agent-improve
Review this conversation and generate a structured improvement report.
Discover context for fixbot. This is called by `/fixbot` (or `/autobot` before launching the session) to determine the app database and gather issue context.
$ npx -y skills add metabase/metabase --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/fixbot-discoverContext preview
What this command does when you run it.
Discover context for fixbot. This is called by `/fixbot` (or `/autobot` before launching the session) to determine the app database and gather issue context.
Discover context for fixbot. This is called by `/fixbot` (or `/autobot` before launching the session) to determine the app database and gather issue context.
The user provided: `$ARGUMENTS`
`$ARGUMENTS` must include a `--output-dir <PATH>` flag — the caller (`/fixbot` or `/autobot`) generates the per-run path. Discover never picks a directory itself, so nothing is ever written to a shared `.bot/fixbot/...` location.
The positional argument can be one of three formats:
**If the input is a GitHub issue number or URL:** 1. Fetch the GitHub issue with `gh issue view <NUMBER> --repo metabase/metabase --json body,comments,title` 2. Search the issue body and comments for a Linear issue link (pattern: `https://linear.app/metabase/issue/[A-Z]+-[0-9]+`). Extract the Linear issue ID from the URL. 3. If no Linear link is found, search Linear directly: run `./bin/mage -bot-fetch-issue` with a search term derived from the GitHub issue title. If that doesn't find a match, tell the user you couldn't find a corresponding Linear issue and stop.
**Validation:** Confirm the issue ID looks like `[A-Z]+-[0-9]+`. If not, tell the user the expected format and stop.
Set `ISSUE_ID=<LINEAR_ID>`.
Parse `$ARGUMENTS` for `--output-dir <PATH>`. If absent, stop and tell the caller to pass `--output-dir`. Set `OUTPUT_DIR=<PATH>` and `TIMESTAMP=` the trailing timestamp portion of the path. All artifacts in subsequent steps go directly under `<OUTPUT_DIR>/`.
Run:
./bin/mage -bot-fetch-issue <ISSUE_ID>
Read the output to extract issue details and branch name.
Save the full output to `<OUTPUT_DIR>/linear-context.txt` using the `Write` tool.
Extract the branch name from the Linear issue output. If none specified, use the issue ID lowercased (e.g., `mb-12345`).
From the issue description/comments:
Write the structured result to `<OUTPUT_DIR>/config.env` using the `Write` tool:
APP_DB=<postgres|mysql|mariadb> BRANCH_NAME=<branch-name> ISSUE_ID=<ISSUE_ID> TIMESTAMP=<TIMESTAMP> OUTPUT_DIR=<OUTPUT_DIR>
Metabase is the easy, open-source way for everyone in your company to ask questions and learn from data.
Repo: metabase/metabase
Review this conversation and generate a structured improvement report.
Tear down and remove an autobot session (worktree, Docker containers, and tmux).
List all autobot sessions with status information.
Print the most recent `result.md` for an autobot session, so the user can see how a bot is doing without attaching to its tmux session.
Stop an autobot session (kill tmux and dev environment, but keep the worktree).
Launch a bot command in an isolated autobot session with its own worktree, backend, and frontend.