fireworks-tech-graph
Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG.…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Agents & models
25,570 results
planning-with-files
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks,…
x402-payments
Enable and integrate x402 crypto payment protocol for XActions API access. Supports multi-chain, multi-token payments for pay-per-use API calls. Use when users…
prompt-engineer
Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts,…
context-guardian
Helps developers keep agent context lean and focused for maximum performance. Use this skill whenever the user wants to: audit or reduce context bloat in their…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
distributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or…
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device…
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
simpo-training
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model…
slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation…
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use…
codonfm-score
Validate, prepare, or run public CodonFM Encodon masked-codon variant scoring and review compatibility of its scoring workflows. Use only when the user…
tao-finetune-video-clip
InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT…
quiz-funnels
Build and manage marketing catalogs, landing pages, and multi-step funnels with your AI agent. Create catalogs from JSON schemas, publish them instantly, run…
mine
Use only when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history.
kamino-lend
Supply, borrow, and manage positions on Kamino Lend — the leading Solana lending protocol
orca
Concentrated liquidity AMM on Solana — swap tokens and query pools via the Whirlpools CLMM program. Trigger phrases: swap on orca, orca swap, swap tokens on…
workflow-engine
The ai-dev-team workflow contract. ALWAYS consult this at the START of any development task and BEFORE EVERY handoff between agents — it decides which process…
dao-governance
Comprehensive expertise in decentralized autonomous organization governance systems, including Snapshot off-chain voting, OpenZeppelin Governor on-chain…
discord-bot-architect
Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive…
worktree-discipline
Enforce "no commits on main, agents work in worktrees" with ONE machine-global git pre-commit hook — zero per-repo code. A single `~/.githooks/pre-commit`…
agent-model-selection
Guidelines for selecting appropriate language models for agents based on task-specific benchmarks, availability, and cost efficiency.
metro-ai-apps-builder
Conversational orchestrator that turns a plain business objective into a working Intel Edge AI application by asking only business questions — never which…