@whaojie797-design

8 款生产级 AI Agent Skill：持久记忆、代码安全评审、自然语言数据分析、调试复现、测试生成、IaC 安全扫描、性能诊断、文档生成 | 8 production-ready agent skills (memory, code-review security, NL data analysis, agentic debugger, testforge, iac-guard, perf-doctor, docsmith). Pure Python stdlib, zero dependencies.

four-agent-pipeline agent skill: Specifier -> Coder -> Refactorer -> Architect. Turn a vague requirement into gate-verified code with Gherkin acceptance specs, steel-cage quality gates (coverage, complexity, duplication, mutation score), and automatic failure routing. Zero-dependency Python scaffolder included. MIT.

Auditable change-proof package for AI code changes: what changed, why safe, how to verify, risks remain. AI 代码改动验收 Skill

Portable, recoverable, verifiable agent handoff protocol across Codex/Claude Code/Cursor/Gemini CLI. 跨 Agent 任务续航 Skill

Generate a 10-minute readable engineering onboarding pack for any local repo. Deterministic static analysis; Python/TS-JS/Docker Compose. Agent Skill for Codex/Claude Code/Cursor.

Responsible Chinese brand-voice & content-quality editor Skill: specific, factual, on-brand. 中文品牌表达校准 Skill

Verifiable Chinese research evidence pack: official & primary sources first, facts/inferences/unknowns separated. 中文可信研究 Skill

Chinese decision-style business report Agent Skill - messy materials into traceable, decision-ready Chinese reports. 中文决策型商业报告 Skill

Local, deterministic change-monitoring for the web sources your agent depends on. (init/check a sources.yml; flags content/title/new/gone changes, HIGH on watch keywords.)

Agent Skill: reverse-engineer how a video was made. Extracts real keyframes/subtitles/audio, then produces a shot list, ready-to-paste AI image+video prompts, and a full replication guide (AI and live-action paths).

Detect drift between a Mermaid architecture diagram and the codebase it describes. (check parses graph/flowchart, scans definitions + import/call, flags missing-in-code / stale-edge / missing-in-diagram.)

Static, local, explainable pre-install security audit for Agent Skills. Scans SKILL.md/scripts/config for destructive commands, hidden network calls, secret reads, obfuscation, prompt injection, persistence. CLI + 36 fixtures + GitHub Actions.

China-aware candidate<->role fit scoring for agents. (assess a profile against a role; five weighted dimensions + China-specific red flags like age_35 / 996 / non_compete.)

四智能体 AI 编程流水线提示词：需求规格官→编码官→重构官→架构守门官，钢铁笼子质量关卡（覆盖率/圈复杂度/变异得分）+ 失败路由表，让 AI 互相制衡、机器卡终局 | Four-agent AI coding pipeline prompts (Specifier→Coder→Refactorer→Architect) with steel-cage quality gates, mutation testing and failure routing.