memory
Search OpenLoomi memory (files + knowledge base + insights) — thin doorway into the openloomi-memory sub-skill
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/melandlabs/openloomi/HEAD/plugins/claude/commands/memory.md -o ~/.claude/commands/memory.mdmemory.md
# /openloomi:memory <query>
Thin doorway into the
[`openloomi-memory`](../skills/openloomi-memory/SKILL.md) sub-skill.
- With a `<query>` argument → runs `search-all` across local memory
files, the knowledge base (RAG), and recent insights.
- With no argument → lists the most recent 7 days of insights
(`list-insights --days=7`) so the user can see what's already been
captured.
For everything else (filter by channel, get a single document / insight,
create / update / delete, time-travel queries, living connections,
entity registry) say "memory search", "knowledge base", "insights" —
the sub-skill's frontmatter triggers on those phrases and walks Claude
through the right subcommand.
The CLI lives at
`${CLAUDE_PLUGIN_ROOT}/skills/openloomi-memory/scripts/openloomi-memory.cjs`
and auto-reads the bearer token from `~/.openloomi/token`.
## Steps
1. **With query** — run a comprehensive search:
```bash
node ${CLAUDE_PLUGIN_ROOT}/skills/openloomi-memory/scripts/openloomi-memory.cjs \
search-all "<query>"
```
Aggregate results from `memory` (local files), `knowledge` (RAG), and
`insights`. Print top 5 from each source with file path / doc id /
insight id and a short preview. If the user wants more, run the same
with `--limit` raised, or fall through to a specific source via the
sub-skill's `search-memory` / `search-knowledge` / `list-insights`
commands.
2. **Without query** — list recent insights:
```bash
node ${CLAUDE_PLUGIN_ROOT}/skills/openloomi-memory/scripts/openloomi-memory.cjs \
list-insights --days=7
```
Print the most recent 10 (or all if fewer than 10) with their `type`,
`groups`, `time`, and a short `content` preview.
3. If the user asks for a specific source after seeing results, dispatch
to the matching subcommand:
| Source | Subcommand |
| -------------- | -------------------------------------------------------------------------------- |
| Local files | `search-memory "<query>" [--directory=<subdir>]` |
| Knowledge base | `search-knowledge "<query>"` or `list-documents` / `get-document <id>` |
| Insights | `list-insights [--days=N] [--channel=<gmail\|telegram\|...>] [--keyword=<k>...]` |
## Failure modes
| Symptom | What to surface |
| ------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------- |
| `~/.openloomi/token` missing or unreadable | Run `/openloomi:setup` first to mint a guest bearer. |
| CLI exits with `AUTH_FAILED` | Same as above — token is stale or invalid. |
| `search-knowledge` returns empty | Likely no documents uploaded yet. Tell the user the knowledge base is empty and they can upload via OpenLoomi Desktop → Knowledge Base. |
| `search-memory` returns empty | Local `~/.openloomi/data/memory/` has no matches for the query. That's a legitimate result, not an error — surface the empty `results` array. |
## Constraints
- **Never** delete memory files or insights without explicit user
confirmation of the target path / id. The CLI's `delete-memory` /
`delete-insight` commands are irreversible.
- **Never** write to `~/.openloomi/data/memory/` directly from this
command. Use `add-memory` (with `--file` and `--directory`) so the
filename and placement are deterministic and audit-able.
- The skill is a **doorway** — don't duplicate the sub-skill's full
API reference here. If the user asks for something this doc doesn't
cover, route to the sub-skill via natural-language triggers.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
Walk the user through installing the optional composio skill and turning on screen memory
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.