pp-superhuman
Superhuman email from your terminal or Claude Code, backed by a local SQLite store and agent-native JSON I/O. Trigger phrases: `check my email`, `what's in my inbox`, `draft a reply to <thread>`, `send <draft> with undo`, `snooze this thread`, `look up <email>`, `who is <email>`, `use superhuman`, `run superhuman`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/productivity/superhuman/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# Superhuman — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `superhuman-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first:
1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install superhuman --cli-only
```
2. Verify: `superhuman-pp-cli --version`
3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill.
If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.3 or newer):
```bash
go install github.com/mvanhorn/printing-press-library/library/productivity/superhuman/cmd/superhuman-pp-cli@latest
```
If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds.
## When to Use This CLI
Pick the Superhuman CLI when you want email read/draft/respond access from a terminal or Claude Code, scriptable thread search backed by a local store, capability discovery via `which`, or Ask AI semantic search piped into other tools.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
- **`workflow`** — Compound commands that combine multiple API operations into one verb (see `workflow --help`).
```bash
superhuman-pp-cli workflow --help
```
- **`which`** — Resolve a natural-language capability query to the best matching command from this CLI's curated feature index.
```bash
superhuman-pp-cli which 'snooze a thread for tomorrow'
```
- **`lookup`** — Live contact enrichment for an email: name, bio, location, timezone, avatar, social links, and Twitter handle from Superhuman's profile service. Optional `--photo` downloads the contact's avatar.
```bash
superhuman-pp-cli lookup [email protected] --agent --select name,location,twitterHandle
```
- **`userdata write`** — Low-level escape hatch over Superhuman's CRDT mutation endpoint for paths the typed commands don't cover. Dry-run by default; `--apply` to fire; path must start with `users/`.
```bash
superhuman-pp-cli userdata write "users/<google-id>/settings/<key>" '{"value":true}' --apply
```
## Command Reference
**ai** — Semantic search via Ask AI
- `superhuman-pp-cli ai` — Ask AI semantic search (SSE stream)
**attachments** — Upload, list, download attachments
- `superhuman-pp-cli attachments` — Upload an attachment for a draft
**drafts** — Drafts — create, update, send, delete
- `superhuman-pp-cli drafts list` — List drafts
- `superhuman-pp-cli drafts new` — Create a fresh outbound draft with generated IDs
- `superhuman-pp-cli drafts write` — Create or update a draft (write to draft path)
**messages** — Individual messages within threads
- `superhuman-pp-cli messages get` — Fetch one message by id
- `superhuman-pp-cli messages get-by-rfc822` — Lookup a message by RFC822 Message-ID
- `superhuman-pp-cli messages list` — List messages with Gmail search syntax
- `superhuman-pp-cli messages query` — Semantic email search
**lookup** — Live contact enrichment for an email address
- `superhuman-pp-cli lookup <email>` — Fetch live profile (name, bio, location, timezone, avatar, links, Twitter handle); `--photo <path>` also downloads the photo
**participants** — Local correspondent analytics
- `superhuman-pp-cli participants list` — List email participants from the local store
- `superhuman-pp-cli participants show <email>` — Show participant details
**reminders** — Snooze reminders for threads
- `superhuman-pp-cli reminders cancel` — Cancel a snooze (un-snooze a thread)
- `superhuman-pp-cli reminders create` — Create a snooze reminder for a thread
**teams** — Team and account info
- `superhuman-pp-cli teams` — List teams the user belongs to
**threads** — Email threads — read, list, search, archive, label
- `superhuman-pp-cli threads get` — Get a thread by ID
- `superhuman-pp-cli threads list` — List recent threads
**send** — Send, schedule, and remind from one command
- `superhuman-pp-cli send` — Send a real email through Superhuman's backend
**snippets** — Reusable Superhuman UI snippets
- `superhuman-pp-cli snippets list` — List saved snippets
- `superhuman-pp-cli snippets get <name>` — Show a snippet
- `superhuman-pp-cli snippets create --name <name>` — Create a snippet
- `superhuman-pp-cli snippets update <name>` — Update a snippet
- `superhuman-pp-cli snippets delete <name>` — Delete a snippet
**awaiting-reply** — Threads that need attention
- `superhuman-pp-cli awaiting-reply` — List threads where the latest message awaits your reply
**watch** — Gmail history stream
- `superhuman-pp-cli watch` — Emit Gmail history deltas as NDJSON
**users** — User account state
- `superhuman-pp-cli users` — User achievements / gamification state
**userdata** — Low-level Superhuman CRDT surface (advanced)
- `superhuman-pp-cli userdata write <path> <json>` — Write a raw value to a CRDT path; dry-run by default, `--apply` to fire, path must start with `users/`
### Finding the right command
When you know what you want to do but not which command does it, ask the CLI directly:
```bash
superhuman-pp-cli which "<capability in your own words>"
```
`which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match — fall back to `--help` or use a narrower query.
## Recipes
### Fast triage view across recent threads
```bash
superhuman-pp-cli threads list --limit 100 --json --select id,subject,snippet,participants
```
Pull a wide swath of recent threads with only the fields you need; pipe to jq or an LLM for further triage.
### Folder views and thread filters
```bash
superhuman-pp-cli threads list --type sent --limit 20 --json
superhuman-pp-cli threads list --type starred --label IMPORTANT --json
superhuman-pp-cli threads list --participants-file participants.txt --intersect-with-stdin < thread-ids.txt --json
```
Use `--type` for common mailbox folders: `inbox`, `sent`, `done`, `starred`, `archived`, `spam`, `trash`, and `important`. Add `--label`, `--participants-file`, or `--intersect-with-stdin` when composing local-store filters.
### Draft from stdin and send with an undo window
```bash
echo 'Body text here' | superhuman-pp-cli send --to [email protected] --subject 'Update' --body-stdin --undo 30s
```
Write a draft from a piped body, then send it with a 30s undo window: agents can abort before the send fires.
### Create a fresh draft without hand-building IDs
```bash
superhuman-pp-cli drafts new --to [email protected] --subject 'Update' --body-stdin < body.txt --json
```
`drafts new` creates a fresh outbound draft and generates the Superhuman-style draft, thread, and RFC822 identifiers.
### Snooze a thread for later
```bash
superhuman-pp-cli reminders create --thread-id <thread-id> --trigger-at 2026-05-13T09:00:00Z
```
Schedule a thread to resurface at a specific time; pair with `reminders cancel` to un-snooze.
### Send with follow-up reminders and scheduled delivery
```bash
superhuman-pp-cli send --to [email protected] --subject 'Proposal' --body-file proposal.txt --remind-in 3d --if-no-reply
superhuman-pp-cli send --to [email protected] --subject 'Tomorrow' --body 'See you then' --schedule-at '+1d'
superhuman-pp-cli sendRelated 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.