vartifact
Show the user a visual result as a live page in VelaTerm. Use when the user asks to see, mock up, sketch or prototype a screen,…
Ask a focused question about another vlx-term session without importing its full conversation into the current context. This is the skill form of `vrefer SESSION --ask "QUESTION"`. Use it when the target session is known and the user needs a conclusion, decision, result, reason,
$ npx -y skills add vlinx-io/VelaTerm --skill vask --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/vaskContext preview
The summary Claude sees to decide when to auto-load this skill.
Ask a focused question about another vlx-term session without importing its full conversation into the current context. This is the skill form of `vrefer SESSION --ask "QUESTION"`. Use it when the target session is known and the user needs a conclusion, decision, result, reason,
name: vask description: >- Ask a focused question about another vlx-term session without importing its full conversation into the current context. This is the skill form of `vrefer SESSION --ask "QUESTION"`. Use it when the target session is known and the user needs a conclusion, decision, result, reason, or status from it. Read-only: nothing is sent to the target session and nobody is interrupted. Available only inside vlx-term-hosted local sessions. allowed-tools: Bash(vrefer:*), Bash(vsearch:*)
Use `vask` as the focused-question form of `vrefer --ask`. There is no separate shell command: invoke the existing read-only command with the session reference and the user's question.
vrefer <session> --ask "<question>"
If the target is not known, search first:
vsearch <distinctive words...> vrefer <id-from-search> --ask "<question>"
`<session>` accepts a full id, an id prefix of at least eight characters, an exact session name, or a unique substring. Quote names containing spaces. If several sessions match, select an id from the candidate list and retry rather than guessing.
By default the answering agent receives the complete transcript. If the user enabled **Summarize first** in Settings → Agents, VelaTerm compresses the transcript with the one globally selected Agent, model, and reasoning effort, adds relevant original full-text search excerpts from the same session, and then asks the answering agent. This setting is automatic; the skill command and `--ask` syntax do not change.
Use `--with <kind>` only when the user explicitly wants a particular **answering** agent. It does not change the configured pre-summary Agent. Use `--timeout <seconds>` when the default 120-second overall limit is unsuitable.
The returned text is an agent's reading of another session, not a verbatim transcript. When exact wording or broader context matters, follow up with `vrefer <session>` or `vrefer <session> --range A:B`.
If answering fails, `vrefer` explains the reason on stderr and returns the transcript as its fallback. Check stderr before treating stdout as a completed answer.
The best ADE. Not just a terminal. Not just an IDE. Manage agent sessions like Codex. Split terminals like iTerm2. VelaTerm keeps both in one native app, and brings them to your browser and your phone. Watch the intro video (2:55) · Download · User manual
Show the user a visual result as a live page in VelaTerm. Use when the user asks to see, mock up, sketch or prototype a screen,…
Query VelaTerm plan-execute workflows by session: find planner, executor and optional reviewer IDs, tasks, states, rounds,…
Query the current project's CodeGraph and the VelaTerm knowledge base only when the user explicitly requests vkb, including /vkb…
Open a file or URL in the vlx-term center pane (mirrors the `vopen` command). Markdown opens in a WYSIWYG editor, images in the…
You CAN read other sessions' conversations. Sessions are not isolated from you here: this reads any other vlx-term session's…
You CAN search other sessions' conversations. This is a full-text search across every vlx-term session on this machine or within…