Updated 1w ago
by HWYD
ai-mind
一个按版本持续演进的 AI Native Runtime Skeleton。 它从本地聊天闭环起步,逐步演进到: 结构化流式协议 Tool Calling Multi-Tool Runtime Skill Runtime MCP / Agent / 数据层
20 GitHub stars (20)
Steady at 20 stars — no new stars in the 16 days since Sep 30.
- 15 skills (15 skills found in its SKILL.md files)
- 3 forks (3 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add HWYD/ai-mind
Asks which skills and agents to install. Just one: npx skills add HWYD/ai-mind --skill ai-mind-implementation-reader — add -g for every project.
Claude Code
git clone https://github.com/HWYD/ai-mindcp -r "ai-mind/.agents/skills/ai-mind-implementation-reader" ~/.claude/skills/
Copies the ai-mind-implementation-reader skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add HWYD/ai-mind
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
ai-mind-implementation-reader
Read completed AI Mind version implementation code after a version, Step, or feature has been built. Use for AI Mind only to explain the real code reading order, key files and functions, main execution flow, and plain-language implementation summary based on git diff, changed files, actual source, recent commits, and the version spec when version implementation is involved. Does not do code revie…
.agents/skills/ai-mind-implementation-reader/SKILL.md on GitHub (opens in a new tab) -
ai-mind-step-audit
当 AI Mind 的某个 specs task / tasklist step 已经实现完成、需要进入下一 Step 前做阶段性工程审计时使用;如果用户没有指定 Step,默认尝试从 specs/<version-topic>/tasks.md 定位最新已完成或当前待审 Step。该 Skill 会对照 specs 中的 spec / plan / tasks / acceptance / decisions、相关 ADR 和 architecture docs,检查实现质量、范围控制、回归风险、Agent/Resource/Tool/Stream 约束、测试验证是否充分,并输出人工 Review 路线、关键代码链路讲解和是否可以进入下一 Step 的判断。
.agents/skills/ai-mind-step-audit/SKILL.md on GitHub (opens in a new tab) -
ai-mind-technical-blog
基于 AI Mind 的真实版本资料、最新实际源码、测试与 Git 变更,分析技术博客选题、设计大纲、撰写完整初稿或优化既有文章。用于“分析 AI Mind 某版本适合写什么博客”“整理版本博客大纲”“根据 AI Mind 实现写技术博客”“优化 AI Mind 既有博客”等场景,服务 AI Mind 的版本工程复盘。
.agents/skills/ai-mind-technical-blog/SKILL.md on GitHub (opens in a new tab) -
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch t…
.agents/skills/shadcn/SKILL.md on GitHub (opens in a new tab) -
speckit-agent-context-update
Refresh the managed Spec Kit section in coding agent context file(s)
.agents/skills/speckit-agent-context-update/SKILL.md on GitHub (opens in a new tab) -
speckit-analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
.agents/skills/speckit-analyze/SKILL.md on GitHub (opens in a new tab) -
speckit-checklist
Generate a custom checklist for the current feature based on user requirements.
.agents/skills/speckit-checklist/SKILL.md on GitHub (opens in a new tab) -
speckit-clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
.agents/skills/speckit-clarify/SKILL.md on GitHub (opens in a new tab) -
speckit-constitution
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
.agents/skills/speckit-constitution/SKILL.md on GitHub (opens in a new tab) -
speckit-converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
.agents/skills/speckit-converge/SKILL.md on GitHub (opens in a new tab) -
speckit-implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md
.agents/skills/speckit-implement/SKILL.md on GitHub (opens in a new tab) -
speckit-plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
.agents/skills/speckit-plan/SKILL.md on GitHub (opens in a new tab) -
speckit-specify
Create or update the feature specification from a natural language feature description.
.agents/skills/speckit-specify/SKILL.md on GitHub (opens in a new tab) -
speckit-tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
.agents/skills/speckit-tasks/SKILL.md on GitHub (opens in a new tab) -
speckit-taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
.agents/skills/speckit-taskstoissues/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.