Loading...
Loading...
Found 179 Skills
Review a Memory Bank with fresh-context specialists and produce a prioritized fix list.
Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure
AI's Knowledge Base CLI - Query and manage world knowledge for AI agents. Use when users want to search knowledge, add knowledge sources, or interact with the worldbook knowledge base. This is a CLI-first approach that treats AI agents as first-class citizens.
Generate high-divergence, out-of-the-box analysis plans and prompts that counter anchoring, mode collapse, and context bias while staying practical. Use when requests ask for unconventional strategies, non-obvious options, radical reframing, MCP-assisted synthesis across prior messages/sources, or "think differently" outputs that still require executable next steps.
CRITICAL: Use for Makepad Splash scripting language. Triggers on: splash language, makepad script, makepad scripting, script!, cx.eval, makepad dynamic, makepad AI, splash 语言, makepad 脚本
Proactive token budget assessment and task chunking strategy. Use this skill when queries involve multiple large file uploads, requests for comprehensive multi-document analysis, complex multi-step workflows with heavy research (10+ tool calls), phrases like "complete analysis", "full audit", "thorough review", "deep dive", or tasks combining extensive research with large output artifacts. This skill helps assess token consumption risk early and recommend chunking strategies before beginning work.
Locate the latest checkpoint for a run id and provide a follow-up play/eval command. Use when asked to find a checkpoint.
Orchestration workflow for orchestrator role ONLY. Use when: - Agent's role name (tmux pane title) is "orchestrator"
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.
Creates missing instruction files (CLAUDE.md, AGENTS.md, GEMINI.md), audits token budget, prompt cache safety, cross-agent consistency. Use after setup or when instruction files need alignment.
Worker-Agent integration for intelligent task dispatch and performance tracking
Use when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.