AI Native Bootstrap
为既有或新建代码仓库建立可审计的 AI 原生研发流程,生成工程规范、验证入口、证据模板与风险护栏;写入默认关闭、检查未配置即阻断、不伪造通过。触发词:初始化项目研发规范、AI 原生研发流程、接入 AGENTS.md、生成 Intent/Spec/Plan 模板、配置质量门禁、项目工程规则、bootstrap、AI-native SDLC、spec-driven workflow、evidence-based review、engineering guardrails。不适用于:普通功能开发与代码编写(应直接实现)、CI 与生产发布授权(应改用平台部署审批流程)、真实项目验收结论(应由人工结合真
AI-Native Bootstrap v1.0.0
Use this skill to build auditable working controls, not a collection of placeholder Markdown files. The source-of-truth policy is references/implementation-standard.md (read for full requirements). The operational distinctions and tool paths are in references/adapters-and-safety.md.
Entry points
Use the directory containing this SKILL.md as <SKILL_ROOT>. All bundled scripts use Python 3.9+ standard library only.
- Install the reusable skill once (user-scoped or project-scoped):
python3 <SKILL_ROOT>/scripts/install.py --agent codex --scope user --applyReplacecodexwithclaudeoropencode. The installer has no write side effects without--applyand never silently replaces existing installations. - Read-only inspect a project:
python3 <SKILL_ROOT>/scripts/bootstrap.py audit --project <REPO>python3 <SKILL_ROOT>/scripts/bootstrap.py plan --project <REPO> - Bootstrap explicitly, after evaluating the plan and approvals:
python3 <SKILL_ROOT>/scripts/bootstrap.py init --project <REPO> --adapter codex --applySupported adapters:codex,claude,opencode,all. Changes require a clean Git worktree and non-default branch; an empty, unversioned directory may be bootstrapped with an explicit warning. An existingAGENTS.mdmust not be overwritten. - Verify files after bootstrap:
python3 <SKILL_ROOT>/scripts/bootstrap.py verify --project <REPO> - Review / configure project-specific real checks:
Edit the generated candidate-check manifest in the target repository to confirm the observed commands; set each verified entry's
enabledtotrue. Then run the generated local check entrypoint (check.py). Until enabled, it must failBLOCKED(exit 2), not fake success. For authentic deterministic Evals, fill the generated cases file (empty by default) and run the evaluation entrypoint (eval.py); an empty suite also fails BLOCKED.
Execution protocol for the acting Agent
- Read repository instructions and inspect git status, architecture, tests, deployment and CI before making changes. Avoid reading
.env, secret values, key material, production data, or raw sensitive logs. - For audit/plan/harness-only requests, perform no application coding, commits, pushes or deployments. For bootstrap, only create the approved engineering harness files; do not alter business logic or lock files.
- Classify risk R0-R3 following
references/implementation-standard.md. A request to bootstrap does not authorize R2/R3 actions, CI credential changes, remote pushes or production releases. Higher-risk actions require separate explicit approval and enforced authority at the actual target system. - Respect the current repository's source of truth.
AGENTS.mdis preferred only when no authoritative file exists; preserve existingAGENTS.mdandCLAUDE.md. Treat generated Claude pointer as an adapter, not another policy owner. - Never call a scaffolded test entrypoint "complete" until real commands have been configured and run, with actual exit codes. Keep Evals as a plan until real accepted cases and an evaluation runner exist.
- If the worktree is dirty, the current branch is protected/default, files conflict, or parent directories are symlinked, do not force writes. Report the exact blocker and choose a safely isolated branch/worktree through user-authorized means.
- Record evidence as
PASS,FAIL,BLOCKED,NOT RUN, orN/Aand label unverified CI/production permissionsUNVERIFIED. AgentPASSis not human approval. - Conclude with the full A-H report specified in section 12 of
references/implementation-standard.md, including changed paths, evidence, negative tests, rollback and unresolved items. Never report an unperformed action as successful.
Required follow-through after scaffolding
- Inspect the detected candidate-check manifest: every candidate is unverified and disabled by default. Confirm real project commands and safe environment, then enable only those verified and run them.
- Add one genuine project regression if a real historical failure/test fixture is available, or mark D05
BLOCKEDwith a collection plan. No synthetic success fixtures may be claimed as a project regression. - Inspect existing CI and add deterministic gates only if safe and approved. Never infer branch protection or remote approval from a local file.
- Use a fresh-context read-only reviewer for important changes. Verify against
intent/spec/planand classify findingsIMPORTANT/NIT/UNKNOWN. - For every R2/R3 or production transition, stop at preparation, leave evidence and request approval at the actual execution boundary.
Bundle self-test
Run python3 <SKILL_ROOT>/scripts/validate_bundle.py and python3 -m unittest discover -s <SKILL_ROOT>/tests -v. Check references/adapters-and-safety.md when adapting tooling. Do not automatically install dependencies or use network access.
Provenance
- 产物版本:1.0.0;构建与上架迁移日期:2026-11-13。
- 构建器:SkillBuddy v2.4.6(静态审核、缺陷修复与 WorkBuddy 上架迁移)。
- 署名主体:擎漫网络;关联品牌 Qomob.AI。
- 方法来源:包内实施标准标注为 Anthropic《The AI-Native SDLC Playbook》(54 页)及针对现有项目的工程化扩展;发布方另提供「基于 Claude《The AI-Native SDLC Playbook 2》提炼」的表述。两种表述尚未核对统一,对外文案引用前须由发布方确认原始出处;本包不宣称其为原文逐条规定。
- 关键假设:目标项目可由 Python 3.9+ 标准库只读审计;Git 非强制前提;生产权限与审批不由包内文件强制。
- 已验证范围:包内离线自检 22/22(macOS / Python 3.13.12);SkillBuddy 静态预检、官方校验与行为沙盘结果见随包审核报告。证据级 E2(静态 + 沙盘模拟)。
- 未验证:WorkBuddy 宿主 T1/T2/T3 实测、平台审核结果、真实项目接入、Python 3.9-3.12 兼容矩阵、Codex/Claude/OpenCode 会话内的技能发现。
behavior_verification: not_run。
免责声明
本技能会在本地读写仓库文件、执行项目中已有的检查命令,并检查 Git 状态与目录结构。所有写入默认关闭,须显式 --apply;审计与计划阶段为只读。请在干净、隔离的分支或工作树中使用,启用任何项目检查前先自行审查命令内容与运行环境。本包不会读取或上传 .env、令牌、私钥等凭据值,不联网、不推送、不部署;但也正因如此,它不能替代 CI、分支保护与生产审批等真实执行侧的强制措施。生成的报告属于技术建议,不构成人工验收或生产发布授权;重要场景请在真实环境复验后再投入使用。
Related skills
- Downloads
- Security audit
- Review
- Last updated
- 3d ago
- Current version
- v1.0.0
- License
- MIT-0
