_granola_meetings` — NL search with citations
2. `list_meetings` — by time range
3. `get_meetings` — details by ID array
4. `get_meeting_transcript` — verbatim transcript by ID
## Pipeline Integration
When a new meeting is detected, fire an Inngest event:
```bash
curl -X POST "http://localhost:8288/e/$EVENT_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "meeting/noted",
"data": {
"meeting_id": "<id>",
"title": "<title>",
"date": "<YYYY-MM-DD>",
"source": "granola",
"participants": ["Person A", "Person B"]
}
}'
```
Inngest functions that process meetings:
- `check/granola-meetings` — event-triggered check for new meetings
- `granola-check-cron` — hourly cron (`7 * * * *`) polling for new meetings
- `granola-backfill` — bulk backfill all meetings
## Related
- ADR-0055: Granola Meeting Intelligence Pipeline
- Source repo: `~/Code/joelhooks/granola-cli`
- Inngest functions: `packages/system-bus/src/inngest/functions/check-granola.ts`
- Meeting analysis: `packages/system-bus/src/inngest/functions/meeting-analyze.ts`
- Transcript indexing: `packages/system-bus/src/inngest/functions/meeting-transcript-index.ts`
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.