Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →seemseam/assigned-review-chain
Submit one node result to the assigned Reviewer and finish only after a bounded pass/rework chain.
Passed 15 of 19 test cases with the skill, and 6 of 19 without it.
and 10 more in the full report
11 fixed6 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
The review response for task 'queue-worker-05' from 'reviewer-riley' came back as 'status: non_converged'. What terminal status must be reported?
| Checked | Without skill | With skill |
|---|---|---|
| Returns terminal status needs_rework. | Missed | Passed |
The instructions your model reads when the skill loads.
Use this skill only when the node task names one assigned Reviewer.
The only Coder terminal status enum is done|blocked|needs_rework.
After implementation and verification, run exactly once per bounded review hop:
command ask --chain --artifact-reply <assigned-reviewer> <<'EOF'
Node: <node id>
Workgroup: <workgroup id>
Visible workspace identity: <controller-assigned workspace identity>
Canonical node work packet ref: <ref>
Allowed paths:
- <project-relative path>
Acceptance refs:
- <ref>
Verification refs:
- <ref>
Verification results:
- <command and result>
Changed paths:
- <path>
Blockers:
- <none or exact blocker>
Review the current node against the supplied work packet and acceptance refs.
Your first non-empty reply line must be exactly one of:
- status: pass
- status: rework_required
- status: blocked
- status: non_converged
Do not put a preamble or code fence before that machine line.
EOF
Replace <assigned-reviewer> with the literal Reviewer name supplied in the
node task. It is not an environment variable and must not be inferred.
test cases passed, vs 6 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.