Run all available tests and linters, check for anti-patterns, and generate a comprehensive code quality report
中文简介正在准备中。当前显示原文说明。
Check code for standardization, readability, maintenance complexity, and defensive coding practices
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Analyze the apple-fm codebase for code hygiene issues. Generate a report on standardization, readability, maintenance complexity, and defensive coding.
Scope: src/, apple-fm-helper/main.swift, and (where relevant) tests/.
src/ is lowercase/camelCase matching the primary concept
(cliArgs.ts, protocol.ts, session.ts). Flag a name that matches neither..js; import type for type-only
imports (eslint enforces order — if lint passes, order is fine). The .js
check is your responsibility.--temp expects a number, got "abc"). Flag terse throw new Error('failed').src/protocol.ts,
apple-fm-helper/main.swift, tests/fixtures/stub-helper.js, and
docs/4-protocol.md must all agree. Flag any divergence.src/*.ts over ~200 LOC.apple-fm-helper/main.swift may touch FoundationModels;
only helper.ts spawns the process; pure logic stays in protocol.ts /
session.ts / cliArgs.ts. Flag any layer violation (e.g. session.ts
spawning directly instead of going through an injected GenerateFn).package.json dependencies stays empty. Flag additions.parseArgs rejects unknown commands/flags and bad
numbers; parseEvent throws on malformed lines; helper.ts bounds the
subprocess with a timeout and captures stderr. Verify these still hold.any / non-null: grep src/ for : any, as any, <any>, and !
non-null assertions (tests get a pass). House style is unknown + narrowing.error event (not a bare crash)
and exits nonzero; availability is checked before generation.For each finding: File (path + lines), Category (standardization | readability | maintenance | defensive), Severity (high | medium | low), Description, Suggestion.
End with a prioritized top-N (apple-fm is small — expect 0–5 in a healthy state).
Suggest Hot Sheet tickets (hs-task for cleanups, hs-bug for defects) for
non-trivial findings.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Run all available tests and linters, check for anti-patterns, and generate a comprehensive code quality report
中文简介正在准备中。当前显示原文说明。
Check requirements docs against implementation and report discrepancies
中文简介正在准备中。当前显示原文说明。
Read the latest Glassbox code review and apply all feedback annotations
中文简介正在准备中。当前显示原文说明。
Read the Hot Sheet worklist and work through the current priority items
中文简介正在准备中。当前显示原文说明。
Run as a distributed worker — continuously claim, work, and release Up Next tickets
中文简介正在准备中。当前显示原文说明。
Create a new bug ticket in Hot Sheet
中文简介正在准备中。当前显示原文说明。