一键导入
tuicr
// Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in tmux/zellij when a user needs an interactive review pane.
// Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in tmux/zellij when a user needs an interactive review pane.
| name | tuicr |
| description | Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in tmux/zellij when a user needs an interactive review pane. |
Use tuicr review as the default agent interface. The TUI is where the human
reviews code; the CLI is how the agent discovers active sessions, reads user
comments, and, only when appropriate, adds agent-authored comments.
First decide which workflow the user is asking for:
User-led review of agent-generated changes
tuicr review comments when they say comments are ready. If you are
explicitly waiting while the user reviews, poll the same command
periodically and look for new comment IDs.Agent review of an AI-generated patch
tuicr review add and an explicit --username
identifying the agent. Ask first when the workflow or session is ambiguous.If the user's intent is ambiguous, ask which workflow they want.
Determine the repository directory from the user's request, current working directory, or recent file operations. Ask if it is ambiguous.
List persisted sessions:
tuicr review list --repo /path/to/repo
Choose the session:
"active": true, attach to it."active": true as a convenience signal. If slug resolution fails, ask the
user for the slug or repo path used by the session.The CLI works even if the agent is not running inside tmux or zellij, so do not require a multiplexer just to connect to an existing active session.
When the user needs an interactive tuicr pane and no active session exists:
| Environment | Action |
|---|---|
$TMUX is set | Run tuicr-wrapper.sh /path/to/repo |
$ZELLIJ is set | Run tuicr-wrapper-zellij.sh /path/to/repo |
| Neither is set | Tell the user you are waiting for them to start tuicr in the repo, then attach with tuicr review list after they say it is ready |
If both $TMUX and $ZELLIJ are set, prefer the innermost multiplexer if that
is clear; otherwise ask.
Wrapper paths are relative to this skill directory:
<skill-directory>/tuicr-wrapper.sh /path/to/repo
<skill-directory>/tuicr-wrapper-zellij.sh /path/to/repo
If your tool supports command timeouts, use a long timeout, such as 10 minutes,
because the wrappers wait for the TUI to exit. Once the TUI creates its active
session, use tuicr review list --repo /path/to/repo to capture the slug. If
your environment cannot run another command while the wrapper is waiting, read
the comments after the user exits tuicr.
This is the main review loop for user-led review.
There is no push stream from tuicr to the agent. Read comments by running the CLI on demand. After the user says comments are ready, or after the TUI exits, run:
tuicr review comments --repo /path/to/repo --session <slug>
The command emits JSON. Each comment includes fields like:
idlocationpathstart_lineend_linesidecomment_typelifecycle_statecontentTreat these comments as the user's review feedback:
issue: blocking problem to fix firstsuggestion: consider implementing or explain why notnote: answer or acknowledgepraise: no action requiredIf you are waiting during an active review, poll this command about every 30 seconds and compare comment IDs with the previous result. Read immediately when the user says comments are ready. Stop polling once the user says the review is done or your tooling would block other work.
If the result is empty, ask whether the user saved comments in the intended
session or whether another active session should be selected. If the review may
have continued while you were working, rerun tuicr review comments before
claiming completion.
Only add comments when the workflow allows it and, for agent-authored review, after the user approves writing them into tuicr.
Defaults:
--type issue for problems by default.suggestion, note, or praise when that better matches the intent.--username so agent comments are visually distinguishable.Examples:
tuicr review add --repo /path/to/repo --session <slug> \
--target-file src/main.rs \
--line 42 \
--side new \
--type issue \
--username "Codex" \
"Handle the empty case here."
tuicr review add --repo /path/to/repo --session <slug> \
--target-file src/main.rs \
--type suggestion \
--username "Codex" \
"Consider splitting this file-level concern into a helper."
Omit --target-file for a review-level comment. Add --end-line for a range
comment. Use --side old for removed lines and --side new for added or
unchanged lines in the new file.
For structured input, use --input with literal JSON, @path/to/file.json, or
- for stdin. Supported target types are review, file, line, and
line_range.
Older wrapper-driven flows may emit:
=== TUICR INSTRUCTIONS ===
...
=== END TUICR INSTRUCTIONS ===
If present, process those instructions. Otherwise prefer
tuicr review comments; it is the primary source of review feedback. If the
wrapper mentions clipboard export, ask the user to paste it only when the CLI
comments are unavailable.
tmux:
Ctrl-b then arrow keysqCtrl-b then Ctrl-arrowCtrl-b then zzellij:
Alt + arrow keysqCtrl-n, then arrow keysAlt-fAlt + [ / ]| Situation | Action |
|---|---|
| Multiple plausible active sessions | Ask which session slug to use |
| No active session, tmux/zellij available | Start a new tuicr pane with the matching wrapper |
| No active session, no multiplexer | Tell the user you are waiting for them to start tuicr |
tuicr not installed | Tell the user to install tuicr |
| Not a repository | Ask for the correct repo directory |
| Comments are empty | Confirm the selected session or ask the user to save/add comments |
git diff output.