alterlab-boltz
Co-fold biomolecular complexes with Boltz-2, an open AlphaFold3-style model — predict protein + ligand (SMILES/CCD), protein + nucleic-acid, and multi-chain…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
25,188 results
Co-fold biomolecular complexes with Boltz-2, an open AlphaFold3-style model — predict protein + ligand (SMILES/CCD), protein + nucleic-acid, and multi-chain…
Generate de-novo protein backbones with RFdiffusion (Watson 2023) — a diffusion model for unconditional monomer generation, motif scaffolding, binder design…
Carry a spec or tickets through implementation, polish, and PRs in one workflow.
MCP config converter for agent CLIs. Converts Claude Code MCP settings into Codex CLI MCP configuration, copying env values directly into Codex config. Use…
Manages named skill profiles (loadouts) so you can switch between focused skill sets and prevent system prompt bloat from too many active skills.
JVM dependency intelligence via Maven Tools MCP server. Use when the user asks about Maven or Gradle dependencies, safe upgrades, CVEs, license risks, release…
Diffusers model weight preparation tool for Huawei Ascend NPU. Supports downloading model weights from HuggingFace and ModelScope, as well as generating fake weights based on model_index.json and each component's config.json for business validation. Use when users need to download Diffusers model weights or generate test weights.
Run NPU inference/training tests on a remote SSH server with vllm-ascend Docker container. Use when the user asks to test models on NPU, run inference on…
Metacognition skill for AI agents. Use when starting work, feeling stuck, output feels off, or before complex tasks. Teaches how to think about thinking.
Structured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets), debate (a 4-persona panel on 4 models…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's…
Mine transcripts, .agents, br, and git for skill diffs, br updates, or rare wiki entries. Triggers: "curate skills from sessions", "mine transcripts for skill…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
Agent self-evolution system. Collects signals from user feedback, stores execution trajectories (golden + correction pairs), analyzes patterns, proposes…
An automation tool for large model training tasks based on ark_sdk. It helps users create and submit Ark model training tasks through natural language, supports SFT training with user-provided data, RFT+GRPO and direct GRPO strategies, and guides users to complete the training, status tracking, and evaluation loop. Use case: triggered when users need to perform large model SFT supervised fine-tuning, RLHF training, GRPO training, RFT training, or need to automate the training process.
Creates Claude Code plugins that package skills, agents, hooks, and MCP servers into distributable bundles. Covers plugin.json manifest, directory…
Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules. Read by skills, never dispatched on its own.
Coordinator workflow for orchestrating dockeragents through fix-review-iterate-present loop. Use when delegating any task that produces code changes. Ensures…
Control Chrome browser programmatically using chrome-devtools-mcp. Use when user asks to automate Chrome, debug web pages, take screenshots, evaluate…
Create a new skill that uses an MCP server, following best practices from the MCP CLI guide. Use when user wants to create a skill for a new MCP server or…
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when…
AI agent payment infrastructure — ACTP escrow, x402 instant payments, USDC settlement on Base L2. Interactive onboarding: asks your preferences, generates…
Use when adding, pruning, archiving, restoring, or reviewing Agent Notes.
Apply an external agent-research knowledge base to a repo's agent-meta: read a public knowledge mirror and the host repo's own CONTEXT.md / CLAUDE.md /…