Agent skill

Hai Architecture

by hylarucoder in hylarucoder/hai-stack

Investigates architecture and change complexity from repository runtime paths to bounded modules, React components, and shared contracts.

Custom licenceAuto-check passedFrontend & Design

Install Hai Architecture

skills CLI
$ npx skills add hylarucoder/hai-stack --skill hai-architecture -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hylarucoder/hai-stack hai-architecture --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hylarucoder/hai-stack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hai-architecture .claude/skills/hai-architecture && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hai-architecture
GitHub stars
382
Token cost
~2.1k tokens
SKILL.md length
1,045 words
Files
18 (incl. references)
Skills in repo
18
Repo updated
First seen
Licence
Custom licence

At a glance

Investigates architecture and change complexity from repository runtime paths to bounded modules, React components, and shared contracts.

  • Works in 6 steps: Read every cited file in this session… → Trace callers and implementations before… → Read ADRs, dependency rules,… → …
  • 系统太绕、架构审查、模块边界、组件诊断、props API、effect/re-render
  • SKILL.md covers Purpose, Select the work mode, Evidence gate and Core judgments, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hai Architecture is an agent skill from hylarucoder/hai-stack. Investigates architecture and change complexity from repository runtime paths to bounded modules, React components, and shared contracts. Use for 系统太绕、架构审查、模块边界、组件诊断、props API、effect/re-render, or SSOT/双源/漂移、重复规则、多处默认值、同名异形. Select global or bounded mode; return traced evidence, the complexity center, alternatives, and a first proof. React and SSOT lenses retain scored diagnosis or adjudicated treatment reports. Use hai-debug for unexplained faults and code-review-and-quality for diff/local-smell reviews.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 19 other files, including reference files (for example `SKILL.zh_CN.md`, `agents/openai.yaml` and `references/global-audit.md`).

It sits in Frontend & Design, covering React components. It works with React.

When your agent uses it

  • 系统太绕、架构审查、模块边界、组件诊断、props API、effect/re-render
  • SSOT/双源/漂移、重复规则、多处默认值、同名异形

Example prompts

  • “Use the hai-architecture skill to investigate architecture and change complexity from repository runtime paths to bounded modules, React components…”
  • “/hai-architecture”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read every cited file in this session and cite real file:line locations.
  2. Trace callers and implementations before asserting a call chain or blast radius; name the search.
  3. Read ADRs, dependency rules, architecture tests, and public contracts that declare intended
  4. Compare a module's public surface with the complexity it actually hides before calling it deep
  5. Count each root cause once; cross-reference related symptoms instead of multiplying findings.
  6. Label inference as unverified instead of presenting it as evidence.

What it can do on your machine

Read from SKILL.md and the folder at commit a6c7ed2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hai Architecture loads about 2.1k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 132 tokens; SKILL.md has 1,045 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~132
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,045 words (~2,063 tokens).

“For Chinese readers, see SKILL.zh_CN.md. The English SKILL.md is the execution source of truth.”

— opening of SKILL.md by hylarucoder, Custom licence
name
hai-architecture

Read the full SKILL.md on GitHub

Files

SKILL.md and 17 other files (references) in skills/hai-architecture of hylarucoder/hai-stack.

  • SKILL.md
  • SKILL.zh_CN.md
  • agents/openai.yaml
  • references/global-audit.md
  • references/global-lenses.md
  • references/global-output-template.md
  • references/go-patterns.md
  • references/html-report.md
  • references/output-template.md
  • references/principles.md
  • references/react-output-template.md
  • references/react-patterns.md
  • references/red-flags.md
  • references/ssot-detection-cookbook.md
  • references/ssot-output-template.md
  • references/ssot-patterns.md
  • references/typescript-patterns.md
  • references/worked-example.md

Open the folder on GitHubat commit a6c7ed2

Compare with similar skills

Hai Architecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hai Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hai Architecture this skillhylarucoder/hai-stack382—~2.1kAutomated safety check: PassCustom licence
React Router Developmentremix-run/react-router57k1 repos~1.5kAutomated safety check: PassMIT
React UI State PatternsChrisWiles/claude-code-showcase6.1k8 repos~1.6kAutomated safety check: PassNone
Vercel React Best Practicessanity-io/sanity6.4k130 repos~1.6kAutomated safety check: PassMIT
Dify Component Writing Guidelanggenius/dify158k—~626Automated safety check: PassCustom licence
React Frontend Development Guidelinesdiet103/claude-code-infrastructure-showcase10k2 repos~2.9kAutomated safety check: PassMIT

Similar skills

  • React Router Development

    remix-run/react-router

    Guides work on React Router apps by first identifying whether the app uses Framework, Data or Declarative mode, then loading the matching reference and the installed package docs.

    57k GitHub starsUsed in 1 repo~1.5k tokens
    Frontend & DesignAuto-check passed
  • React UI State Patterns

    ChrisWiles/claude-code-showcase

    Sets patterns for React interfaces: when to show loading spinners or skeletons, how to surface errors, how to disable buttons during async work and how to handle empty lists.

