- 📁 assets/
- 📁 SX-openclaw-discovery/
- 📁 SX-openclaw-token-optimizer/
- 📄 SKILL.md
Record issues, lessons learned, errors, and corrective actions reported by the Lynx-Guardian plugin for continuous improvement. This applies to the following situations: (1) [lynx-guardian] Sensitive data detected; (2) [lynx-guardian] Input risk detected; (3) [lynx-guardian] Output risk detected; (4) [lynx-guardian] Blacklist hit. Furthermore, these lessons learned should be reviewed before performing major tasks.
How to design, structure, and validate custom Copilot agents for this workspace.
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
创建和修改 Agent 的指南。当用户想要创建新的 Agent 或修改现有 Agent 时使用此 Skill。Agent 是定义 AI 角色、行为准则和工作流程的 Markdown 文件，存放在 marketplace 的 atoms/agents 目录下。
Set up and launch an autonomous AI research project with Limina. TRIGGER when: user types /limina, says 'start a limina project', 'set up a research project', 'I want to research X autonomously', 'create a research agent', 'autonomous research', 'start a new research mission', or asks to investigate/research a hard technical problem systematically with experiments and evidence. Also triggers on 'limina' mentioned as a tool to use. DO NOT TRIGGER for: general coding questions, simple research lookups, or tasks that don't need structured multi-session research.
- 📁 .github/
- 📁 app/
- 📁 docs/
- 📄 .env.example
- 📄 .gitignore
- 📄 .mcpbignore
Automate DSers dropshipping — search products, import from AliExpress/Alibaba/Accio, apply pricing rules, push to Shopify & Wix, and replace broken suppliers at the SKU level. 13 tools for the full product lifecycle.
Manually trigger context compaction to summarize conversation history.
How keyboard shortcuts are wired globally and per-panel in this repo.
Development guidelines for DotCraft project. Use this skill when developing DotCraft core features, adding new modules (including external channel adapters via AppServer/JRPC), modifying existing code, or writing documentation. Covers C# code style, tool naming (PascalCase for AI functions), module development norms (via spec), external channel extension with Python SDK, spec-first workflow, testing requirements, and bilingual documentation.
Parse project briefs and linked assets for /archi.init. Must run in isolated context/subagent. Protocol-invoked only; do not auto-trigger from casual user requests.
Use Mergify CI commands to upload JUnit test results, detect git references, manage CI scopes, and retrieve merge queue metadata. ALWAYS use this skill when working with CI pipelines, test result uploads, quarantine, scopes detection, or merge queue CI context. Triggers on CI, JUnit, test results, quarantine, scopes, git refs, CI insights.
Use when deciding whether a completed AnthroClaw run should become durable memory or a reusable native skill update. Helps convert user corrections, repeated workflows, and recovered mistakes into safe learning proposals.
Traces failures from observed symptoms to the first incorrect state transition.
