发现最适合你需求的 AI 技能
Interpret East Asian Four Pillars / Saju charts from already-derived pillars (year, month, day, hour stems/branches). Use when the user asks for 사주, 사주팔자, 명리, 팔자, 십성, 조후, 합충형해파, 신강약, 일간, 용신 discussion, or wants a rule-based reading from known pillars such as 경오년 기묘월 신미일 기해시. Prefer this skill for interpretation, not calendar derivation; assume the four pillars are already given unless the user explicitly asks for calendar conversion.
|
ElevenLabs text-to-speech with mac-style say UX.
Operate long-running AI tasks safely across GPT-5.4 and Claude by using model selection rules, phased execution, checkpoints, resumable workflows, API throttling discipline, and subagent isolation. Use when a task may run for a while, touch multiple files/systems, involve external APIs, browser automation, Azure, Orgo, or multiple subagents, or when the user asks about long autonomous runs, rate limits, reliability, or safe operating mode.
Operate long-running tasks safely when the environment is optimized for GPT-5.4 as the primary and often only model. Use when the user wants a low-cost, high-throughput long-run workflow, plans to keep everything on GPT-5.4, or asks how to run long coding, research, build, documentation, Azure, or multi-agent tasks safely without relying on Claude.
>-
Bootstrap any SaaS, dashboard, mobile, or API project with a reusable 3-agent AI operating system. Creates AGENTS.md, architect/builder/tester instructions, docs templates, and prompt templates for Codex-style execution.
A high-end spatial ownership and lineage recognition protocol. Teaches the OpenClaw agent to treat the physical space (mansion/villa) as a sovereign domain, using the owner's Chinese Surname (Hanzi) as the ultimate visual totem, security matrix, and ambient interactive core.
A multimodal emotional perception and Hanzi-based ambient art rendering engine. Empowers the OpenClaw agent to act as a spatial empath, translating human emotions into dynamic, therapeutic Hanzi morphological transformations (stroke fluidity, breathing rhythms, color shifts).
A hardcore spatial physics and dialectical reasoning framework. Teaches the OpenClaw agent to process environmental controls using Chinese antonym morphological shifts and dynamic masking, transcending traditional numerical GUI logic.
Optimized super-skill collection for OpenClaw/Codex, merging Perplexity + Claude Code expertise across 11 domains. Features specialized reference loading (progressive disclosure), tool-integrated workflows (exec, fs, web_fetch), and persona-aligned frameworks. Use for high-stakes professional AI tasks requiring structured reasoning, templates, or domain-specific gap analysis.
Test, extract, replace, split, and explain regular expressions. Use when asked to test a regex pattern, extract matches from text, do regex replacements, split text by pattern, or understand what a regex does. Supports named groups, case-insensitive/multiline/dotall flags, and JSON output. Works with stdin pipes or inline text. Zero dependencies.