mempalace
claudecodexAI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
按 AI Native 手册的方法:体检、安装配置、推荐、新项目、坑检查、复盘提炼
Plugin ainative from marketplace ainative in NeoJubao/ainative-handbook. Commands read from the repo's manifest — 15 days ago.
doctor只读体检 Claude Code 环境和当前项目:插件与 skill 是否冗余或互相抢触发、权限规则和 hook 是否还在、配置是否被切换工具覆盖、.env 与密钥是否安全、CLAUDE.md 和 docs 是否到位,输出 P0/P1/P2 问题表和一推荐一替代的修复方案,不改任何东西。当用户说:体检、诊断、检查我的 Claude Code 配置、插件太多、skill 太多、护栏还在吗、为什么插件都没了、权限规则失效、doctor、audit setup、check my Claude Code config、health check、too many plugins 时使用。
harvest把一篇复盘提炼成 1–3 张坑卡草稿:frontmatter(含一句话规则和可直接发的推文)加四段正文(发生了什么、为什么会这样、怎么做、相关),并做脱敏检查(IP、域名、密钥、账号 ID、人名、客户名、内部代号,以及你的 .ainative-denylist.txt 自定义词表);草稿只写到你指定的目录,不发布、不提交。当用户说:提炼复盘、把复盘变成卡片、沉淀经验、写坑卡、复盘总结成规则、这次事故能学到什么、harvest、retro to card、turn this postmortem into a pitfall card、extract lessons 时使用。
new-project按 AI Native 手册的第 0 步起一个新项目:确定档位和技术栈(默认 Next.js + TypeScript + Tailwind + bun,纯静态站部署到 Cloudflare),然后逐步建仓库、写一页 CLAUDE.md、建 docs 目录、写第一份以 intent 开头的 spec、配最小护栏;每个写操作前都先确认。当用户说:新项目、起个项目、开个新仓库、从零开始、初始化项目、搭脚手架、第 0 步、new project、start a new repo、bootstrap a project、scaffold、day 0 时使用。
pitfall-check用 AI Native 手册的坑库逐条审查一份计划、spec,或当前分支的 git diff(默认当前分支相对主分支),只报告真正命中的坑,每条附证据(文件和行号或计划段落)、卡片链接和具体修法,只读不改。当用户说:坑检查、查坑、用坑库审一下、合并前检查、发版前检查、这个计划有没有坑、帮我看看这个 diff 有没有踩坑、pitfall check、review against pitfalls、pre-merge check、check my plan for pitfalls 时使用。
recommend根据当前项目的真实情况推荐档位(小工具/产品/组织)、部署平台(Vercel/Cloudflare)、流程引擎(Matt Pocock skills/superpowers)、插件组合和护栏强度;每项给一个推荐、一个替代,附理由和手册链接。先自己查项目事实,只对查不到的问 1–3 个问题,只读不改。当用户说:推荐、我该用什么、该装哪些插件、选哪个平台、Vercel 还是 Cloudflare、这个项目算哪一档、要不要换流程引擎、Matt 还是 superpowers、recommend、which plugins should I use、what tier is this project 时
setup按 AI Native 手册给 Claude Code 落地配置:根据档位(小工具/产品/组织)和主引擎(Matt Pocock skills 或 superpowers)安装、启用、停用插件,合并权限规则和 hook,设置个人 skill 开关。会改配置,但一定先体检、出变更计划、做 dry-run、等你明确确认,执行前自动备份,从不删除你已有的规则。当用户说:帮我配置 Claude Code、按手册配置、应用体检建议、加护栏、装推荐插件、精简插件、切换流程引擎、setup、configure Claude Code、apply doctor fixes、install recommende
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
DataHub development and interaction toolkit with connector planning, PR review, catalog search, metadata enrichment, lineage tracing, data quality management, and connection setup skills
13 skills · 8 commands · 4 agents
Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
1 skill · hooks
CI/CD pipeline configuration, GitHub Actions/GitLab CI workflow setup, and automated deployment pipeline orchestration
4 skills · 1 command · 5 agents
Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts
13 skills · hooks
Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/autoresearch-agent:setup, /ar-run, /ar-loop, /ar-status, /ar-resume), 8 built-in evaluators, configurable loop intervals (10min to monthly).
6 skills · 1 agent · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.