Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
platform-tracing-agentforce-configure
Generate AgentforcePlatformTracingSettings metadata to enable or disable Agentforce agent execution trace spans flowing to Data Cloud. Use this skill for any AgentforcePlatformTracingSettings metadata work. TRIGGER when: user mentions Agentforce tracing, agent trace spans, Data Cloud tracing, AgentforcePlatformTracingSettings, platform observability tracing, enable agent tracing, wants agent execution spans in Data Cloud, mentions .settings-meta.xml for AgentforcePlatformTracing, or asks about enabling observability for Agentforce agents. DO NOT TRIGGER when: user wants Platform Tracing for TraceSpanEvent (use platform-tracing-configure), wants to query or analyze existing agent trace data in Data Cloud (use agentforce-observe), wants Event Log Files or ELF configuration, wants Change Data Capture (use integration-eventing-cdc-configure), or wants ManagedEventSubscription (use integration-eventing-subscription-configure).
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
ad-bootstrap
Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps. Use whenever the user wants to bootstrap, scaffold, generate, create, set up, or audit AGENTS.md / CLAUDE.md / agents.md (the operational guide for agents working on this project).
ad-philosophy
Universal agent behavior and documentation discipline — think before coding, ground in real patterns, prefer simplicity, make surgical changes, define verifiable goals, verify before claiming done, and write documentation that captures only definitions and decisions. Auto-invokes on non-trivial changes, refactors, debugging, "think before coding", "ground before coding", "verify done", "before implementing", on documentation work — "writing docs", "writing readme", "writing architecture", "writing adr", "writing task", "audit docs" — or whenever the task is ambiguous enough that guardrails matter.
wecom-preflight
WeCom MCP 文档/智能表格调用前置检查。仅当已经决定调用 `wecom_mcp` 的 doc 类能力时使用；不要用于给企业微信用户或群发消息、联系人查询、日程、会议或待办。发消息必须使用 OpenClaw core `message` 工具。
hermes-persona-builder
陪伴型 AI 人设生成与优化流程。当用户想给 Hermes Agent（或任意 AI 陪伴角色）做一个"有感情、聊久不掉、像真人"的人设时使用。通过"定调子 → 名字 → 外形 → 性格 → 背景 → 关系 → 说话节奏 → 生成 SOUL.md → 迭代"的结构化对话，从一句模糊想法（如"我想要个JK女友""年上男友""高冷御姐"）产出可直接贴进 Hermes SOUL.md 的第一人称人设文本。支持女友/男友/各种气质的陪伴角色，并让用户选择"一句一句发"还是"整段说"的输出风格。当用户说"做个人设/捏个AI女友男友/给Hermes弄个角色/优化人设/换个人设"时触发。
lingtai-preset-skill
Routing table for the 12 TUI-shipped built-in preset templates. Reach for this skill when you need to select, configure, compare, or troubleshoot a built-in preset template — not an arbitrary saved preset. Routes to one nested manual per built-in preset under reference/<preset>/SKILL.md.
preset-health
Nested swiss-knife reference for saved-preset health checks. Read this when the human asks whether saved presets still work, which preset is expired or misconfigured, why `system(action="presets")` shows a bad connectivity status, or for a safe procedure to enumerate saved presets, classify each failure (expired key, missing credentials, unreachable endpoint, invalid model/config, connectivity failure), and report results without leaking secrets. This is a READ-ONLY diagnostic workflow: it never edits a preset or an agent `init.json` on its own — it produces an actionable report and tells the human exactly which one-line change to confirm.
preset-skill-gemini
Nested lingtai-preset-skill reference for the `gemini` built-in preset. Read when verifying shipped identity, provider sources, and compatibility facts for the `gemini` template preset.