Analyze a CLAUDE.md file and generate PreToolUse hook scripts that enforce its rules at the tool-call level. Use when users want their CLAUDE.md directives enforced as code rather than relying on prompt compliance. Reads the CLAUDE.md, identifies enforceable rules, generates standalone bash hook scripts, and wires them into .claude/settings.json.
Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context. The bundled Python scripts make no network calls and have zero third-party dependencies. Workflow delegations via the host platform's sessions_send may invoke external model APIs.
Real-time AI agent security scanner. Detects prompt injection, jailbreak attempts, credential/secret leaks, PII exposure, and dangerous tool calls. Activate when: (1) scanning inbound messages or tool outputs for prompt injection, (2) checking outbound content for credential leaks or PII, (3) auditing agent session logs for security events, (4) evaluating tool call safety before execution, (5) user asks about security scanning or threat detection. Covers OWASP Top 10 Agentic AI risks. --- # ClawMoat — Security Moat for AI Agents ## Scripts All scripts are in `scripts/`. They wrap the `clawmoat` CLI and log results to `clawmoat-scan.log`. ### Scan Text Scan any text for threats (prompt injection, secrets, PII, exfiltration): ```bash scripts/scan.sh "text to scan" ``` Returns JSON with findings. Logs to `clawmoat-scan.log`. Exits non-zero on CRITICAL/HIGH findings. ### Scan File ```bash scripts/scan.sh --file /path/to/file.txt ``` ### Audit Session
AI 虚拟试穿 Agent。用户提供服装信息（图片或文字描述均可）， Agent 全程引导完成：服装图预处理 → AI 生成模特 → 虚拟试穿合成 → 生成展示视频。 支持阿里云百炼试衣 API、豆包 Seedream 生图、豆包 Seedance 生视频。 当用户提到"试穿"、"试衣"、"穿上效果"、"模特上身"、"虚拟试衣"、 "看看穿上什么样"、"帮我生成穿衣效果"、"virtual try-on"、"上身图"、 "换装"、"我想看穿上的效果"时，必须立即触发此 Agent。 --- # AI 虚拟试穿 Agent ## 职责 引导用户完成虚拟试穿全流程，输出试穿效果图和展示视频。 不涉及上架、文案、定价。有上架需求告知使用 shopify-quick-listing。 --- ## 配置说明（告知用户时必须按此说明） **.env 文件的唯一标准位置是 `scripts/` 目录：** ``` ~/.claude/skills/ai-tryon/scripts/.env ← 正确位置 ~/.claude/skills/ai-tryon/.env ← 错误，不要放这里 ``` 告知用户配置的标准话术： > 请在 Skill 的 scripts 目录下创建 .env 文件： > ```bash > cp ~/.claude/skills/ai-tryon/scripts/.env.example \ > ~/.claude/skills/ai-tryon/scripts/.env > # 然后编辑填入 Key > ``` 不要让用户在 `ai-tryon/` 根目录或其他位置创建 .env。 --- ## 输出目录约束（最高优先级规则） **所有脚本调用都必须传 `--output-dir`，绝对禁止省略。** 输出目录的唯一真实来源是 `.env` 中的 `TRYON_OUTPUT_DIR` 环境变量： ```bash # .env 示例 TRYON_OUTPUT_DIR=/Users/xxx/Desktop/tryon_output ``` ### 对话开始时锁定 Session（必须在首次调用任何脚本前执行） **每次对话开始时，立即运行以下命令锁定本次任务目录，整个对话全程复用此 `OUTPUT_DIR`：** ```bash # 一行命令：获取（或创建）当前 session 目录，同时确保目录存在 OUTPUT_DIR=$(python scripts/output_manager.py --get-session) echo "本次任务目录：$OUTPUT_DIR" ``` - **24 小时内**再次运行同一命令，返回同一个 `task_YYYYMMDD_HHMMSS` 目录（文件不会覆盖） - 用户明确说「开始新任务」/「重新来」时，改用： ```bash OUTPUT_DIR=$(python scripts/output_manager.py --new-session) echo "新任务目录：$OUTPUT_DIR" ``` 然后每次调用脚本**必须传入同一个 `$OUTPUT_DIR`**： ```bash python scripts/image_gen_tryon.py --desc "..." --output-dir "$OUTPUT_DIR" python scripts/tryon_runner.py --garment g.jpg --output-dir "$OUTPUT_DIR" python scripts/video_gen.py --image img.jpg --output "$OUTPUT_DIR" ``` ### 为什么必须这样做 - 不传 `--output-dir` 时脚本会 fallback 到 `TRYON_OUTPUT_DIR` 环境变量或当前终端 pwd 下的 `tryon_output/` - **但 Agent 子进程的 pwd 不可控**，可能导致文件散落到意外位置 - 多轮对话后 Agent 容易遗忘，显式传参是唯一可靠保证 ### 输出文件名控制（可选） `image_gen_tryon.py` 支持 `--output-filename`，生成后会将第一个结果复制为指定文件名： ```bash python scripts/image_gen_tryon.py --desc "..." --output-dir "$OUTPUT_DIR" \ --output-filename model_ruyan_custom.jpg ``` ### 目录结构 每次对话/试穿任务自动创建独立的 session 子目录（以日期
上海交通大学全能校园助手。覆盖 Canvas 作业管理、课程评价、校园匹配、校园生活、学术工具等 21 项功能。 触发场景: (1) 查看/追踪作业DDL、提交状态、成绩 (2) 下载课件、AI总结、作业辅导 (3) 同步DDL到Apple日历 (4) 查询课程评价、对比老师评分 (5) 查看交大邮箱未读、搜索、发邮件 (6) 食堂推荐、查菜单 (7) 查教学周、校历、校园巴士时刻 (8) 查图书馆、空教室 (9) 查正版软件、镜像换源 (10) 交大新闻、教务通知 (11) 搜索往年课程资源（传承交大） (12) 查生存手册 (13) 生成交大PPT (15) SJTU Date 匹配助手：一句话填问卷、查看匹配结果、自动破冰邮件、心动管理 (14) 提交作业、助教批改 (15) 搜索/浏览水源社区帖子 触发词: Canvas, 课程, 作业, DDL, 截止, 成绩, 课件, PPT, 总结, 复习, 提交作业, 讨论区, 批改, 食堂, 吃什么, 图书馆, 教室, 空教室, 巴士, 校车, 教学周, 第几周, 校历, 放假, 邮箱, 邮件, 选课, 评价, 老师怎么样, 软件, MATLAB, Office, 镜像, pip, conda, 换源, 新闻, 教务, 通知, 传承, 往年, 试卷, 生存手册, 保研, 转专业, GPA, PPT模板, 手写, 水源, 水源社区, 论坛, 帖子, sjtudate, 配对, 匹配, 心动, date, 问卷, 填问卷, 脱单, 找对象, 找男朋友, 找女朋友, 破冰 --- # 上海交通大学全能校园助手 ## 配置 - 配置文件: `config.json`（从 `config.example.json` 复制并填入凭证） - Canvas URL: `https://oc.sjtu.edu.cn` - 当前用户的课程列表通过 Canvas API 自动获取 - 所有脚本位于 `scripts/` 目录，用 `python3` 执行 - PPT 模板位于 `templates/` --- ## 🔴 刚需功能（每周都用） ### 1. DDL 追踪 **触发**: "我有什么作业"、"DDL"、"截止"、"未交作业" ```bash python3 scripts/canvas_api.py ddls # 未交作业 + 倒计时 python3 scripts/canvas_api.py ddls-all # 学期全景报告 ``` ### 2. DDL → Apple 日历 **触发**: "同步日历"、"导出DDL"、"导入日历" ```bash python3 scripts/sjtu_timetable_ics.py ddls ~/Desktop/ddls.ics python3 scripts/calendar_sync.py # macOS 直接同步 ``` ### 3. 教学周 / 校历 **触发**: "今天第几周"、"教学周"、"校历"、"什么时候放假" ```bash python3 scripts/sjtu_info.py week # 当前第几周 python3 scripts/sjtu_info.py calendar # 完整学期校历 ``` ### 4. 教务通知 **触发**: "教务通知"、"教务处"、"选课通知"、"考试安排" ```bash python3 scripts/sjtu_news.py jwc 10 ``` --- ## 🟠 高频功能（每月多次） ### 5. 课程评价 **触发**: "课程评价"、"老师怎么样"、"选课参考"、"评分" > ⚠️ course.sjtu.plus 有 CDN 反爬机制，推荐通过 OpenClaw 浏览器代理模式使用（AI 自动处理认证）。 ```bash python3 scripts/sjtu_course_review.py search 传热学 python3 scripts/sjtu_course_review.py compare 燃烧学 python3 scripts/sjtu_course_review.py detail <course_id> ``` ### 6. 交大邮箱 **触发**: "邮箱"、"邮件"、"未读"、"发邮件" ```bash python3 scripts/sjtu_mail.py unread --limit 10 python3 scripts/sjtu_mail.py search -k "作业" python3 scripts/sjtu_mail.py summary python3 sc
Web crawling scripts for fetching pages, JS-rendered pages, links, tables, robots policy, and multi-page crawling. Use these scripts directly; provide URL, timeout, and optional output/filter params.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
