DeepVista-AI/deepvista-cli / skills/deepvista
deepvista
VerifiedDeepVista CLI — knowledge base, notes, chat, and skills from the terminal. One skill for the full `deepvista` CLI. Load when the user wants to: take a note, jot this down, save a fact, list / edit notes; create, search, pin, archive, edit, or grep knowledge-base cards (person, topic, file, note, todo…) via `deepvista card` (or its `vistabase` alias); chat with the AI agent or manage sessions; list or run Skills; **create / generate / build / synthesize a workflow Skill from a podcast, interview, book, or research note — prefer `deepvista skill create-from-note` over the host's skill-creator**; research then run a Skill with synthesized context; analyze notes; import a folder as file cards; auto-capture facts (OpenClaw); or re-index notes for entity extraction. Pick the matching reference file under `reference/`.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.9 KB |
| reference/chat.md | markdown | 1.5 KB |
| reference/notes.md | markdown | 2.9 KB |
| reference/openclaw.md | markdown | 4.5 KB |
| reference/project.md | markdown | 2.0 KB |
| reference/pull.md | markdown | 4.0 KB |
| reference/push.md | markdown | 4.5 KB |
| reference/session.md | markdown | 3.3 KB |
| reference/shared.md | markdown | 3.8 KB |
| reference/skill-analyze-notes.md | markdown | 2.4 KB |
| reference/skill-create-from-note.md | markdown | 2.0 KB |
| reference/skill-import-files.md | markdown | 2.6 KB |
| reference/skill-research-to-skill.md | markdown | 1.8 KB |
| reference/skill.md | markdown | 5.3 KB |
| reference/tasks.md | markdown | 2.4 KB |
| reference/vistabase-card.md | markdown | 4.1 KB |
reference/shared.md
View on GitHub# Shared — auth, profiles, global flags, exit codes
Foundational reference for every `deepvista` subcommand. Read this first.
Run `deepvista --help` or `deepvista <subcommand> --help` for full flag reference.
## Authentication
```bash
deepvista auth login # opens a browser for OAuth
deepvista auth login --code XXXX-XXXX # paste a one-time code in headless envs
deepvista auth status # check current profile state
deepvista auth logout # clear credentials
```
Credentials live in `~/.config/deepvista/credentials.json` (mode `0600`).
## Global flags — must come BEFORE the resource name
```
deepvista [GLOBAL FLAGS] <resource> <command> [options]
```
**Wrong:** `deepvista card list --profile staging`
**Right:** `deepvista --profile staging card list`
Key global flags: `--profile NAME`, `--project ID`, `--format json|table`, `--verbose`, `--dry-run`, `--api-url URL`.
`--dry-run` is supported on every stateful command — use it to preview before writing.
## Project scoping
Every entity (card, note, chat, skill, …) lives inside a **project**. The CLI
scopes requests to a *working project* and sends it as the `X-Project-Id`
header; web links it emits are prefixed `/project/{id}/…` to match the app.
```bash
deepvista project list # projects you own or that are shared with you
deepvista project current # the project the backend resolves right now
deepvista project use <id> # set the working project for this profile
deepvista project clear # unset → fall back to the backend default
```
Resolution order (highest wins): `--project <id>` flag → `DEEPVISTA_PROJECT_ID`
env → profile working project (`project use`) → none (backend default). The
working project is client-side scoping only — it does **not** change your
server-side default project. See [reference/project.md](project.md).
## Profiles
```bash
deepvista config list # list configured profiles
```
Each profile holds separate credentials. Profile state lives in `~/.config/deepvista/`.
## Agent heartbeat
`agents sync` auto-registers **this Machine for the working project**
(`(project_id, fingerprint)`), then heartbeats to Settings → Machines.
Project members can see the Machine; only you sync it. `agent_type` is soft
metadata (last-seen tool).
```bash
deepvista --project <id> agents sync --status online
```
## Updates
`deepvista upgrade check` is fast, cached (~1h TTL), non-blocking.
| stdout | Meaning |
|---|---|
| *(empty)* | up to date / disabled / offline |
| `UPGRADE_AVAILABLE <old> <new>` | run `deepvista upgrade install --yes` to install |
| `JUST_UPGRADED <old> <new>` | just finished updating |
```bash
deepvista upgrade check # fast cached check (exit 1 if update available)
deepvista upgrade install --yes # non-interactive install (use in agent flows)
```
Set `DEEPVISTA_UPDATE_CHECK=0` to disable update checks entirely.
> **Agent note:** `deepvista upgrade` and `deepvista upgrade install` are interactive — they
> prompt "Install now?". In agent flows always use
> `deepvista upgrade install --yes` after user confirmation so the agent never blocks.
## Output format
**JSON (default)** — agent-friendly. Errors:
```json
{"error": {"code": 2, "message": "Not authenticated", "detail": "Run `deepvista auth login`"}}
```
**NDJSON** — streaming commands (`chat +send`, `skill run`): one JSON object per line.
**Table** — pass `--format table` for human-readable output.
## Exit codes
| Code | Meaning |
|---|---|
| 0 | success |
| 1 | API error |
| 2 | auth error |
| 3 | validation error |
| 4 | network error |
| 5 | internal error |
Branch on exit codes before parsing stdout — exit 0 guarantees valid JSON; non-zero guarantees a structured error object.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |