Tmb comment triage

Skill trustmybot/plugin/skills/tmb_comment-triage

Bro's PR/MR comment triage — resolve the PR, fetch the comment threads, judge which are task-worthy, and dispatch SWE per ratified group. Loaded by bro when /monitor surfaces PR/MR comments.From its SKILL.md

Install

npx -y skills add trustmybot/plugin --skill tmb_comment-triage

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.9 KB, as published. Nobody here has run it

PR/MR comment triage

pr_monitor_comments_get does the deterministic fetch + since-marker bookkeeping. This skill is the judgment around what's task-worthy.

Resolve the PR

If the Human named a PR number, use it. Otherwise:

GitHub: gh pr view --json number
GitLab: glab mr list --source-branch <branch> --json

Empty result → ask the Human which PR/MR number to monitor (free-text answer).

Fetch

Call pr_monitor_comments_get with the PR number.

Carrier: resolve the linked issue with branch_report_md for the current branch rather than reading the DB directly. If unresolved, ask the Human which issue the PR is linked to (free-text answer).

Triage (judgment)

Skip as informational when:

The body is a bare acknowledgment — an LGTM, a +1, a thanks, a nit.
The author is a bot (already classified by the MCP tool).
The comment is already resolved.

Treat as task-worthy when the comment names a concrete change request (should be, please change, consider X over Y, ends with ?), or contains a code suggestion fence.

Group task-worthy comments by file or shared concept; one task per group. Flag tasks that touch DB schema files (e.g. schema/*.sql), public API surfaces, or config directories (e.g. agents/, skills/, plugin manifest files) as (arch-impact).

Dispatch

Offer the ratified groups as a multi-select — one option per group, titled by the task it would become (suffix arch-impact ones) — and let the Human pick a subset.

For each ratified group: task_create_batch(...), spawn SWE, and if arch-impact, invoke scan_run(source='bro_auto_post_change') after SWE returns to refresh the world model.