By GXFrighting
AI-powered development tools for code review, research, design, and workflow automation.
Conditional document-review persona, selected when the document has >5 requirements or implementation units, makes significant architectural decisions, covers high-stakes domains, or proposes new abstractions. Challenges premises, surfaces unstated assumptions, and stress-tests decisions rather than evaluating document quality.
Conditional code-review persona, selected when the diff is large (>=50 changed lines) or touches high-risk domains like auth, payments, data mutations, or external APIs. Actively constructs failure scenarios to break the implementation rather than checking against known patterns.
Reviews code to ensure agent-native parity -- any action a user can take, an agent can also take. Use after adding UI features, agent tools, or system prompts.
Creates or updates README files following Ankane-style template for Ruby gems. Use when writing gem documentation with imperative voice, concise prose, and standard section ordering.
Conditional code-review persona, selected when the diff touches API routes, request/response types, serialization, versioning, or exported type signatures. Reviews code for breaking contract changes.
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
Run comprehensive agent-native architecture review with scored principles
Sync GaleHarnessCLI skills with latest changes from the reference upstream repo. Use when you need to pull upstream updates, review what changed, apply gh: renames, and re-inject HKTMemory patches. Triggers: 'sync upstream', 'update skills', 'pull latest changes', 'upstream diff'.
This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals, Basecamp, HEY, or Campfire style. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and the "clarity over cleverness" philosophy.
Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
巨风科技研发团队提效工具 —— 基于 Compound Engineering 工作流与 HKTMemory 向量知识库的 AI 驱动开发套件。
普通用户优先安装 Release 二进制,不需要 clone 仓库:
curl -fsSL https://raw.githubusercontent.com/wangrenzhu-ola/GaleHarnessCodingCLI/main/scripts/install-release.sh | bash
gale-harness --version
Windows release binary installer 尚未进入 P0a 范围。当前不要把 source-mode 的 scripts/setup.ps1 当作普通用户默认一键安装;需要在 Windows 上试用或参与开发时,请参考下方“安装方式”里的贡献者源码安装路径。Windows release 安装器会在后续阶段补齐。
每一次工程实践都应该让后续工作变得更简单,而不是更复杂。
传统开发累积技术债务,每个功能增加复杂度。HarnessCLI 反转这一模式:
Brainstorm -> Plan -> Work -> Review -> Compound -> Repeat
^
Ideate (可选 -- 用于发现改进点)
每个阶段都与 HKTMemory 向量知识库双向交互:阶段开始前检索相关记忆,阶段完成后存储新产生的知识。
| 命令 | 用途 | HKTMemory 交互 |
|---|---|---|
/gh:ideate | 通过发散思维和对抗性过滤发现高影响力改进点 | 检索历史建议,存储新发现 |
/gh:brainstorm | 在规划前探索需求和方案,通过交互式问答细化想法 | 检索相关需求,存储需求文档 |
/gh:plan | 将功能想法转化为详细实施计划,带自动置信度检查 | 检索相似方案,存储技术规划 |
/gh:work | 系统化执行工作项,使用 worktree 和任务追踪 | 检索实现模式,存储实现总结 |
/gh:work-x | iOS Morph-X 实施模式:在保留工作流能力的同时降低模板化代码重复风险 | 检索历史模式标签,存储蓝图/策略指纹 |
/gh:review | 多代理代码审查,分层角色和置信度门控 | 检索审查模式,存储审查发现 |
