Cua Wechat Devtools Ui Inspection
Use Cua Driver to inspect and navigate WeChat DevTools simulator for Mini Program UI visual review. Covers AX tree quirks, pixel-click strategies, and NW.js limitations.
Auto Gui Debug Loop
General-purpose GUI debugging loop — use Cua Driver + Vision AI to automate any desktop GUI app with screenshot analysis and automated click/verify flow
Requesting Code Review
Use when requesting a code review before pushing changes.
Context Aware Task Decomposition
Use when the context window is getting full and tasks need breaking down.
Skill Slimming Strategy
Use when a skill SKILL.md is over 2000 words and needs trimming to the Superpowers standard of under 500 words.
Hermes Core Skills
25 executable AI agent skills for debugging, planning, token efficiency, and security
Cua Driver Install Macos
Install, configure, and integrate Cua Driver (trycua/cua) on macOS for background desktop control via MCP, including permission granting and Hermes integration.
Hermes Improvement Multiphase Plan
Structured multi-phase plan for improving Hermes Agent — IDE docs, release frequency, plugin marketplace, desktop app, and Rust performance.
Agent Capability Comparison Methodology
A Claude skill from ChrisLamDev/hermes-core-skills.
Autonomous Work Signaling
Use when signaling work status across autonomous sessions.
Writing Plans
Use when the user asks for a plan instead of executing work.
Test Driven Development
Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.
Openclaw Hermes Arch
Use when understanding the relationship between OpenClaw Gateway and Hermes Agent.
Systematic Debugging
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
Spec Driven Development
Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
Multi Agent Browser Text Extraction
Use delegate_task with multiple browser-equipped sub-agents to extract verbatim text from Chinese academic/religious websites with JavaScript-heavy tree navigation. Covers coordination patterns, site-specific navigation, error recovery, and QA verification.
Token Efficiency
Use when context is getting large, when working on long sessions, or when you notice token consumption is high. Use before dispatching subagents, before reading large files, and during context compaction.
Security Hardening Checklist
Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
Think Tool
Use when facing a complex decision, multiple possible approaches, or before making irreversible changes. Use when the best course of action is not obvious and requires reasoning before acting. Use before running destructive operations, before large refactors, or when you catch yourself rushing.
Cua Desktop Automation Skills
Router Learning System + macOS desktop automation skills for AI agents using Cua Driver — task routing, fallback chains, self-learning history.
Cua Browser Github Oauth
Complete GitHub OAuth/Device Code Flow via Cua Driver browser automation — bypasses Chrome URL bar search issue when authenticating from headless agents
Checkpoints And Rewind
Use before making irreversible changes (deleting files, destructive git operations, large refactors). Use when you need the ability to roll back if something goes wrong. Use at the start of any task that modifies multiple files.
Context Compaction Verification And Recovery
Use when verifying that tool commands actually executed after compaction.
Subagent Driven Development
Use when executing implementation plans with independent tasks in the current session
Self Regulation Brake System
Brake system that auto-stops the agent after N repeated failures, prevents token burning on loops.
Desktop Browser Automation Cua
Use Cua Driver to automate desktop browsers (Chrome/Safari) — open pages, type text, click elements, execute JavaScript. Includes React/Draft.js workaround for X.com and similar SPA platforms.
Cross Session Execution Framework
Use when managing a long-term project across multiple Hermes sessions.
Cua Driver Macos Automation
Use Cua Driver for macOS desktop automation — launching apps, clicking UI elements, and controlling web pages via Accessibility API and JavaScript injection.
Router Learning System
Router Learning System — 越用越聰明嘅任務路由引擎。
Plan
Use when the user asks for a plan instead of executing work.
Hermes Tweet
Use when Hermes Agent needs X/Twitter search, public signal research, monitoring, or approval-gated account actions through the Hermes Tweet plugin.
Cua Vision Hybrid Control
Hybrid control loop using Cua Driver (Accessibility) + Vision AI (Screenshot Analysis) for macOS desktop apps. Full pipeline: screencapture → vision_analyze → Cua hotkey/click → screencapture verify.
Multi Role Synthesis Framework
Use when Chris wants multiple perspectives on a design/feature decision and then a final integrated verdict. 多角色各自俾建議 → 終極角色做篩選整合，避免單一角度的盲點。
Batch Skill Description Standardization
Use when needing to standardize descriptions across many skill files at once — change format, fix wording, or enforce a convention like 'Use when...' prefix.
Hermes Agent
Use when setting up or extending Hermes Agent.
Open Source Adaptation Pattern
Use when evaluating whether an open-source project fits our needs.