preflight — community preflight, agentkit-forge, community, ide skills

v1.0.0

关于此技能

非常适合需要为 Windows 项目提供自动化质量保证和交付检查的开发代理。 Runs enhanced delivery checks before ship: quality gates, changelog, coverage delta, commit convention conformance, TODO/FIXME hygiene, and documentation updates for externally visible changes.

JustAGhosT JustAGhosT
[0]
[0]
更新于: 3/8/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 4/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Concrete use-case guidance Explicit limitations and caution
Review Score
4/11
Quality Score
41
Canonical Locale
en
Detected Body Locale
en

非常适合需要为 Windows 项目提供自动化质量保证和交付检查的开发代理。 Runs enhanced delivery checks before ship: quality gates, changelog, coverage delta, commit convention conformance, TODO/FIXME hygiene, and documentation updates for externally visible changes.

核心价值

赋予代理人执行质量门禁、验证变更日志和覆盖率增量检查,并确保提交约定一致性、TODO/FIXME 卫生和文档更新,使用类似 pnpm 的协议对外可见的更改。

适用 Agent 类型

非常适合需要为 Windows 项目提供自动化质量保证和交付检查的开发代理。

赋予的主要能力 · preflight

为 Windows 开发人员自动执行预发检查
验证实际项目的变更日志和覆盖率增量
强制执行提交约定一致性和 TODO/FIXME 卫生

! 使用限制与门槛

  • 需要 pnpm 安装
  • 仅限 Windows 开发环境
  • 仅限具有特定配置文件 (.agentkit/spec 和 .agentkit/overlays/agentkit-forge) 的项目

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The page lacks a strong recommendation layer.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

preflight 是什么?

非常适合需要为 Windows 项目提供自动化质量保证和交付检查的开发代理。 Runs enhanced delivery checks before ship: quality gates, changelog, coverage delta, commit convention conformance, TODO/FIXME hygiene, and documentation updates for externally visible changes.

如何安装 preflight?

运行命令:npx killer-skills add JustAGhosT/agentkit-forge/preflight。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

preflight 适用于哪些场景?

典型场景包括:为 Windows 开发人员自动执行预发检查、验证实际项目的变更日志和覆盖率增量、强制执行提交约定一致性和 TODO/FIXME 卫生。

preflight 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

preflight 有哪些限制?

需要 pnpm 安装;仅限 Windows 开发环境;仅限具有特定配置文件 (.agentkit/spec 和 .agentkit/overlays/agentkit-forge) 的项目。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add JustAGhosT/agentkit-forge/preflight。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    preflight 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

preflight

安装 preflight,这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence
<!-- GENERATED by AgentKit Forge v3.1.0 — DO NOT EDIT --> <!-- Source: .agentkit/spec + .agentkit/overlays/agentkit-forge --> <!-- Regenerate: pnpm -C .agentkit agentkit:sync -->

preflight

Runs enhanced delivery checks before ship: quality gates, changelog, coverage delta, commit convention conformance, TODO/FIXME hygiene, and documentation updates for externally visible changes.

Usage

Invoke this skill when you need to perform the preflight operation.

Checks (beyond /check)

  1. Quality Gates — Run /check and fail on any error
  2. Changelog Updates — Verify changelog/release notes when user-facing behavior changed (CLI flags, API contracts, UI copy, migration semantics)
  3. Commit Convention — Validate commits in range follow conventional commit format
  4. TODO/FIXME Hygiene — Detect entries without issue references in changed files
  5. Coverage Delta — Fail when coverage regresses vs. baseline. Accept documented waivers with author, rationale, linked issue, and expiry date.
  6. Docs Updates — Confirm docs updated for API/CLI behavior changes

Output

Produce a pass/fail table: Check | Status | Evidence | Required Follow-up. Include range resolution info, baseline and current coverage percentages with delta.

Usage

/preflight [--stack <stack>] [--range <git-range>] [--base <remote-branch>] [--strict]

If --range is omitted, auto-detect via merge-base against the default branch. If detection fails, fall back to HEAD~50..HEAD with a visible warning.

Project Context

  • Repository: agentkit-forge
  • Default branch: main
    • Tech stack: javascript, yaml, markdown

Conventions

  • Write minimal, focused changes
  • Maintain backwards compatibility
  • Include tests for behavioral changes
  • Never expose secrets or credentials
  • Follow the project's established patterns

相关技能

寻找 preflight 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具