connect
Walk the user through installing the optional composio skill and turning on screen memory
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/melandlabs/openloomi/HEAD/plugins/claude/commands/connect.md -o ~/.claude/commands/connect.mdconnect.md
# /openloomi:connect
Walk the user through three independent opt-in steps. Each step is gated by
an explicit y/N from the user. NOTHING happens silently.
## Step 1 — Verify `composio` skill readiness
Before asking the user anything, **detect** whether `composio` is already
in place. Two pieces must both exist for Step 1 to be a no-op:
```bash
# 1. CLI on PATH?
command -v composio >/dev/null 2>&1
# 2. Skill shipped in this plugin?
test -f "${CLAUDE_PLUGIN_ROOT}/skills/composio/SKILL.md"
```
Then branch on the combined result:
- **Both present** → print one line
(`composio ready: CLI on PATH, skill loaded from plugins/claude/skills/composio/`)
and continue straight to Step 2. **No y/N.**
- **CLI missing only** → ask:
> Composio CLI not on PATH. Install it via the official installer?
> (`curl -fsSL https://composio.dev/install | bash`) [y/N]
> On y, run that command. **Never run `npm install -g` without consent.**
- **Skill missing only** → ask:
> The composio skill isn't shipped in this plugin (`plugins/claude/skills/composio/SKILL.md` missing).
> Restore it (e.g. `git pull` or reinstall the plugin)? [y/N]
> On y, defer to whatever restore flow the user picks; do not regenerate
> skill content here.
- **Both missing** → ask the CLI-missing question; the skill ships
with the plugin and will come back when the plugin is restored, so
one y/N is enough.
After Step 1 resolves (no-op or install), continue to Step 2.
## Step 2 — Enable screen memory
Tell the user:
> OpenLoomi Desktop's user profile / preferences page has a "Chronicle"
> section that controls Screen Memory. Turn it on to let Loomi
> summarize what you're looking at. Open the Preferences page now? [y/N]
Only on explicit y/N: print the navigation hint
`OpenLoomi Desktop → Preferences → Chronicle → Screen Memory`
and continue.
**Do NOT print any `openloomi://...` URL.** The plugin codebase does
not register a deep-link scheme for this entry — only the navigation
hint above is real.
## Step 3 — Connect at least one messaging connector
Suggest the `openloomi-connectors` skill, which ships **with this plugin**
at `plugins/claude/skills/openloomi-connectors/`. Defer to that skill's
own onboarding flow for OAuth and connector discovery; do not duplicate
OAuth logic here.
For accounts connected through **Composio** (a broader 1000+ apps
surface — X, LinkedIn, Notion, HubSpot, Linear, Jira, etc.), invoke the
`composio` skill in parallel per that skill's own guidance. When the
user asks "what am I connected to?" or "list my accounts", present the
union of both sources.
## Reminder
Never print or echo any tokens. Never pass `--api-key` flags. Never
download additional binaries. The plugin is intentionally read-mostly.Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK
Persist learning across turns by actively maintaining MENTAL_MODEL.md in the workspace. Use for iterative coding, debugging, benchmarking, or any feedback-driven task; read and update the file with actual filesystem writes before every response, never just hidden/internal memory.
Create an end-to-end Continual Learning Bench task. Use when adding a new src/tasks/<name> benchmark task, including design interview, concrete Jinja prompt templates, JSON action contracts, observation templates, debug schedule, behavioral E2E tests, validation, smoke/debug runs with icl and icl_notepad, and README documentation.
Drive a native macOS app via the cua-driver CLI (default) or MCP server — snapshot its AX tree, click/type/scroll by element_index, verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host (e.g. "open a file in TextEdit", "navigate to /Applications in Finder", "click the Save button in Numbers").
High-performance data analysis using Polars - load, transform, aggregate, visualize and export tabular data. Use for CSV/JSON/Parquet processing, statistical analysis, time series, and creating charts.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Discover and install skills from the open agent skills ecosystem. Use when: (1) user asks "how do I do X" where X might have an existing skill, (2) user says "find a skill for X" or "is there a skill for X", (3) user asks "can you do X" where X is a specialized capability, (4) user wants to extend agent capabilities, (5) user wants to search for tools, templates, or workflows, (6) user mentions they wish they had help with a specific domain (design, testing, deployment, etc.).