技能列表

|

Trajectory compiler that converts real OpenClaw session traces (or raw_trajectory_log) into a parameterized, reusable Skill via 4 stages: trace interception → DAG abstraction → schema+code synthesis → registration.

Token and context window optimization — compact prompts, reduce redundancy, prioritize critical context. Use when hitting context limits or to improve agent efficiency.

Use this skill when the user wants to inspect, report on, create, update, pause, resume, budget, target, upload assets for, or troubleshoot Meta, Facebook, or Instagram ads via the Marketing API. It covers ad accounts, campaigns, ad sets, ads, creatives, ad images and videos, targeting search, batch reads, and Insights reports. Helpful for requests about Meta Ads Manager, ROAS or CPA reporting, launch workflows, creative rollout, audience setup, delivery issues, budget changes, or bulk ad operat

Use when analyzing a TikTok video or breaking down its script and structure.

Le campanhas, conjuntos, anuncios e criativos no Meta Ads para diagnostico, relatorios e recomendacoes operacionais usando somente o MCP brijr/meta-mcp.

X2C Distribution and Wallet API — publish video to X2C platform, manage assets (balance, claim X2C, swap to USDC, withdraw, transactions).

Use this skill when the user wants to design, scope, or refine a Buddhist, spiritual, or cyber-chanting AI product. It is especially useful for local-first ritual companions, merit-point systems, daily practice robots, dedication assistants, scripture libraries, and future online Buddhist communities. Turn rough ideas into a concrete product concept with users, scenarios, features, local-vs-online scope, safety boundaries, and monetization.

Orchestrate OpenClaw Agent Swarm workflows for multi-project coding automation. Use when user says "合并"/"merge" replying to a PR_READY notification, spawns a coding task, or asks about agent/task/MR status. Covers: Obsidian task intake, Claude coding, Codex review, GitLab MR flow, merge+sync, done-status closure.

108 个思维模型，16 个系列，含周期分析实战指南

Apply a Munger-style latticework of mental models from multiple disciplines to analyze a problem. Use when the user needs multi-disciplinary perspective, wants to avoid single-framework bias, or needs to triangulate insights from physics, biology, psychology, economics, math, and history simultaneously.

Mac laptop clamshell mode assistant. Supports running with lid closed WITHOUT external display/keyboard/mouse. Auto-detects Mac model and macOS version, provides safe configuration with rollback.