Agent Skill · 研究检索

agent-native-architecture（Agent 本机架构）

agent-native-architecture 用于查找、检索和筛选相关信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

agent-native-architecture 是研究检索类 Agent Skill，可用宿主为 Codex、Claude、Cursor、Gemini CLI，通过GitHub 仓库获取，权限为调用外部服务；许可证信息还不明确，第三方扫描有提醒项，按安装量在研究检索类的 73,675 个 Skill 里排第 67,439。

总安装 245周安装 10GitHub Stars 7下载 79核验 2026-05-01

研究检索调用外部服务 GitHub 仓库未标认证来源可访问许可证需确认审计提醒 Codex Claude Cursor Gemini CLI

安装说明

本站只整理中文说明，不托管安装包，也不代用户安装。

GitHub

许可证: unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手，先确认命令和权限，再让它执行。

请帮我安装这个 Agent Skill：agent-native-architecture（Agent 本机架构）
来源仓库：https://github.com/iliaal/ai-skills
仓库路径：skills/agent-native-architecture
安装命令：
npx skills add https://github.com/iliaal/ai-skills --skill agent-native-architecture
安装前请先检查当前环境是否支持对应 CLI，并向我确认将要执行的命令、安装目录、联网范围和文件读写权限；确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill；本站只展示命令，不托管安装包，也不自动执行。

skills.shnpx skills

npx skills add https://github.com/iliaal/ai-skills --skill agent-native-architecture

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题，通常会让助手先检索再总结。

agent-native-architecture 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。可通过 npx skills add 命令从指定仓库安装并使用该技能。

安装前建议确认权限范围、维护状态，以及是否会触发联网或文件读写操作。可结合来源仓库和原始 README 进一步核验具体用法和功能边界。

来源仓库内路径：skills/agent-native-architecture

上手步骤

4 步

1
确认自己的宿主工具
公开资料标注支持 Codex、Claude、Cursor、Gemini CLI；先确认自己用的是其中之一，再按对应工具的 Skills 目录放置。
2
拿到安装命令
可以直接复制的命令是 npx skills add https://github.com/iliaal/ai-skills --skill agent-native-architec…；命令里的占位符换成自己的路径或密钥再执行。
3
安装后重启宿主
命令执行完要完全退出宿主工具再打开，让新装的 Skill 被重新扫描到，否则列表里可能看不到。
4
按最小权限试用
它需要调用外部服务，先在测试目录或测试账号里跑，确认没问题再放到正式项目。

常见问题

6 条

agent-native-architecture 怎么安装？

在终端执行 npx skills add https://github.com/iliaal/ai-skills --skill agent-native-architecture。装完完全退出宿主工具再打开，让它重新扫描本地 Skill。

agent-native-architecture 支持哪些 AI 工具？

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录，一般也能手动放进去，但要自己确认触发方式是否一致。

agent-native-architecture 需要什么权限？

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API，使用前需要确认账号、额度、数据发送范围和服务条款。

