Local Python-based browser automation toolkit using Playwright. Provides command-line tools for navigating, interacting with, and testing web applications without using MCP protocols. Supports clicking, typing, hovering, screenshots, content extraction, and JavaScript execution.
Use the solveit_client CLI (`sic`) to interact with SolveIt dialogs, messages, and the API client from the command line or scripts. Trigger when working with SolveIt automation, dialog management, or message manipulation outside of Python.
禅道开发工作流助手 v1.6.0 - 自动化禅道需求/任务/Bug 下载与技术实现方案设计。 【v1.6.0 核心更新】 - 新增子任务检测与关联内容下载逻辑 - 解决子任务（如 task 61563）描述为空的问题 - 自动下载关联需求和父任务，确保获取完整需求描述 【v1.5.0 核心更新】 - 集成 superpowers:brainstorming 技能，技术方案设计效率提升 70%+ - 合并架构方案和编码方案为"技术实现方案"，消除重复探索 - 代理数量减少 85%（12-17个 → 1-2个），简单需求 5-8 分钟完成 - 聚焦三项核心内容：需求分析、架构设计、实现步骤 【触发条件】当用户提到以下任一内容时，必须使用此技能： - 禅道、zentao、chandao、禅道系统 - 需求、开发需求、story、需求ID - 任务、task、任务ID - Bug、缺陷、bug ID - 下载禅道、获取需求、同步禅道 - 开发某需求/任务、开始开发 - 禅道URL链接（包含 story-view、task-view、bug-view） - ID与类型组合： - "需求39382"、"任务12345"、"Bug67890"（类型+ID） - "39382需求"、"12345任务"、"67890Bug"（ID+类型） - "禅道需求39382"、"开发任务12345"（前缀+类型+ID） - 任何涉及禅道项目管理系统的请求 【技能功能】 1. 自动检测 Java/Python 环境和 superpowers 技能依赖 2. 内置下载工具，无需额外安装 3. 交互式配置禅道服务器信息 4. 下载需求/任务/Bug 详情及附件到本地 5. 使用 brainstorming 技能生成技术实现方案 6. 子任务自动检测与关联内容下载（v1.6.0 新增） 【依赖】需要 superpowers 插件 5.0.6+ 即使只提到"需求"或"任务"关键词，只要上下文暗示与项目管理相关，也应触发此技能。 --- # 禅道开发工作流助手 ## 内置工具 本技能内置两个版本的禅道下载工具，自动选择最佳运行时： | 工具 | 位置 | 运行时 | |------|------|--------| | Java 版 | `{SKILL_DIR}/scripts/chandao-fetch.jar` | Java 8+ | | Python 版 | `{SKILL_DIR}/scripts/chandao_fetch.py` | Python 3.6+ | ## 执行步骤 ### Step 1: 环境检测与运行时选择 **1.1 检测 superpowers 技能（v1.5.0 新增）** **重要**：v1.5.0 版本依赖 superpowers 插件，必须先检测。 使用 Bash 工具检测： ```bash # 检测 superpowers 插件 ls ~/.claude/plugins/cache/claude-plugins-official/superpowers/ 2>/dev/null | head -1 ``` **检测结果处理**： | 检测结果 | 处理方式 | |----------|----------| | 检测到 5.0.6+ 版本 | 继续执行 | | 检测到旧版本 | 提示用户更新 | | 未检测到 | 询问用户是否安装 | **如果未安装**，使用 AskUserQuestion 询问： ```
Writes and runs Python code in a sandbox. Describe the task in plain English — the skill will write and execute the program.
Evaluate Python test suite quality using mutmut to introduce code mutations and verify tests catch them. Use for mutation testing, test quality assessment, mutant detection, and test effectiveness analysis.
Code quality linter definitions. Tells the Code Review Guardian agent which linters to check and run. Does NOT install anything. See PREREQUISITES.md for installation. --- # Code Review Guardian Tools ## Tool Inventory Check each linter's availability and detect project languages before scanning. Report status in the Tools Report. | Tool | Check Command | Purpose | Relevant When | |------|--------------|---------|---------------| | ESLint | `eslint --version` | Style, bugs, complexity | JavaScript/TypeScript (package.json) | | Ruff | `ruff --version` | Fast Python linter | Python projects | | Pylint | `pylint --version` | Deep Python analysis | Python projects | | Clippy | `cargo clippy --version` | Idiomatic Rust patterns | Rust projects (Cargo.toml) | | dotnet format | `dotnet format --version` | C# style and analyzers | C# projects (.csproj) | | Checkstyle | `mvn checkstyle:check` or `gradle checkstyleMain` | Java style and bugs | Java projects (pom.xml, build.gradle) | ## Scan Commands (run in parallel per language, when available) ``` # JavaScript/TypeScript eslint . --no-error-on-unmatched-pattern --format compact # Python ruff check . pylint --disable=C0114,C0115,C0116 --score=yes <files> # Rust cargo clippy --message-format=short # C# dotnet format --verify-no-changes --verbosity minimal # Java
Create or modify tools (.json + .sh pairs) and skills (SKILL.md files) and hot-reload them into the active conversation using reload_capabilities. Use when you want to build a new capability, extend yourself with a new tool, fix an existing tool, create or update a skill, or build a complete application (web server, API, data pipeline, CLI) — all without restarting. --- ## Overview You can extend yourself at runtime. New tools and skills take effect immediately via `reload_capabilities` — no session restart required. Session-scoped capabilities live in `core/` inside your session directory: - **Tools**: `core/tools/<name>.json` (schema) + `core/tools/<name>.sh` (implementation) - **Skills**: `core/skills/<name>/SKILL.md` (frontmatter + body) **There is no limit on what a tool can do.** The shell script can call Python, Node.js, any language or binary on the system. Build first, use immediately. --- ## Building a tool
JSON-RPC patterns for Odoo 17 (Community + Enterprise) — session auth, `account.move` vendor bill creation with line items, multi-currency resolution, and `mail.activity` manager approvals. Load this when writing C# or Python code that talks to Odoo without the official XML-RPC library, or when debugging `NotNullViolation` / inactive currency errors.
MiniMax 全功能工具包。触发词：minimax、生成图片、生成语音、生成音乐、生成视频、配置 minimax。Agent 首先运行 `python3 scripts/toolkit.py check --json` 了解环境状态。
Guide for using dttb, a Python package that attaches timestamps to exception tracebacks. Use this when debugging Python scripts, working with unknown exception timings, or configuring error logging.
Deploy Python apps, API backends, and MCP servers to Floom. Use when building a Python function or API that needs a live URL, REST endpoint, web UI, or MCP tools.
Baseline de conhecimento para AI/ML engineering moderno em Python. Foco em LLM engineering, RAG systems, agent frameworks (LangChain/LangGraph), multiple LLM providers (Anthropic, OpenAI, Bedrock, Gemini, Meta), vector databases (Qdrant), semantic caching (MongoDB, Redis), testing, observability, security, e production patterns. Complementa arch-py skill com patterns AI-specific.
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:
