Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

pipeline-guide

MaaEnd Pipeline JSON 编写指南。基于 MaaFramework Pipeline 协议,提供节点命名、识别算法、动作类型、流程控制、可复用节点等编码规范与模式参考。在编写、修改或审查 Pipeline JSON、设计节点流程、使用 TemplateMatch/OCR/Custom 识别或 Click/Swipe 动作时使用。

3.41k repo starsObserved in 1 repos
Agent Building

analytics

Analyze your AI agent's performance using LangWatch analytics. Use when the user wants to understand costs, latency, error rates, usage trends, or debug specific traces. Works with any LangWatch-instrumented agent.

3.37k repo starsObserved in 2 repos
Agent Building

generate-rag-dataset

Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.

3.37k repo starsObserved in 2 repos
Agent Building

improve-setup

Expert AI engineering consultant for your LangWatch setup. Audits your codebase, traces, evaluations, and scenarios, then guides you to improve — starting from low-hanging fruit and going deeper. Use when you want to level up your agent's engineering quality.

3.37k repo starsObserved in 2 repos
Agent Building

prompts

Version and manage your agent's prompts with LangWatch Prompts CLI. Use for both onboarding (set up prompt versioning for an entire codebase) and targeted operations (version a specific prompt, create a new prompt version). Supports Python and TypeScript.

3.37k repo starsObserved in 2 repos
Agent Building

arming-thought

触发:在每次新的顶层对话开始时自动调用,用于建立“实事求是”的总原则,并在明确适用时为后续任务选择下游 skill;如果你是被派遣执行单一具体任务的子 agent,则跳过此 skill。 English: Trigger at the start of each new top-level conversation to establish the core methodology and select downstream skills only when clearly useful. Skip this skill when you are a delegated sub-agent handling a narrow, concrete task.

3.36k repo starsObserved in 5 repos
Agent Building

gnhf

Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.

3.32k repo starsObserved in 1 repos
Agent Building

audit-agents

Audit the linq2db `.agents/` instruction corpus (docs, skills, agents, hooks, scripts) + the per-agent entry points `AGENTS.md` / `CLAUDE.md` / `.github/copilot-instructions.md` for duplicated rules, dead references, terminology drift, retired-path mentions, SKILL template gaps, `linq2db.slnx` mismatches, and auto-memory entries that would be better as project-level rules. Reports findings in severity order and offers per-finding patches after explicit user confirmation. Read-only until confirmation.

3.30k repo starsObserved in 1 repos
Agent Building

update-slnx

Sync the /.agents/* virtual folders in linq2db.slnx with the actual on-disk contents of the .agents/ directory. Use after adding, removing, or renaming files or subdirectories under .agents/ (skills, hooks, docs, local settings, etc.).

3.30k repo starsObserved in 1 repos
Agent Building

ccb-clear

Clear CCB managed agent conversation context with `ccb clear`. Use when the user writes `$ccb-clear`, `$ccb_clear`, or asks to clear/reset one or more CCB agent contexts without restarting or deleting project state.

3.27k repo starsObserved in 2 repos
Agent Building