Menú
Use after completing work, implementing major functionality, or before merge. Dispatches a code-reviewer subagent to verify the work against requirements. Review early and often.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Update the per-session intent ledger for every user input and provide current intent as semantic context consumed by gates, skill-evolution, and jailbreak-detector. Keep intent summaries without storing raw prompts.
Use when the user asks about skill upgrades, update recommendations, or an evolution backlog; analyze io-trace and conduct_feedback to produce report-only evolution candidates. No automatic edits.
Use when an implementation plan already exists. Execute it in a separate session with review checkpoints.
Use when implementing a known feature, bug fix, or refactor with a resolved behavior contract. Requires a failing test before production code; use discovery first when the target or premise is unknown.
Use at the start of every coding or development conversation. Defines how to find and invoke coding-convention family skills. Requires relevant skills before any response, including clarification questions.
Runs after session-intent-analyzer and jailbreak-detector/downstream gate as their consumer. Decomposes the request and routes output, verification, lifecycle, and boundary skills without owning intake, raw intent inference, or tool permission.
| name | requesting-code-review |
| description | Use after completing work, implementing major functionality, or before merge. Dispatches a code-reviewer subagent to verify the work against requirements. Review early and often. |
| compatibility | ["Python 3.11+ standard library"] |
Dispatch the code-reviewer subagent to catch issues before they accumulate.
The reviewer receives only the context prepared for evaluation. It never
receives the session history. This keeps the reviewer focused on the work
output rather than on your thought process, and preserves your own context for
follow-up work.
○ Core principle: review early, review often
□ Required
□ Optional but valuable
□ 1. Capture the git commit hashes
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)
□ 2. Dispatch the code-reviewer subagent
Use the Task tool with the code-reviewer type. Fill in the references/code-reviewer.md template.
Placeholders
{WHAT_WAS_IMPLEMENTED}: what you just built.{PLAN_OR_REQUIREMENTS}: what you were supposed to do.{BASE_SHA}: the starting commit.{HEAD_SHA}: the ending commit.{DESCRIPTION}: a short summary.□ 3. Respond to the feedback
[Task 2 complete: validation function added]
You: Request a code review before proceeding.
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[dispatch code-reviewer subagent]
WHAT_WAS_IMPLEMENTED: conversation index validation and repair functions
PLAN_OR_REQUIREMENTS: Task 2 of .tmp/implementation-plans/deployment-plan.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: added verifyIndex() and repairIndex(), four issue types
[subagent returns]:
Strengths: clean architecture, real tests
Issues:
Important: progress indicator missing
Minor: reporting interval magic number (100)
Assessment: ok to proceed
You: [fix the progress indicator]
[proceed to Task 3]
□ Subagent-Driven Development
□ Executing Plans
□ Ad-Hoc Development
□ Never do
□ When the reviewer is wrong
Template: references/code-reviewer.md