agent-native-architecture 是免费的吗？

公开资料没有标注明确许可证，收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

agent-native-architecture 用的人多吗？

公开数据是累计安装 245 次，近一周安装 10 次，下载 79 次，GitHub 7 星。这些数字来自第三方目录统计，只能当作热度参考，不代表质量或安全性。

agent-native-architecture 安全吗？

第三方扫描有提醒项，说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

同时适配 4 种工具，换客户端不用重新找替代品。

先想清楚的地方

许可证没有明确标注，能不能商用、能不能再分发都不确定。
第三方扫描存在提醒项或未通过项，需要人工逐条确认。
第三方目录整理，版本更新和行为细节以来源仓库为准。

适不适合你

更适合

已经在用 Codex，想直接扩展它能力的人。
需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

需要明确授权才能用到公司项目里的场景。
需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类

Skill	总安装	GitHub 星	权限	许可证	扫描
find-skills 寻找技能 · Codex、Claude	31,199,813	16,486	操作浏览器	MIT	有提醒
self-improving-agent 自我改进 Agent · OpenClaw	16,464,002	3,396	接触敏感数据	MIT-0	通过
soultrace 灵魂追踪 · Codex、Claude	7,588,944	12	需要联网	未明确	有提醒
self-improving 自我完善 · OpenClaw	6,829,284	1,046	需要联网	MIT-0	通过
microsoft-foundry 微软代工厂 · Codex、Claude	6,614,144	764	调用外部服务	未明确	有提醒
agent-native-architecture Agent 本机架构 · 本页	245	7	调用外部服务	未明确	有提醒

按安装量取同分类前几名；数字来自第三方目录统计，只作热度参考，不代表质量结论。

SKILL.md 原文

Agent-Native Architecture

Core Principles

Five principles govern agent-native design. For detailed explanations, examples, and test criteria, see core-principles.md.

Principle	One-line test
Parity	Can the agent achieve every outcome the UI allows?
Granularity	To change behavior, do you edit prose or refactor code?
Composability	Can you add a feature by writing a new prompt, without new code?
Emergent Capability	Can the agent handle open-ended requests you didn't design for?
Improvement Over Time	Does the app work better after a month, even without code changes?

Focus Area Selection

Design architecture - Plan a new agent-native system from scratch
Files & workspace - Use files as the universal interface, shared workspace patterns
Tool design - Build primitive tools, dynamic capability discovery, CRUD completeness
Domain tools - Know when to add domain tools vs stay with primitives
Execution patterns - Completion signals, partial completion, context limits
System prompts - Define agent behavior in prompts, judgment criteria
Context injection - Inject runtime app state into agent prompts
Action parity - Ensure agents can do everything users can do
Self-modification - Enable agents to safely evolve themselves
Product design - Progressive disclosure, latent demand, approval patterns
Mobile patterns - iOS storage, background execution, checkpoint/resume
Testing - Test agent-native apps for capability and parity
Refactoring - Make existing code more agent-native
Anti-patterns - Common mistakes and how to avoid them
Success criteria - Verify your architecture is agent-native
Hooks patterns - Hook events, decision control, MCP matchers, async hooks

Wait for response before proceeding.

Reference Routing

Response	Action
1, "design", "architecture", "plan"	Read architecture-patterns.md, then apply Architecture Checklist below
2, "files", "workspace", "filesystem"	Read files-universal-interface.md and shared-workspace-architecture.md
3, "tool", "mcp", "primitive", "crud"	Read mcp-tool-design.md
4, "domain tool", "when to add"	Read from-primitives-to-domain-tools.md
5, "execution", "completion", "loop"	Read agent-execution-patterns.md
6, "prompt", "system prompt", "behavior"	Read system-prompt-design.md
7, "context", "inject", "runtime", "dynamic"	Read dynamic-context-injection.md
8, "parity", "ui action", "capability map"	Read action-parity-discipline.md
9, "self-modify", "evolve", "git"	Read self-modification.md
10, "product", "progressive", "approval", "latent demand"	Read product-implications.md
11, "mobile", "ios", "android", "background", "checkpoint"	Read mobile-patterns.md
11a, "icloud", "storage", "documents", "file state", "entitlement"	Read mobile-storage.md
11b, "background task", "battery", "on-device", "cloud routing"	Read mobile-execution.md
11c, "model tier", "token budget", "cost-aware", "batch", "caching"	Read mobile-cost.md
12, "test", "testing", "verify", "validate"	Read agent-native-testing.md
13, "review", "refactor", "existing"	Read refactoring-to-prompt-native.md
14, "anti-pattern", "mistake", "wrong"	Read anti-patterns.md
15, "success", "criteria", "verify", "checklist"	Read success-criteria.md
16, "hook", "hooks", "PreToolUse", "decision control", "async hook"	Read hooks-patterns.md
0, "quick start", "getting started", "overview", "introduction"	Read quick-start.md

After reading the reference, apply those patterns to the user's specific context.

Architecture Review Checklist

When designing an agent-native system, verify these before implementation:

Core Principles

Parity: Every UI action has a corresponding agent capability
Granularity: Tools are primitives; features are prompt-defined outcomes
Composability: New features can be added via prompts alone
Emergent Capability: Agent can handle open-ended requests in your domain

Tool Design

Dynamic vs Static: For external APIs where agent should have full access, use Dynamic Capability Discovery
CRUD Completeness: Every entity has create, read, update, AND delete
Primitives over Workflows: Tools expose atomic capabilities; compose workflows in prompts
API as Validator: Use z.string() inputs when the API validates, not z.enum()
Eval Gate: 10 Q/A pairs in CI (read-only, multi-hop, closed-data), 9/10 pass threshold. See mcp-tool-design.md Evaluation section.

Files & Workspace

Shared Workspace: Agent and user work in same data space
context.md Pattern: Agent reads/updates context file for accumulated knowledge
File Organization: Entity-scoped directories with consistent naming
Context Durability: Incremental progress writes (WAL pattern) so interrupted tasks resume from last checkpoint

Agent Execution

Completion Signals: Agent has explicit complete_task tool (not heuristic detection)
Partial Completion: Multi-step tasks track progress for resume
Context Limits: Designed for bounded context from the start
Validate-Before-Run: Agent previews planned actions before executing destructive operations

Context Injection

Available Resources: System prompt includes what exists (files, data, types)
Available Capabilities: System prompt documents tools with user vocabulary
Dynamic Context: Context refreshes for long sessions (or provide refresh_context tool)
Trust levels for loaded content: System prompt distinguishes trusted (developer-authored) from untrusted (user input, retrieved docs, tool outputs); untrusted text is data, never instructions. See dynamic-context-injection.md Trust Levels section for the prompt-injection defense details.

UI Integration

Agent -> UI: Agent changes reflect in UI (shared service, file watching, or event bus)
No Silent Actions: Agent writes trigger UI updates immediately
Capability Discovery: Users can learn what agent can do

Governance

Approval Gates: Destructive or irreversible actions require user confirmation
Audit Trail: Agent actions logged with timestamp, tool, and outcome
Scope Boundaries: Agent cannot access resources outside its designated workspace

Hooks & Governance Automation

Event Coverage: Only 6 hook events fire in agent context (PreToolUse, PostToolUse, PermissionRequest, PostToolUseFailure, Stop/SubagentStop); session lifecycle logic lives in the orchestrator
Decision Gates: PreToolUse hooks enforce tool-level policy (allow/deny/ask/defer) instead of hardcoded checks
Completion Gating: SubagentStop hooks block premature completion when verification steps remain
MCP Matchers: Regex patterns target tools by server and operation for capability-based security
Two-Tier Config: Shared policy committed, personal overrides git-ignored, per-hook disable toggles

Mobile (if applicable)

Checkpoint/Resume: Handle iOS app suspension gracefully
iCloud Storage: iCloud-first with local fallback for multi-device sync
Cost Awareness: Model tier selection (Haiku/Sonnet/Opus)

When designing architecture, explicitly address each checkbox in your plan.

平台分布

Codex

32.31%

按下载量换算26

Claude

27.51%

按下载量换算22

Cursor

20.33%

按下载量换算16

Gemini CLI

10.53%

按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API，使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息，不托管安装包，不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项，安装前请自行复核。目前只有一个公开来源，建议同时核对源仓库。

继续浏览同类 Skills

更多研究检索 Skills（73,675）返回 Skills 目录

上一个 Skill

agent-native-architecture（Agent 本机架构）

8b-is/8b-is-mp

下一个 Skill

agent-native-architecture（Agent 本机架构）

petekp/claude-code-setup