haaaiawd
- 32 skills
- 0 followers
- 1 day ago last updated
- ▌ Anws System 2 · haaaiawdUse when users in a skills-only environment need to decide which anws workflow to start from, or need routing among forge / change / genesis / probe / blueprint / challenge / upgrade. It is the navigation entry for the anws workflow set.
- ▌ Disk Space Audit · haaaiawd bundleScan and analyze disk space usage on Windows and macOS (with Linux references), then produce a categorized cleanup report — and, only when the user explicitly asks, execute cleanup with per-item confirmation. Use this skill whenever the user asks to "scan C drive", "analyze disk space", "find what's eating my storage", "clean up system drive", "磁盘空间分析", "清理 C 盘", "扫描磁盘占用", "找重复文件", "find duplicates", or wants a breakdown of where disk space went. Also trigger when user mentions disk full, low space warnings, or wants to know what can be safely deleted. The audit phase is always read-only. The cleanup phase requires explicit, per-item user confirmation and never proceeds on ambiguous intent.
- ▌ Prompt Quality Inspector · haaaiawdIndustrial prompt review and optimization. Use when: you want a credible, explainable score (0–100) for a prompt/spec, then guided clarification and a rewritten, execution-ready integrated prompt (product + tech stack + data + security + operations). Keywords: prompt review, prompt quality, scoring rubric, spec prompt, PRD-to-implementation, requirements, architecture, offline/on-prem, security, observability.
- ▌ Skillhome · haaaiawdManage a unified skill repository across multiple AI agent applications (Windows, Linux, macOS). Use when the user asks to share, sync, map, or migrate skills between agents (Codex, Devin, Claude Code, Windsurf, Cursor, Gemini, Open Cloud, Hermes, etc.), unify skill storage, fix broken skill junctions, or says "skillhome", "统一管理 skill", "skill 映射", "skill 同步", "共享 skill", "在 Devin 里用 Codex 的 skill", or similar cross-agent skill requests. To install a skill, use "skillhome add <source> -g": local zip/directory is installed directly into the central repo (no npx needed, handles non-UTF-8 SKILL.md); remote sources (owner/repo, URL) wrap `npx skills add`. Auto-syncs and global-shares to all agents. To install SkillHome itself, run "npx skills add Haaaiawd/skillhome -g" or download from https://github.com/Haaaiawd/skillhome/releases.
- ▌ Second Nature Setup · haaaiawd bundleSecond Nature 初始化清单：workspace 根与 agent 对齐、anchor files、加密密钥 env、平台凭据写入 state 库、policy、首轮 heartbeat_check；Quiet/memory 路径；宿主侧每轮补充 heartbeat_check（HEARTBEAT.md）。稳定后把原则沉入 SOUL/MEMORY。
- ▌
- ▌ Terminal Logo UI · haaaiawd bundle当用户需要为 CLI / Terminal 设计或实现 logo、banner、header、welcome screen 时使用。适用于需要处理风格方向、宽度适配、fallback 和信息区的场景。
- ▌ Terminal Selection UI · haaaiawd bundle当用户需要为人类直接使用的 CLI / Terminal 设计或实现 single-select、multi-select、checkbox 或 choice list 时使用。适用于 human-in-the-loop 的终端交互层，以及需要处理状态模型、键位映射、TTY 降级和布局约束的场景。
- ▌ Git Forensics · haaaiawd bundle分析 Git 历史，发现"逻辑耦合"（总一起改的文件）和"热点"（高频修改的复杂模块）。基于 Adam Tornhill 的《Your Code as a Crime Scene》方法论。
- ▌
- ▌ Complexity Guard · haaaiawd bundleThe final gatekeeper. Audits RFCs to reject over-engineering, unnecessary dependencies, and resume-driven development.
- ▌
- ▌ Anws System · haaaiawd当用户在 skills-only 环境中需要判断应该从哪个 anws 工作流开始，或需要在 forge / change / genesis / probe / blueprint / challenge / upgrade 之间路由时使用。它是 anws 工作流集合的导航入口。
- ▌ Exam Author · haaaiawd bundleTerminal Bench 2.0 / General Coding 出题任务的提交流程规范。覆盖 ZIP 结构、 Dockerfile + solve.sh + test.sh 编写、依赖匹配校验、风险命令扫描、提交前 checklist 和本地 docker 验证闭环。当用户提到"出题"、"terminal bench"、 "general coding"、"Env Zero"、"exam_001"、"solve.sh"、"提交 zip"、"reward=1"、 "harbor 框架"、"oracle 测试"、"难题种子卡"、"problem_seed"、"难度自测"、 "加压"、"治标解法"、"多 bug 合并"、"SSRF"、"guard 时机"、"红鲱鱼"、 "混淆式包装"、"校验结果吞掉"、"console.warn 不 throw"、"混淆等级"、 "L3 混淆"、"显性 bug 隐藏真 bug"、 或在 exam 类目录下要编写/验证/打包提交物时，立即使用本 skill。它是出题 流水线的交付端，消费发现端产出的难题种子卡构造四件套并验证难度。即使用户 只是说"帮我看看这个题能不能提交"、"走一遍流程"、"打包一下"、"把这张种子卡 做成题"，只要上下文是 terminal bench 出题，也应触发。
- ▌ Seed Harvester · haaaiawd在真实项目中把一个刚解决（或难以解决）的工程问题，萃取并包装成一个 最小复现包的"难题种子卡"。这个 skill 是给**真实项目里遇到问题的 AI agent**用的。当你刚啃完一个棘手 bug、部署故障、依赖冲突、配置错误、 AI review 指出的难题，或用户说"把这个坑沉淀成题"、"汇总这个错误"、 "提炼一下这个问题"、"把刚才那个问题整理出来给出题用"、"记录前因后果" 时，立即使用本 skill。产出 problem_seed.md 或 problem_seed.json （难题种子卡），作为出题流水线的交接物。
- ▌ Nexus Query · haaaiawd bundlePrecise, instant code structure queries for active development — answer 'who depends on this interface before I refactor it', 'how many modules break if I change this', 'what is the real impact radius of this feature change', 'which module is the true high-coupling hotspot in this legacy codebase'. Essential before any interface change, continuous refactoring task, sprint work estimation, or when navigating unfamiliar or large legacy codebases. Requires Python 3.10+ and shell. Use nexus-mapper instead when building a full .nexus-map/ knowledge base.
