Devlab Tech Debt Ops
seed-forge/harness-ai-kit技术债全生命周期运维：审计分析\u2192建议报告\u2192确认后重构（微观+宏观）\u2192回归验证。覆盖从\u201c发现债务\u201d到\u201c安全消除\u201d的闭环。Triggers on \"\u91cd\u6784\", \"\u6280\u672f\u503a\", \"\u6280\u672f\u503a\u5ba1\u8ba1\", \"audit\", \"god class \u592a\u5927\", \"\u62c6\u5206\u6a21\u5757\", \"refactor\", \"tech debt\", \"\u4ee3\u7801\u592a\u4e71\u8981\u91cd\u6784\", \"tech debt audit\".
At a glance
This skill is for Coding.
git clone --depth 1 https://github.com/seed-forge/harness-ai-kit
cp -r harness-ai-kit/skills/devlab-tech-debt-ops ~/.claude/skills/devlab-tech-debt-ops
Also in seed-forge/harness-ai-kit
View the repo国内镜像源与代理分层策略（Docker / Debian / Alpine / Node / Python / Maven / Gradle / Go），用于 Dockerfile 与 CI 的可维护加速。
Goal 驱动执行技能。将计划（Plan）转化为可追踪、可恢复、有验收标准的闭环执行流程。 每次制定计划或执行计划时自动激活，确保任务从启动到交付全程...
AI Agent / LLM 应用工程化方法论。指导如何把一个 AI 智能体应用"拆成哪几块 + 如何避免重走老路"：分层管道、规则优先+LLM兜底、多模型触点路由、Pr...
Review completed dev sessions to decide whether work should be distilled into devlab-* assets (skills, CLI tools, MCP servers, loops, subage...
前后端契约规范技能（contract 技能簇首个，定位介于 devlab-srv-* 与 devlab-web-* 之间）。约束大型前后端分离项目的接口/序列化契约、字段类型一致...
DAO 层通用 SQL 方言兼容性检查 + 系统性修复工作流。支持 MyBatis/JPA/MyBatis-Plus/SQLAlchemy 四种持久层框架，扫描源码识别 Oracle/PostgreSQL/My...
eval 自评测体系驱动的 AI Agent 生产体系方法论。以评测集为核心资产，建立"评测集组织 + Mock 隔离 + 标准化比对 + 自动评测脚本 + 回归门禁"闭环；...
通用 spec 驱动的 AI 协作开发方法论。把需求转成 requirements/design/tasks 三件套提案作为事实源，经审查→细化→分任务执行→回归验证，全程 human-o...
评估技术库/框架与项目需求的适配度，识别结合点、约束和集成方案。适用于技术选型决策、库集成可行性分析、框架迁移评估。 Triggers on "tech fit",...
存量 Web 系统深度功能验收方法论（L1-L4）。registry 功能点驱动 + 唯一入口执行器 + 假成功嗅探 + 三对齐审计，覆盖盘点建模、用例固化、失败五分类...
容器 OOM 全链排查。从 dmesg OOM killer → cgroup memory limits → Docker/Compose memory 配置 → swap → 应用内存分析，定位根因并输出修复建议。
Other Coding skills
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI be...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design...
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model...
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS,...
Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor...