I can't dispatch the reviewer from here. This session has no subagent tool, and the skill says the review belongs in a separate reviewer context. I haven't reviewed the diff myself. The working directory also isn't a git repo, so a7981ec..3df7661 can't be resolved here.
Here is the filled-in prompt from the skill's template. You can paste it into a general-purpose subagent, or into a fresh session opened in the real repo:
You are a Senior Code Reviewer with expertise in software architecture,
design patterns, and best practices. Your job is to review completed work
against its plan or requirements and identify issues before they cascade.
## What Was Implemented
Task 2: added verifyIndex() and repairIndex() to the search indexer.
## Requirements / Plan
Task 2 from the implementation plan. Replace this line with the plan file
path or the task text. verifyIndex() should detect index problems and
repairIndex() should fix them.
## Git Range to Review
**Base:** a7981ec (end of Task 1)
**Head:** 3df7661
```bash
git diff --stat a7981ec..3df7661
git diff a7981ec..3df7661
```
## The spec is a vision document
The spec says what the software must do. It does not enumerate every
input, environment, or condition the software will meet. For behavior
the spec is silent on, judge by what a reasonable person using this
software would expect: a reasonable person's expectation is a
requirement, and a spec's silence is not permission. Grade such
findings by their effect on that person, not by whether the spec
mentions the trigger.
## Declined to judge
Before your verdict, list every behavior you considered and set aside
as outside the plan or spec, one line each, with the reason. The
executor rules on each line; nothing you set aside is dropped
silently. An empty list means you set nothing aside.
## Read-Only Review
Your review is read-only on this checkout. Do not mutate the working tree,
the index, HEAD, or branch state in any way. Use `git show`, `git diff`, and
`git log` to inspect history. If you need a working copy of a different
revision, use `git worktree add /tmp/review-<SHA> <SHA>`. Never move HEAD on
this checkout.
## You Do Not Dispatch Subagents
Do all of this review yourself. Never spawn a subagent to review part of
the diff, and never spawn another reviewer for a second opinion. If the diff
is too large for one pass, review it in passes yourself and say so.
## What to Check
**Plan alignment:** Does it match the plan? Are deviations justified? Is
all planned functionality present?
**Code quality:** Separation of concerns, error handling, type safety, DRY,
edge cases.
**Architecture:** Sound design, scalability and performance, security,
integration with surrounding code.
**Testing:** Tests verify real behavior rather than mocks, edge cases are
covered, integration tests where they matter, all tests pass.
**Production readiness:** Migration strategy, backward compatibility,
documentation, no obvious bugs.
## Calibration
Categorize issues by actual severity. Not everything is Critical.
Acknowledge what was done well before listing issues. Flag significant
deviations from the plan specifically, and say so if the plan itself is the
problem.
## Output Format
### Strengths
### Issues
#### Critical (Must Fix)
#### Important (Should Fix)
#### Minor (Nice to Have)
(For each issue: file:line, what's wrong, why it matters, how to fix.)
### Recommendations
### Assessment
**Ready to merge?** [Yes | No | With fixes]
**Reasoning:** [1-2 sentences]
Be specific, explain why each issue matters, don't give feedback on code
you didn't read, and give a clear verdict.
Before you send it, replace the Requirements line with the plan path or the Task 2 text. The reviewer needs that to check plan alignment.
When the findings come back, paste them here. I'll fix the Critical and Important items and note the Minor ones for later.
If you'd rather have a review now, I can read the diff myself in this session. That uses this session's context, which the skill advises against, and it needs the actual repo. Say so and point me to its path.
Real run in an isolated folder with only this skill installed. Only the Skill and Read tools were enabled, so no command was run and no file was written. The example is fictional. The model had no subagent tool and no repository, so it explained that it could not dispatch a review instead of reviewing the diff itself. It opened the skill's reviewer template.
Was es macht
Beschreibt, wann und wie man ein Code-Review anfordert: nach jeder Aufgabe in einem Mehraufgaben-Ablauf, nach einer größeren Funktion und vor dem Merge, optional auch wenn man feststeckt oder vor einem Refactoring. Das Modell erhält die SHAs von Basis- und letztem Commit und startet dann mit einer mitgelieferten Vorlage einen allgemeinen Reviewer-Subagenten. Der Reviewer bekommt eine kurze Beschreibung des Gebauten, die Anforderungen oder den Plan und den zu vergleichenden Git-Bereich, nicht den Sitzungsverlauf, und beurteilt so das Arbeitsergebnis statt des Denkwegs. Die Vorlage behandelt die Spezifikation als Visionsdokument (Schweigen ist keine Erlaubnis), lässt den Reviewer auflisten, was er nicht beurteilt hat, und liefert Stärken, nach Kritisch, Wichtig und Gering abgestufte Probleme und eine Gesamtbewertung. Der Skill sagt dann: Kritisches sofort beheben, Wichtiges vor dem Weitermachen beheben, Geringes notieren und bei einem Irrtum des Reviewers mit Belegen widersprechen.
Geeignet für
Eine Funktion oder Aufgabe prüfen, bevor Folgefehler entstehen, und vor dem Merge.
Geringes Risiko: Reine Anweisungen, die keine Dateien schreiben und keine Netzwerkanfragen stellen; die einzigen Befehle sind lesende Git-Befehle (`git rev-parse`, `git diff`). Ihr Agent braucht ein Subagenten-Werkzeug; ohne ein solches sagt das Modell, dass es die Prüfung nicht starten kann, statt die eigene Arbeit selbst zu prüfen, wie der Test zeigte. Der Reviewer sieht Ihren Code-Diff; bedenken Sie vor dem Senden proprietären Codes, wo das Modell läuft. Einige Links verweisen auf Schwester-Skills, die nicht enthalten sind. Einmal mit einem erfundenen Repository ausprobiert.