/gh:compound | 记录已解决问题,沉淀团队知识 | 检索相关解决方案,存储完整知识 |
/gh:debug | 系统性查找根本原因并修复缺陷 | 检索类似问题,存储调试经验 |
/gh:debug-x | iOS Morph-X 调试模式:保持根因定位纪律,并在修复产出后执行变换和相似度审计 | 检索历史模式标签,存储蓝图/策略指纹 |
/gh:optimize | 迭代优化循环,并行实验和 LLM 评分 | 检索优化策略,存储优化结果 |
/document-review | 多角色并行评审需求/方案文档 | 无 |
/gh:sessions | 搜索历史 Claude Code/Codex/Cursor 会话 | 无 |
/gh:slack-research | 搜索 Slack 获取组织上下文 | 无 |
入口说明:
/gh:brainstorm是主要入口 —— 它通过交互式问答将想法细化为需求文档,在不需要时自动跳过。/gh:ideate效果显著但使用较少 —— 基于代码库主动发现改进建议。
核心 gh: 流程内置 Karpathy-inspired guardrails,不需要额外调用独立 skill。/gh:brainstorm 先挑战问题 framing 并拆分假设、非目标和成功标准;/gh:plan 要求复杂度能追溯到需求、风险或约束;/gh:work 把非平凡执行绑定到最小 execution contract 和 surgical diff;/gh:review 用意图摘要检查 diff hygiene,避免计划边界漂移和顺手重构。
背景记录见 docs/solutions/workflow-issues/karpathy-guidelines-workflow-guardrails-2026-04-24.md。
/gh:work-x 和 /gh:debug-x 是面向 iOS Swift/ObjC 代码产出的特殊工作流。它们先根据项目 seed、历史模式标签和 .morph-config.yaml 选择实现蓝图,再在代码产出后运行 gale-harness morph --apply 与 gale-harness audit --similarity,输出相似度风险报告。
Morph-X 的定位是降低模板化代码重复风险并提供自检证据,不保证 Apple App Review 通过,也不能替代真实的产品、UI、内容和功能差异。
以研发导师的视角,指导工程师在不同开发场景下如何高效使用。
需求理解 -> 技术规划 -> 编码实现 -> 代码审查 -> 知识沉淀
| 步骤 | 命令 | 产出 |
|---|---|---|
| 需求探索 | /gh:brainstorm "实现用户登录功能" | 检索历史案例,输出结构化需求文档到 docs/brainstorms/ |
| 技术规划 | /gh:plan docs/brainstorms/user-login-requirements.md | 检索相似方案,输出任务分解和置信度评估到 docs/plans/ |
| 编码实现 | /gh:work docs/plans/user-login-plan.md | 创建 git worktree,检索实现模式,存储实现总结 |
| 代码审查 | /gh:review | 多代理并行审查(安全/性能/正确性/可维护性) |
| 知识沉淀 | /gh:compound "用户登录功能的实现经验" | 记录解决方案供未来参考 |
# 推荐:使用完整工作流
/gh:debug
# 支持多种输入方式
/gh:debug "用户登录时偶尔出现 500 错误"
/gh:debug
> Error: Connection timeout at UserService.authenticate()
> Stack trace: ...
/gh:debug https://github.com/org/repo/issues/123
/gh:debug 会自动检索 HKTMemory 中类似历史问题,系统性定位根因,修复后自动存储调试经验。
# 需求文档评审
/document-review docs/brainstorms/new-feature.md
# 技术方案评审
/document-review docs/plans/implementation-plan.md
多角色代理并行评审:产品视角(挑战假设/战略影响)、安全视角(数据暴露/认证漏洞)、可行性视角(技术可行性/架构冲突)、范围视角(复杂度/过度设计)。
# 归档已解决的问题
/gh:compound "解决大文件上传超时问题"
# 以上命令都会自动检索 HKTMemory
/gh:brainstorm "..."
/gh:plan "..."
/gh:debug "..."
/gh:optimize "优化首页加载速度"
定义可测量目标,构建测量脚手架,并行运行多个实验方案,用 LLM 评分评估效果,自动保留改进方案。
# 查询历史会话
/gh:sessions "上次我们是怎么处理认证问题的?"
/# 搜索 Slack 讨论
/gh:slack-research "团队对微服务拆分的讨论"
一个工程师同时驱动 10+ 条需求流水线。每条流水线在独立 worktree 中运行,共享代码库和知识库,互不阻塞、互不干扰。
flowchart TB
Lead["🎯 技术负责人\n1 人"]
Lead --> W1["Worktree 1\nbrainstorm/user-auth\n需求探索中"]
Lead --> W2["Worktree 2\nfeat/payment\n编码实现中"]
Lead --> W3["Worktree 3\nfix/email-bug\n审查中"]
Lead --> W4["Worktree 4\nfeat/search\n规划中"]
Lead --> W5["Worktree 5\nbrainstorm/analytics\n需求探索中"]
Lead --> Wn["Worktree N\n...\n并行推进"]
W1 --> HKT["🧠 HKTMemory\n共享知识库"]
W2 --> HKT
W3 --> HKT
W4 --> HKT
W5 --> HKT
Wn --> HKT
npx claudepluginhub gxfrighting/galeharnesscodingcli --plugin galeharness-cliPersonalized coding tutorials that use your actual codebase for examples with spaced repetition quizzes
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.