agentsclimarketplace

Tmb review

Skill trustmybot/plugin/skills/tmb_review

PR-reviewer's diff-level push-gate review — check this task's diff against its spec, then write the validation_record verdict that gates the push. Loaded by pr-reviewer when reviewing a committed task. Self-contained.From its SKILL.md

Install
npx -y skills add trustmybot/plugin --skill tmb_review

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

2.7 KB, as published. Nobody here has run it

PR-reviewer protocol (push gate)

Load context via task_brief(task_id) — spec_body, commit_sha, and the changed dirs' world-model scope.

Worktree discipline

The parent CC session's main checkout may be on ANY branch. Working-tree-dependent verification reads parent's current state, NOT the commit being reviewed.

For working-tree-dependent verification use pr_monitor_worktree with the workspace root — the directory holding .claude/tmb/trajectory.db; it creates the worktree, runs your command, and removes it atomically.

Sha-based git ops (git show <sha>, git diff <sha>~1..<sha>, git ls-tree <sha>) work from any branch without a worktree — use those for diff inspection.

Review the diff against its spec

Diff the commit against its parent and judge the diff itself — cite line numbers for every finding:

  • Does the diff do what the spec's ## Description says, and nothing the typed files[] doesn't name?
  • Is each ## Success Criteria bullet visible in the diff (not just claimed)?
  • Is the changed code correct — happy path plus any failure mode the spec names?
  • Any obvious diff-level defect — broken edge case, an ## Out of Scope item touched, a doc the change made stale?

Writing the validation_attempts row — YOU write it yourself

After producing a verdict, YOU (the pr-reviewer subagent) write the validation_attempts row directly, using the spawn prompt's attempt_n and your subagent_session_id. Which path you take depends on your tool list. If validation_record is available, call it — the schema enforces the shape, and it requires subagent_session_id for the pr-reviewer role — and pass mcp_available: true (the typed signal bro reads off the row). If your tools are only Read + Bash, write the row through the fallback script at ${CLAUDE_PLUGIN_ROOT}/skills/tmb_review/scripts/validation-record-fallback.sh (--help shows the argument shape, including subagent_session_id) — it records mcp_available = 0 for you.

<!-- LOAD-BEARING-SAFETY: never delegate writing this row to bro. Bro impersonating pr-reviewer is a content-integrity violation — the server's validation_record tool returns forbidden for bro identity, and the auto-mode classifier blocks raw DB writes from bro as impersonation. The honor-system fallback is for YOU to write directly via the fallback script. -->

Keep looking

Skills are one crate of 627,559. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.