- ▌ Spec Writer · haaaiawd bundlegenesis Step 2：将模糊或高层需求转化为严格的产品需求文档（PRD）；含 craft 脚手架、PRD spec 契约、可选子代理分片编排与 Step 完成信号。适用于需求含糊、范围过大或表达停留在概念层的场景。
- ▌ Nexus Mapper · haaaiawd bundleGenerate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling reliable cold-start AI sessions across a team. Produces INDEX.md, systems.md, concept_model.json, git_forensics.md and more. Requires shell execution and Python 3.10+. For ad-hoc file queries or instant impact analysis during active development, use nexus-query instead.
- ▌ Task Planner · haaaiawd bundle使用 WBS 将系统设计文档分解为执行主清单（05A_TASKS.md）与验证计划（05B_VERIFICATION_PLAN.md），支持依赖分析、验证追溯与证据定义。
- ▌ Code Reviewer · haaaiawd纯静态「契约忠实度 / 实现侧证据」审查：对照 PRD、ADR、系统设计、05A_TASKS 与 05B_VERIFICATION_PLAN，围绕契约闭合、任务兑现、架构健康、安全边界、验证证据与回流一致性产出可追溯结论；供 /challenge（CODE/FULL）与 /forge（Step 3 §3.6 波末）共用。
- ▌ Task Reviewer · haaaiawd系统性审查 05A_TASKS.md 与 05B_VERIFICATION_PLAN.md，作为 `/challenge` 工作流的任务契约与验证契约证据层；7 Pass（A→G）、四语义模型、发现上限与跨文档门禁不变，落盘叙述遵循 output-contract 与本 SKILL 专属门禁。
- ▌ Tech Evaluator · haaaiawd bundle服务于 `/genesis` Step 3「技术选型」：以 ATAM 与 12 维加权矩阵评估候选栈，产出可追溯的对比结论与 ADR 升格素材；不写正式 ADR 文件（落盘在 Step 5）。优先读本 SKILL 旁 `references/`。
- ▌ Concept Modeler · haaaiawd当用户需求模糊、术语不清晰时使用。通过交互式追问澄清领域概念，提取实体、流程与暗物质（missing_components）。由 **`/genesis` Step 1** 在 Step 0 已确定 `TARGET_DIR = .anws/v{N}` 后调用；与 **同工作区 `/genesis`** 连用。
- ▌
- ▌ Design Reviewer · haaaiawd当 `/challenge` 需要设计侧规范契约闭合证据（架构与系统设计文档三维审查）时加载；产出可锚点、按严重度分级的发现供纳入 07_CHALLENGE_REPORT，不作脱离 challenge 上下文的终局裁决。
- ▌ Output Contract · haaaiawd当在本模板 bundle 内需持久化报告、并行子会话、或与多工作流产出对齐时使用。收录共用落盘 spec 与委派闭环；与 craft-authoring（/craft 撰写脚手架）无关。
- ▌ System Designer · haaaiawd bundle当 `/design-system <system-id>` 需要为单个系统生成 L0/L1 详细设计文档时加载。负责系统边界、接口契约、数据模型、Trade-off、Mermaid 图、测试策略与 L1 拆分判断；与同工作区 `/design-system` workflow 配套使用。
- ▌
- ▌ E2e Testing Guide · haaaiawd规定面向真人的 E2E / 手动验证《测试指南》与《E2E Verification》报告骨架（PRD 可追溯、人机走查顺序、评测列仅能 PASS/PARTIAL_PASS/FAIL）；**不含实机浏览器编排**——先后顺序与回填义务由宿主 **`/forge` §3.7**（及 `/forge` 对应条文）统一写死。
- ▌ Runtime Inspector · haaaiawd当 `/probe` 需要识别运行时入口、进程边界、spawn 链、IPC 通道、协议强度与生命周期风险时加载。只做静态/可观察探测，不修改代码。
- ▌ Testing Night Journal · haaaiawdTest Night-Journal's core features end-to-end including AI model settings, image upload, and entry creation. Use when verifying changes to settings, model config, or entry/image flows.
- ▌