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/session.md
View on GitHub# Session — agent conversation transcripts
`deepvista session` is the dedicated CLI surface for recording an agent run
as a rolling context card (`type=session`). Distinct from:
- **`notes`** — explicit user-authored knowledge.
- **`card`** — incidental info recorded mid-conversation.
Run `deepvista session --help` or `deepvista session <cmd> --help` for full
flag reference.
## Commands
`init` · `tick` · `finalize`
> [!CAUTION] All three are write commands. `init` creates a card on first
> call; `tick` and `finalize` update it. Safe to invoke from hook scripts
> (`SessionStart`, `Stop`, `SessionEnd`).
## Lifecycle
1. **`session init`** — idempotent. Creates a card with
`type=session` keyed by the agent's session id, tagged `cc-session:<id>`,
`agent:<type>`, and `project:<dir>`. Caches the card id locally at
`$XDG_STATE_HOME/deepvista/sessions/<session_id>.json`. Safe to call on
every `SessionStart`.
2. **`session tick`** — parses the transcript JSONL, extracts turns past
the cached `last_turn_index`, appends a summary block per turn, and bumps
the frontmatter `turn_count` / `version`. The update is tagged
`reason="session-tick"` so version history stays readable.
3. **`session finalize`** — flips `status: complete` in the frontmatter and
queues enrichment via `/index_notes`. Pair with the optional final
`--transcript` flush.
Existing rolling notes created by `deepvista notes session-*` (pre-DV-742,
`type=note`) are still recovered on `init` (legacy-tag fallback) so an
in-flight session keeps ticking through the new commands.
## Examples
```bash
# SessionStart hook
deepvista session init \
--session-id "$CLAUDE_SESSION_ID" \
--transcript "$CLAUDE_TRANSCRIPT_PATH" \
--cwd "$PWD"
# Stop hook
deepvista session tick \
--session-id "$CLAUDE_SESSION_ID" \
--transcript "$CLAUDE_TRANSCRIPT_PATH"
# SessionEnd hook
deepvista session finalize --session-id "$CLAUDE_SESSION_ID"
```
## Skipping nested sub-agent sessions
`session init` short-circuits when `--cwd` matches any pattern in
`session_skip_cwd_patterns` (a top-level list in
`~/.config/deepvista/config.json`). This stops the SessionStart hook from
recording sub-agent sessions whose CWD is not a real working directory — e.g.
**claude-mem's observer sub-claude** runs with
`cwd=~/.claude-mem/observer-sessions` and only quotes file paths from the
*primary* session; recording it pollutes the vistabase with bogus File cards.
Defaults skip `*/.claude-mem/observer-sessions[/*]`. Patterns are
fnmatch-style Unix shell globs (`*` matches across `/`). To override, edit
`~/.config/deepvista/config.json` by hand — add a top-level
`session_skip_cwd_patterns` list. An explicit empty list disables skipping.
```jsonc
{
"default": { "api_url": "https://api.deepvista.ai" },
"session_skip_cwd_patterns": [
"*/.claude-mem/observer-sessions",
"*/.claude-mem/observer-sessions/*",
"*/scratchpad/*"
]
}
```
When a session is skipped, `init` emits
`{"skipped": true, "reason": "cwd matches session_skip_cwd_patterns", ...}`
and creates no card. Downstream `tick` / `finalize` self-no-op because no
card was cached (exit 3 "Unknown session", silenced by the hook scripts).
## See also
- [notes.md](notes.md) — explicit user-authored knowledge.
- [vistabase-card.md](vistabase-card.md) — generic card CRUD (`--type person|todo|…`).
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 |