项目提供了34个现成的AI编码agent技能，覆盖规划、测试、审查等完整流程，可以直接复用。
34 composable capabilities available today
独立开发者
Developers using Claude Code
目标用户 · 非用户评价Target user · not a testimonial
SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL
thiientv/godmode
34 个生产级 Agent Skills，零专有运行时，为 AI 编码代理提供可组合工作流34 production-grade Agent Skills with zero proprietary runtime — composable workflows for AI coding agents
给AI编码代理用的生产级技能包，可组合工作流覆盖开发全流程。A collection of 34 reusable, composable coding helpers for AI assistants like Claude Code, with no proprietary runtime.
怎么装：Install: git clone https://github.com/thiientv/godmode.git
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
历史不足Not enough history
只有 1 个快照，还不足以计算增长Only 1 snapshots so far — not enough to compute growth
讨论DISCUSSION
暂无None
还没有采集到外部讨论No external discussion collected yet
状态STATUS
持续活跃Active
质量 AQuality A
项目提供了34个现成的AI编码agent技能，覆盖规划、测试、审查等完整流程，可以直接复用。34 composable capabilities available today
03 / 它能帮你做什么03 / What it helps you do
设计可重复的评估方案
审查代码架构与接口
自动化测试与验证
处理生产事故与发布
简化代码并优化性能
Plan and implement features with test-driven development
Review code for correctness, regressions, and security
Debug and fix issues with structured investigation
Design interfaces, data models, and UI components
Validate browser behavior with automated checks
04 / 谁在用04 / WHO IT’S FOR
项目提供了34个现成的AI编码agent技能，覆盖规划、测试、审查等完整流程，可以直接复用。
34 composable capabilities available today
独立开发者
Developers using Claude Code
目标用户 · 非用户评价Target user · not a testimonial
基于MIT开源许可证，可以自由修改和集成到自己的工具链中。
No proprietary runtime or API key needed
前端开发者
Teams standardizing AI-assisted development
目标用户 · 非用户评价Target user · not a testimonial
支持Claude Code和Codex等主流AI编码工具，无需额外付费服务。
Works with Claude Code and other Agent Skills-compatible clients
技术创业者
Engineers who want reproducible coding workflows
目标用户 · 非用户评价Target user · not a testimonial
项目提供了34个现成的AI编码agent技能，覆盖规划、测试、审查等完整流程，可以直接复用。
34 composable capabilities available today
自动化爱好者
Anyone building production software with AI help
目标用户 · 非用户评价Target user · not a testimonial
不适合谁Not for同样来自文档，不是我们的判断Also from the docs, not our judgement
05 / 安装05 / Install
$ README 里给出的安装方式。The installation method given in the README.
两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
通过 git clone https://github.com/thiientv/godmode.git 克隆仓库到本地。Clone the repository and copy the skills into your project's .agents/skills directory.
06 / 限制与风险06 / Limits and risk
风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01控制浏览器Controls a browserskills/browser-testing/SKILL.md
Use [browser-checklist.md](references/browser-checklist.md) for Playwright,
静态扫描命中一项中风险：文档提到用 Playwright 控制浏览器（见 references/browser-checklist.md）。这意味着相关技能会驱动真实浏览器操作网页，使用时请留意它访问的站点和输入的内容。A static scan flagged a medium-risk item: one skill can control a browser via Playwright. Review the skill before using it in sensitive environments.
这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 2,
"ai-tools": 4,
"dev-tools": 7,
"indie-web": 0,
"skill-agent": 12,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "claude-skill"
},
"localRuntime": "install: git-clone",
"skillMdTotal": 34,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 13,
"browser": 0,
"devtool": 7,
"security": 1,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "34 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 71 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/agent-evaluation/SKILL.md",
"skills/api-and-interface-design/SKILL.md",
"skills/architecture-review/SKILL.md",
"skills/behavior-validation/SKILL.md",
"skills/branch-integration/SKILL.md",
"skills/browser-testing/SKILL.md",
"skills/code-simplification/SKILL.md",
"skills/codebase-orientation/SKILL.md",
"skills/completion-verification/SKILL.md",
"skills/database-design/SKILL.md",
"skills/dispatching-parallel-agents/SKILL.md",
"skills/documentation-and-adrs/SKILL.md",
"skills/frontend-design/SKILL.md",
"skills/implementation-planning/SKILL.md",
"skills/incident-response/SKILL.md",
"skills/observability-and-instrumentation/SKILL.md",
"skills/performance-optimization/SKILL.md",
"skills/plan-execution/SKILL.md",
"skills/pr-code-reviewer/SKILL.md",
"skills/receiving-code-review/SKILL.md",
"skills/release-engineering/SKILL.md",
"skills/requesting-code-review/SKILL.md",
"skills/root-cause-debugging/SKILL.md",
"skills/safe-migrations/SKILL.md",
"skills/security-and-hardening/SKILL.md",
"skills/solution-design/SKILL.md",
"skills/subagent-driven-development/SKILL.md",
"skills/technical-research/SKILL.md",
"skills/test-driven-development/SKILL.md",
"skills/test-strategy/SKILL.md",
"skills/ui-ux-review/SKILL.md",
"skills/using-git-worktrees/SKILL.md",
"skills/using-godmode/SKILL.md",
"skills/writing-skills/SKILL.md"
],
"skillMdFetched": 34
}