Guides, a 56-item checklist, a ready PR template, and a fill-in team policy for code review culture. Includes 10 good/bad comment pairs and 30 situational review comments, unified by a blocker/suggestion/nit/question/praise severity system.
编程专家.Skill P8级编程助手,覆盖：软件/网站项目总控、API设计、Bug诊断、代码生成、代码审查、重构、测试用例、性能基准、技术选型、文档生成、任务拆解、Spec驱动、Karpathy规范、CMS二次开发、前端设计、MySQL、项目知识图谱。支持 @标识 显式调用跳过路由。
Turn open-ended survey responses into a reviewable codebook, coded CSV, theme summary, quote table, and insight deck outline. 将开放式问卷回答整理成可人工复核的 codebook、编码表、主题摘要、引用表和洞察汇报大纲。No fabrication, no PII leakage, no statistical overclaiming.
Audits local static HTML/CSS against 11 selected WCAG 2.1 AA checks, optionally applies conservative local HTML fixes with .bak backups, and exports JSON/HTML reports. No SSH, remote deployment, or compliance certification.
One URL in, three client-ready deliverables out: a WCAG 2.2 AA / ADA audit that samples up to 20 same-domain pages with axe-core browser checks, and produces a Markdown remediation report with severity-ranked, copy-paste fixes, a branded PDF grouped by severity, and a fixed-schema JSON for Jira or APIs. Findings are deduplicated, mapped to WCAG Success Criteria and backed by explicit scan-quality warnings, giving agencies and SMBs audit-ready evidence for ADA risk reviews.
This is the scoring reference the agent uses to turn raw crawl/API data into prioritized findings. Keep this file as the single source of truth — update it whenever a real audit reveals a false positive or a missing check. Scope covered: Crawlability & Indexation, Performance (Core Web Vitals), Structure & Markup. (Mobile/Architecture can be added in a later version.)