fastfold-ai

Run Boltz API workflows via the official `boltz-api` CLI — structure-and-binding, protein design/screen, small-molecule design/screen, ADME prediction, and job status/recovery. Use when the user wants to estimate, submit, monitor, fetch results for, stop, or recover a Boltz API job.

Submits and manages FastFold protein folding jobs via the Jobs API (Boltz-2, OpenFold 3, Chai-1, IntelliFold, AlphaFold2, SimpleFold). Covers authentication, job payloads, modifications, constraints, webhooks, polling, and CIF/PDB URLs. Use when folding with FastFold, OpenFold 3/Chai-1/IntelliFold complexes, ligands/affinity, or scripting create → wait → results.

Generate Mermaid diagrams on demand and proactively for complex multi-step workflows. Use when users ask for flowcharts/diagrams, or when explaining complicated pipelines such as BoltzGen, fold->MD, and computational biology execution flows.

Build and run FastFold BoltzGen protein-design workflows end-to-end through API or Composer draft links. Use this whenever users mention BoltzGen, design-spec YAMLs, binder design, multi-spec scaffold workflows, CIF/PDB preparation, workflow graph upsert, `/workflow/composer/<id>`, candidate metrics/structure results, or ask naturally for "help me design a protein" / "give me a simple example".

Run molecular dynamics (MD) simulations via the FastFold Workflows API. Today supports the CALVADOS+OpenMM workflow (calvados_openmm_v1) from either an existing fold job (AF structure + PAE auto-resolved) or manual PDB+PAE upload, then waits for completion, fetches metrics/plots/CSV artifacts, and extracts trajectory frames as PDB files. Use when running an MD simulation with FastFold, CALVADOS + OpenMM, reading MD metrics/plots, extracting frames, or scripting submit → wait → results for an MD run.

Run OpenMMDL molecular dynamics workflows via the FastFold Workflows API (`openmmdl_v1`) from local topology + optional ligand files, prepare draft scripts, execute drafts, wait for completion, fetch artifacts/metrics, and extract trajectory frames. Use when users ask for OpenMMDL, protein-ligand MD, OpenMMDL script preparation, or `/openmmdl/results/<workflow_id>` reruns.

Share markdown reports to the user's configured Slack agent_cli_report channel via Fastfold API, and persist the markdown as a library item.

Discover and install agent skills — first from the official Fastfold catalog (github.com/fastfold-ai/skills), then from the open skills.sh ecosystem (npx skills find). Use when the user wants to find, search, browse, list, or add new skills/capabilities (e.g. fold, MD, protein design) to the agent CLI.

Create new agent skills and iteratively improve them. Use when the user wants to build, scaffold, author, validate, or package a new skill for the Fastfold agent CLI.