Verwendung
- Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
- Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
- Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/lwlee2608/agent-skills --skill second-opinionVor dem Start
- Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
- Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.
Second Opinion
Get a code review from a different agent by running a fresh headless session of it. The user wants that agent's take, not yours — relay it, don't redo it.
When review-code --second-opinion runs this skill, these rules govern only the relayed review. The caller's own review still runs, and a failure here does not stop it.
Pick the reviewer
If PI_CODING_AGENT is true, you are running in pi — the reviewer is Claude Code (claude). Otherwise the reviewer is pi.
Assume the reviewer is installed, its default model is configured, and the review-code skill is available to it. Don't probe for any of these — if it fails, surface the error and stop.
Rules
- Resolve the target in `review-code`'s vocabulary. Don't compute the diff yourself.
- PR number →
pr <N> - "PR" with no number →
pr <N>for the current branch's PR - Ref range (e.g.,
main...HEAD),all,codebase, or a path → verbatim - Otherwise →
diff
- Pass the user's model verbatim to `--model`, or omit
--modelif they named none — the reviewer falls back to its configured default.
- Run the reviewer's command from the repo root, substituting target and model. The prompt is the same for both:
Use the review-code skill to review <target> in this repo. Do not modify any files.pi:
pi -p \
--model <provider/model> \
--exclude-tools edit,write \
--name "review: <target>" \
"<prompt>"Claude Code:
claude -p \
--model <model> \
--disallowedTools Edit Write NotebookEdit \
--allowedTools "Bash(git *)" "Bash(gh *)" \
--no-session-persistence \
"<prompt>"-pprints only the final answer, so the output is safe to read in the main session.- The tool flags keep the reviewer from "fixing" findings while leaving
gitandghusable. - Reviews can take several minutes — use the longest allowed timeout or run it in the background.
- Never resume a session. No
-c,-r,--resume,--session,--session-id, or--fork— prior context pollutes the review.
- Never inline the diff in the prompt, and never pass `--second-opinion` to the reviewer.
review-coderesolves the target itself, a large diff breaks shell quoting, and the flag would make the reviewer spawn you back.
- Relay the review verbatim. Don't summarize, re-rate, or add your own findings.
- On non-zero exit, print the error and stop. Never fall back to a review of your own.
Verification procedure
- Every reported finding has a
path:linecitation. If findings lack them, the reviewer likely never loadedreview-code— re-run once, then report. A clean review with no findings needs no citations. - If pi rejects the model, check
pi --list-models <name>and retry with a listed name.

