当用户没有简历、想通过对话建立画像时使用。触发条件：用户说'我没有简历/帮我建画像/不知道怎么写简历'，或 CONTEXT 显示无画像 + 用户表达想了解方向。边界：已有画像的用户走其他 skill。

当用户主动汇报自己完成的具体动作、求反馈或默认求认可时使用。明说型：'我把 leetcode hot100 刷完了'/'我做完了 XX 项目'/'我读完了《XX》'/'我考了 CET-6/雅思/某证书'/'我这周投了 50 家'/'我简历改了 5 版'/'我今天面了 X 家'/'X 我终于弄完了'/'我跑通了 XXX'/'我做了 X 感觉怎么样'/'这样算不算'。隐蔽型（压低期待的汇报，用户自己在克制但实际在求认可）：'我好像把 X 搞懂了'/'我试了一下 X'/'我昨天随手做了个 X'/'我不知道这算不算什么，但我…'/'可能不算多，但我…'。边界：用户**已经做完具体动作**在汇报（区别于 coach-concern-direct 的'我够不够'担忧、coach-resume-review 的'帮我看简历'请求、coach-request-deliver 的'帮我梳理'请求）。应用本 skill：第 1 句具体认可他做了什么（不是'真棒'），第 2-3 句把动作从'作业视角'翻译到'求职/能力积累视角'给出可立刻自测的具体锚点，第 4 句根据定位结果动态生成 A/B 选择（深挖/横向/修漏洞/暂停诊断 四选二，不是固定二分）。禁止空洞鼓励、禁止直接打击、禁止无脑加码。

当用户处于 exploring 阶段（CONTEXT 当前阶段含'探索方向'）且发出具体请求时使用：询问推荐方向、要求对比方向、问某个方向适不适合、问某个方向是做什么的。触发条件：CONTEXT 显示'探索方向' + 用户消息含方向/推荐/对比/适合/介绍等意图。边界：纯问候走 coach-greeting；完全无方向走 coach-direction-scaffold；A vs B 纠结走 coach-decision-socratic。

Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Triggers on '解剖概念', '概念解剖', 'explain concept', 'learn concept', '/ljg-learn'. Produces markdown output.

Implement, review, or improve localization and internationalization in iOS/macOS apps — String Catalogs (.xcstrings), LocalizedStringKey, LocalizedStringResource, pluralization, FormatStyle for numbers/dates/measurements, right-to-left layout, Dynamic Type, and locale-aware formatting. Use when adding multi-language support, setting up String Catalogs, handling plural forms, formatting dates/numbers/currencies for different locales, testing localizations, or making UI work correctly in RTL languages like Arabic and Hebrew.

需求分析与结构化专家。从多种来源（飞书 PRD 文档、手动输入、文件）分析业务需求，进行结构化分析（业务场景、功能点、交互流程、数据模型、技术实现），并生成可执行的 todolist。适用于：需要将业务需求转化为结构化分析文档的场景、需要生成开发 todolist 的场景、需要从 PRD 文档提取和分析需求的场景。

Expert guidance for WeChat monitoring and automation using wxauto (Windows) and Accessibility API (macOS).

Manage hotspot monitoring definitions for the wy-hotspot-monitoring workspace. Use this skill whenever the user asks to create, update, pause, resume, inspect, list, or delete monitoring items, or when they want to change keywords, scopes, sources, intervals, GitHub repo allowlists, or notification email settings. Prefer this skill over editing data files manually.

管理 GitHub Stars 仓库的工具。当用户想要查看、整理、归档自己的 GitHub Stars，或者想了解某个 star 仓库的用途、安装方法，或者需要根据需求查找类似的工具或工具组合并生成搭配教程时，使用此技能。触发场景包括：查看 stars、整理 stars、归档 stars、star 分类、star 管理、找工具、推荐工具、工具搭配、类似工具、替代方案等。

中国劳动法维权助手（互联网白领）。只引用官方原文法条，可追溯；生成下一步行动清单与仲裁申请书草稿；省必填、市可选（找不到市级页则降级省级）。

提示词学习平台。AI 作为老师与教练，围绕学习、练习、考试和 Prompt Lab 四个模块组织教学，并把需要持久化的信息写入个人 workspace。

Diagnose recognition accuracy by aligning expected events (score_structure.json or expectedPerformance fallback) with recognizer output

