Use when asked to "review recent changes", "chunk review", "review my diff", "review this PR", "review PR #123", "review PR <url>", "review my changes", or asks for a code review using the team's review prompt. Supports GitHub PRs via `gh pr diff` and local diffs. Applies team-specific review standards from the .chunk/context/review-prompt.md file.
Generate synthetic training data variations using image transforms. Increases dataset diversity with flips, brightness jitter, and noise. Use after labeling.
Add persistent memory to any agent so it can remember prior work, maintain context across sessions, and continue long-running workflows.
Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen. --- # swift-auto-gui The `sagui` CLI provides mouse control, keyboard input, screenshot capture, image recognition, and screen queries for macOS automation. ## Prerequisites - **Accessibility**: Required for mouse and keyboard commands. Enable in System Settings > Privacy & Security > Accessibility. - **Screen Recording**: Required for screenshot and image recognition commands. Enable in System Settings > Privacy & Security > Screen Recording. ## Coordinates All coordinates use **CGWindow coordinate system** — logical points with origin at the **top-left of the primary display**. - x increases to the right - y increases downward - Values are in logical points (not pixels) Use `sagui screen size` to get screen dimensions. ## Commands ### key — Simulate keyboard input ```bash sagui key shortcut command c # Keyboard shortcut (Cmd+C) sagui key shortcut command shift a # Multi-modifier shortcut sagui key down shift # Press key without releasing sagui key up shift # Release a held key sagui key type "Hello, World!" # Type text character by character sagui key type "slow" --interval 0.1 # Type with delay between keystrokes ``` | Subcommand | Arguments | Optional | |---|---|---| | `shortcut` | `<keys...>` (key names) | | | `down` | `<key>` | | | `up` | `<key>` | | | `type` | `<text>` | `--interval <seconds>` (default: 0) | #### Supported key names **Modifiers**: `command`, `shift`, `rightShift`, `control`, `rightControl`, `option`, `rightOption`, `capsLock`, `function` **Letters**: `a`-`z` **Numbers**: `zero`-`nine` **Function keys**: `f1`-`f20` **Arrow keys**: `upArrow`, `downArrow`, `leftArrow`, `rightArrow` **Navigation**: `home`, `end`, `
Build Stellar blockchain applications in Flutter/Dart using stellar_flutter_sdk. Use when generating Dart code for transaction building, signing, Horizon API queries, Soroban RPC, smart contract deployment and invocation, XDR encoding/decoding, and SEP protocol integration. Covers 26+ operations, 50 Horizon endpoints, 12 RPC methods, and 18 SEP implementations with async/await and Stream patterns across Android, iOS, Web, and Desktop.
Deploy the application to staging or production.
Provides comprehensive guidance for Electron framework including main process, renderer process, IPC communication, window management, and desktop app development. Use when the user asks about Electron, needs to create desktop applications, implement Electron features, or build cross-platform desktop apps.
Manage Grid bots (spot/contract/coin-margined) and DCA Martingale bots (Spot DCA 现货马丁 / Contract DCA 合约马丁) on OKX. Covers create, stop, amend, monitor P&L, TP/SL, margin/investment adjustment, and AI-recommended parameters. Requires API credentials. Not for regular orders (okx-cex-trade), market data (okx-cex-market), or account info (okx-cex-portfolio).
跨学科专家研究方法。描述如何从网上的信息去采集、分析最靠谱、最真实的数据并进行分析研究的方法论框架。
Comprehensive guide for developing Letta agents, including architecture selection, memory design, model selection, and tool configuration. Use when building or troubleshooting Letta agents.
HyperDbg Rust 驱动开发完整指南。包含 C++ 代码复刻、Rust 驱动开发、类型同步、编译验证等。在需要开发或维护 HyperDbg_rust 驱动时调用。
Build the EXE and distribution package. Use when the user wants to create a release build.
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:
