---
title: "ai-native-sdlc"
description: "AI-native agent skills for running a verifiable software development lifecycle and improving reusable skills through human-reviewed feedback loops."
canonical: https://agentpluginsdirectory.com/plugins/ai-native-sdlc
last-updated: 2026-10-21
---

# ai-native-sdlc
AI-native agent skills for running a verifiable software development lifecycle and improving reusable skills through human-reviewed feedback loops.
- Slug: ai-native-sdlc
- Publisher: idevlab
- Repository: https://github.com/IchenDEV/sdlc-skill
- Manifest: plugin.json
- Version: 1.1.0
- License: MIT
- Category (editorial): devops-cloud
- Skills: 2 (ai-native-sdlc, self-improving-agent)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-08-29
- Repository last pushed: 2026-08-30
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/ai-native-sdlc
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What ai-native-sdlc does, in the publisher's words

一组面向真实软件交付的 Agent Skills：既能把开发生命周期连成可验证的运行系统，也能用高质量反馈持续改进已有 skill。

本项目遵循 Agent Skills 开放标准和 Agent Plugins 1.0.0 规范，同时兼容 Codex 和 Claude Code 插件格式。

- Bootstrap: 为项目从零搭建端到端 SDLC 链路
- Run a change: 让一项变更沿现有链路推进
- Audit: 只读检查链路是否真实闭合
- Incident to improvement: 把事故连接到改进循环
- Initialize: 为一个现有 base skill 建立独立学习目录
- Record and triage: 标准化保存反馈，按来源、强度和不同任务聚合证据

交互式安装会让你选择目标 Agent 和安装范围（项目/全局）。

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/IchenDEV/sdlc-skill/HEAD/README.md

## Skills

- ai-native-sdlc: Bootstrap, run, audit, or improve an AI-native software development lifecycle. Use when the user asks to set up SDLC, manage a change through a lifecycle, audit their development process, or connect incidents to improvements. Covers intent, spec, plan, build, verification, review, release, operatio…
- self-improving-agent: Build or operate a human-reviewed feedback loop that improves an existing agent skill through evidence, focused proposals, evals, and reversible edits. Use when the user asks to make a skill or agent improve from feedback, establish an improver loop, analyze accumulated agent feedback, or apply an…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.