AI Agent Skills

Operate the user's local Galley desktop orchestrator through the Galley CLI: inspect sessions/projects/goals, start or continue a Galley session, split work int

Foundation for building, modifying, debugging, or verifying Runway Dev Platform integrations in an application: connect Dev MCP, use llms.txt to find current resources,…

Portable OKF knowledge bundle for coding-agent memory and LLM wikis. Use when the user wants to start a wiki, ingest a source, document a repository, query project knowl…

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. U…

Analyze code changes and update KNOWLEDGE_BASE.md with architectural and feature changes.

Use this when adding evaluation to an LLM/agent app - measuring output quality (correctness, faithfulness, relevance, safety) rather than just watching traces. Trigger o…

Use this to build a good evaluation dataset for an LLM app, the part everyone underestimates. Trigger on "make an eval set", "what should I test my LLM on", "I don't hav…

Maintain a project-local, version-pinned wiki of every external dependency. Use whenever a new library is being added, an existing one is being upgraded, an idiom for us…

Prove that a knowledge base actually works before trusting it — after building or adopting docs, a knowledge graph, or a wiki, verify it can orient a fresh agent and res…

Maintain bounded, durable AI project memory in a repository's docs/ai/ pack. Use when Codex or Claude Code needs to create, read, update, or audit project memory (projec…

Query and maintain the user's local LLM Wiki from any Codex or Claude Code conversation or project. Use when the user asks to search personal knowledge, recall prior res…

在风险分析完成后、写测试代码之前，生成中文业务用例并等待用户确认。这是整个 QA 流程中唯一的强制人工门禁——确认后不可回头改用例。 从 context、risk-analysis、已有用例索引出发，生成只含业务行为的 test-cases.json（不含技术检查如 Maven/build/安装）， 渲染 test-cases.html…

Compare two versions of an LLM-directed document - an original (teacher) and a candidate (student) - across a transfer set and return a per-case behavioural-equivalence…

Attacker's-eye test of LLM/agent defenses: instruction hijacking, data exfiltration and tool abuse through untrusted content; verifies whether the defense actually holds.

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural langu…

Use when running or configuring `xmake ai` — the terminal coding agent provided by the xmake-harness addon. Covers installing it, setting an llm provider and api key, se…