Install any skill in seconds. Free to start, no credit card required.
Get Started Free →tobihagemann/answer-reviewer-questions
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer.
Passed 18 of 22 test cases with the skill, and 9 of 22 without it.
and 9 more in the full report
10 fixed8 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Process this question thread from context: thread id 'th_101', path 'src/db/connection.ts', line is null, originalLine is 58, comment asks why connection pooling is disabled, and recalled transcript explains pooling caused race conditions in integration test suites. Generate the unformatted draft answer block.
| Checked | Without skill | With skill |
|---|---|---|
| Uses originalLine number 58 in the thread header location | Missed | Passed |
| Formats the header as **Thread th_101** (src/db/connection.ts:58) | Missed | Passed |
The instructions your model reads when the skill loads.
For each reviewer question thread, recall the implementer's reasoning and compose a raw answer. The answers are plain text and feed into a downstream reply-drafting skill that applies voice rules and reply formatting.
Use the question threads from conversation context. Each thread has: thread id, file path, line (use originalLine when line is null), the reviewer's original comment, and the reconciled intent from $interpret-feedback.
If no question threads were provided, report that there are no questions to answer and stop.
For each thread:
$recall-reasoning skill with <path>:<line>. It returns either recalled reasoning from a past transcript, or a fallback derived from reading the commit diff and surrounding code.Output one block per thread:
**Thread <id>** (<path>:<line>)
<answer text>
_Grounding: derived from current code_
Include the _Grounding:_ line only when $recall-reasoning returned no transcript. Omit it when the answer is grounded in recalled reasoning.
Then call update_plan to mark this step completed and continue with the next step of the active workflow.
$github-voice or apply reply formatting. Downstream drafting applies voice rules when composing the actual reply.$recall-reasoning returned no transcript, still compose an answer from the current code and include the _Grounding:_ line so the downstream drafter knows the answer has weaker grounding.test cases passed, vs 9 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.