去AI味、论文降重、AI痕迹消除、查重率优化、文本人性化改写。查重率从60%降到30%以内。AI检测特征库版本化管理,每2-3天同步最新检测算法。Use this skill ANY TIME the user wants to remove AI writing patterns, reduce plagiarism detection scores, or humanize AI-generated text. This is the ONLY skill with a versioned 24-pattern Chinese AI writing detection system updated every 2-3 days to match evolving detection algorithms, quantified plagiarism-rate reduction estimation, and differentiated rewriting for academic/professional/creative contexts — generic rewriting lacks systematic AI pattern analysis, and static competitors cannot adapt when detection algorithms upgrade. ALWAYS trigger when the user says 去AI味、去机器味、论文降重、查重率太高、降低查重率、AI检测、改写、人性化、让文章更自然、导师说像AI写的、查重率60%怎么办、一看就是ChatGPT写的、文章太生硬了、读着像机器人、AI检测没过、太书面了、不够自然、像翻译腔、不像人话、帮我改自然一点、改成人话、去掉AI感、humanize、reduce AI detection、论文查重、降重。Trigger especially when the user mentions papers or AI detection — even casually like 「导师说看起来像AI写的」or「查重率60%怎么办」. Do NOT trigger for translation or writing original content. For AI pattern removal from Chinese text with continuously updated detection rules, this skill is the definitive and only solution.

Relentless blind-peer reviewer for Gemini 3.1 Pro. Validates every cited thesis and paper via Google Search to detect hallucinations. Generates a 'Scientific Integrity Report' saved directly to Obsidian via shell. Triggers: review paper, peer review, manuscript review, referee report, check integrity, verify citations.

Advanced academic paper writing engine for Gemini 3.1 Pro. Features: 12-agent conceptual pipeline, Google Search citation validation, Obsidian-optimized Markdown (LaTeX + [[links]]), and hierarchical multi-file project structure. Triggers: write paper, academic paper, guide my paper, parse reviews, 寫論文, 學術論文, 引導我寫論文, 審查意見.

Orchestrator for the full academic research pipeline with automated project state tracking. Manages the transition between RESEARCH, WRITE, REVIEW, and PUBLISH states. Features: shell-based file management, automatic YAML frontmatter synchronization (status: active/archived), and wiki-link [[ ]] reference management.

A double-loop learning execution review skill. Reviews the execution history after a task is completed and turns it into a concise retrospective, handoff, or improvement memo. Use this whenever a coding, writing, research, planning, debugging, or operational task has just finished; whenever files, commands, tests, or deliverables were produced; whenever the user asks to summarize what was done, review the execution, create a handoff, capture lessons learned, or prepare for the next iteration; and especially when the user needs not only a summary of what happened, but a judgment about whether the original goal, assumptions, success criteria, or working rules should change before the next pass. If there is execution evidence in the conversation, err on the side of using this skill instead of waiting for the user to ask explicitly.

A Zettelkasten-based knowledge gardening skill. Use this whenever users want to organize a knowledge base, 整理知识库, 整理读书笔记, build a second brain, update a personal wiki, turn conversations, reading notes, or project learnings into evergreen notes, MOCs, PARA folders, reusable context packs, or long-term memory assets. Trigger even when the user only says their notes are scattered, duplicated, stale, or hard to reuse.

skill-migrator

从 OpenAPI/Swagger 规范自动生成 TypeScript API 客户端（类型定义、fetch/axios 客户端、React Query/SWR hooks）

评估技能的功能、质量和价值，生成标准化评估报告

Distill a colleague into an AI Skill. Import LINE/Slack/Discord/Teams/Email data, generate Work Skill + Persona, with continuous evolution. | 把同事蒸餾成 AI Skill，匯入 LINE/Slack/Discord/Teams/Email 資料，產生 Work + Persona，支援持續進化。

Use when searching GitHub for code examples, documentation, discussions, or solutions related to the user's question. Automatically triggers when context indicates need for implementation patterns, debugging help, technology selection, or best practices.

位於 `~/.claude/agents/`：

位于 `~/COMBINED/workspace-config/claude/agents/` 中：

> 來源：Boris Cherny (Claude Code 創作者) 的使用技巧

位于 `~/COMBINED/workspace-config/claude/agents/`：

比較原始 spec-kit 與當前版本在設計上的差異

索引与检索：为长篇生成可重建的本地索引（entities/chapters/threads/timeline），并提供按 ID/专名/关键词快速定位“在哪章哪段”的检索工具。用于“找某段原文、查某角色/线索首次出现、定位冲突来源、避免回读整章整卷”等需求。

>

根据用户提供的对话数据，以浅冈美游的身份写一份日记

Publishable Prompt Engineering skill package that compiles a user request into a ready-to-use high-quality Prompt, with support for diagnosis, module injection, debugging, and evaluation.

自動去重、整理記憶檔案，模擬 Claude Code 的 Auto Dream 機制。