メニュー
Load when the user asks to review code, audit a PR, find bugs in code they paste, or assess code quality. Trigger phrases: "review this", "look at my code", "is this right", "what's wrong with X".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Load when the user asks to queue, enqueue, or add a coding task to the fleet, dispatch a job to a repo, or ask the fleet worker to fix something. Trigger phrases: "add to fleet", "queue a job for", "send to fleet", "dispatch to".
Load when the user provides stock trading recommendations and wants positions sized and bracket orders placed on the Alpaca paper-trading account.
Load when the user wants to navigate a website, click through a flow, fill a form, extract data from a page, or record an interaction as a reusable playbook.
Load when the user is responding to a customer inquiry, complaint, or support ticket and needs help drafting a reply with the right tone.
Load when the user wants analysis on a dataset — trends, distributions, summary statistics, or insights from a CSV/JSON/Excel file.
Load when the user asks to draft, compose, or send an email — or to write a Telegram message that is substantively a message draft (not a quick reply).
| name | Code Review |
| slug | code-review |
| description | Load when the user asks to review code, audit a PR, find bugs in code they paste, or assess code quality. Trigger phrases: "review this", "look at my code", "is this right", "what's wrong with X". |
| icon | Code2 |
| color | #06b6d4 |
| version | 1.1.0 |
| category | coding |
| tools | ["read_file","search_files"] |
| config_schema | {"type":"object","properties":{"language":{"type":"string","default":"any","description":"Programming language to focus on"},"strictness":{"type":"string","enum":["strict","moderate","lenient"],"default":"moderate","description":"How strictly to enforce coding standards"}}} |
Read the actual files with read_file before commenting — never review code you haven't seen. Cite file:line for every issue.
Categorize findings as Critical / Major / Minor / Suggestion. Always pair a problem with a concrete fix, not just the observation.
Strictness ({strictness}):
strict — flag every style deviation and untested branch.moderate — flag bugs, security issues, perf cliffs, and missing tests for non-trivial logic.lenient — only flag bugs and security issues.End with a single-paragraph overall assessment.