    6.1k GitHub starsUsed in 8 repos~1.6k tokens
    Frontend & DesignAuto-check passed
  • Official

    React and Next.js performance optimization guidelines from Vercel Engineering.

    6.4k GitHub starsUsed in 130 repos~1.6k tokens
    Frontend & DesignAuto-check passed
  • Use when implementing or refactoring React/TypeScript components and the task requires decisions about component ownership, feature boundaries, state, data…

    158k GitHub stars~626 tokensUpdated today
    Frontend & DesignAuto-check passed
  • React Frontend Development Guidelines

    diet103/claude-code-infrastructure-showcase

    Guidelines for React 18 and TypeScript apps covering Suspense data fetching, lazy loading, feature folders, MUI v7 styling, TanStack Router and performance.

    10k GitHub starsUsed in 2 repos~2.9k tokens
    Frontend & DesignAuto-check passed
  • React Best Practices

    mastra-ai/mastra

    React performance optimization guidelines from Mastra Engineering.

    29k GitHub stars~1.9k tokensUpdated today
    Frontend & DesignAuto-check passed

More from hylarucoder/hai-stack

All 18 skills in this repo
  • Verify a defined software change against requirements and produce a proportional, evidence-backed acceptance report with specification precedence, scope boundaries, requirement-to-evidence…

    382 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check passed
  • Hai Ast Grep

    hylarucoder/hai-stack

    Produces a ready-to-run ast-grep command or reusable YAML lint/codemod rule, validated against positive and negative fixtures.

    382 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed
  • Readme Beautifier

    hylarucoder/hai-stack

    Reformats and restructures a README or similar Markdown project document without changing its factual content, voice, or scope, then summarizes formatting-only edits.

    382 GitHub stars~1.8k tokensUpdated 3 days ago
    Auto-check passed
  • Hai Visual Explainer

    hylarucoder/hai-stack

    Turns supplied content into self-contained HTML and PNG in two modes: card for one shareable frame(知识卡、信息卡、金句卡、封面、把要点做成一张图), report for multi-section documents(可视化报告、HTML 汇报页、PRD/计划/评审做成网页).

    382 GitHub stars~2k tokensUpdated 3 days ago
    Auto-check passed
  • Code Review And Quality

    hylarucoder/hai-stack

    Reviews a code change for correctness, security, maintainability, architecture, performance, and verification gaps, or performs a local code-smell review.

    382 GitHub stars~934 tokensUpdated 3 days ago
    Auto-check passed
  • Entity Model Auditor

    hylarucoder/hai-stack

    Audits an entity model field by field: what should exist, what exists now, where each value belongs (column, config, computed runtime value, or removal), and what must migrate.

    382 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed

Works with

Questions about Hai Architecture

What does Hai Architecture do?

Investigates architecture and change complexity from repository runtime paths to bounded modules, React components, and shared contracts. Hai Architecture is an agent skill from hylarucoder/hai-stack. Investigates architecture and change complexity from repository runtime paths to bounded modules, React components, and shared contracts.

When should I use Hai Architecture?

Hai Architecture fits situations like: 系统太绕、架构审查、模块边界、组件诊断、props API、effect/re-render; SSOT/双源/漂移、重复规则、多处默认值、同名异形.

How do I install Hai Architecture in Claude Code?

Run `npx skills add hylarucoder/hai-stack --skill hai-architecture -a claude-code`. Or copy the skill folder (skills/hai-architecture in hylarucoder/hai-stack) into .claude/skills/hai-architecture in your project. Claude Code loads it when a task matches its description.

How do I install Hai Architecture in Codex?

Run `npx skills add hylarucoder/hai-stack --skill hai-architecture -a codex`. Or copy the skill folder (skills/hai-architecture in hylarucoder/hai-stack) into .agents/skills/hai-architecture in your project. Codex loads it when a task matches its description.

Can I use Hai Architecture in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hylarucoder/hai-stack --skill hai-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hai-architecture, .gemini/skills/hai-architecture, .github/skills/hai-architecture and .opencode/skills/hai-architecture in your project.

What does Hai Architecture need to run?

SKILL.md names no scripts, command-line tools or credentials: Hai Architecture is instructions for the agent only.

Does Hai Architecture access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hai Architecture safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hai Architecture use?

Hai Architecture has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Hai Architecture use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 16k tokens, read only when the agent opens those files.

What are the alternatives to Hai Architecture?

Skills that share tags, products or a category with Hai Architecture: React Router Development (remix-run/react-router, 57k stars), React UI State Patterns (ChrisWiles/claude-code-showcase, 6.1k stars), Vercel React Best Practices (sanity-io/sanity, 6.4k stars) and Dify Component Writing Guide (langgenius/dify, 158k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hai Architecture?

hylarucoder (a GitHub user) maintains it in hylarucoder/hai-stack, which has 382 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 5, 2026.

Source: hylarucoder/hai-stack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.