全部能力

Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions. Use when encountering any bug, test…

This skill should be used when the user asks to 'place a CEX order', 'trade on centralized exchange', 'buy BTC on CEX', 'sell ETH futures', 'open a long…

| Nuxt 4 server-side development with Nitro: API routes, server middleware, database integration, and backend patterns. Use when: creating server API routes,…

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring…

Browse and recall OpenCode local memory stored on the user's machine: local sessions, plans, conversations, prompt history, and project context. Use immediately when the user asks to check history, previous sessions, past chats, what did we do before, last time, check plans, session history, recall, memory, remember, prior work, previous context, or have we done this before. Auto-trigger proactively when resuming work, continuing a project, referencing prior decisions, debugging repeated issues, revisiting earlier plans, or any follow-up where earlier OpenCode context may help. This means OpenCode local history/files specifically, not ChatGPT/Claude cloud history, generic web search, or unrelated product memory systems. Do NOT use for fresh tasks with no relevant history, or when current files/git already answer the question.

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is…

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+…

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or…

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or…

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward…

Generates semantic commit messages following the Conventional Commits specification with proper types, scopes, breaking changes, and footers. Use when users…

Create a Linear OAuth application and configure Cyrus to use it — supports agent-browser automation or guided manual setup.

This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure", "self-review before…

Python video composition with moviepy 2.x — overlaying deterministic text on AI-generated video (LTX-2, SadTalker), compositing clips, single-file build.py…

Philosophy-aware PR reviews checking alignment with amplihack principles. Use when reviewing PRs to ensure ruthless simplicity, modular design, and zero-BS implementation. Suggests simplifications, identifies over-engineering, verifies brick module structure. Posts detailed, constructive review comments with specific file:line references.

SEO keyword clustering with topic organization, content hub architecture, internal linking strategies. Use for content strategy, keyword research, pillar page…

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory),…

Systematic step-by-step reasoning with revision and branching. Use for complex problems, multi-stage analysis, design planning, problem decomposition, or…

Generate game art assets using each::sense AI. Create 2D sprites, character sprite sheets, seamless textures, UI elements, icons, tilesets, loading screens,…