001TMFCommunity·19 Agent Skills Included

blatant-why

Protein binder and antibody design campaigns with lab feedback

Designs protein binders, antibodies, and nanobodies against a target using BoltzGen, PXDesign, and Protenix on local GPU, HPC, or cloud compute. Researches targets across PDB, UniProt, and SAbDab, then screens every design for interface quality, sequence liabilities, and developability. Ranks candidates by composite score and closes the loop by comparing lab results against predictions to improve the next round.

104|10

↗

npx skills add 001TMF/blatant-why --all -g -y

Available:

Defines the agent's identity as a protein design expert and instructs it on session startup, tool priority, compute provider selection, safety gates, and the research-to-ranking campaign workflow.

All Skills in This Repository (19)

Pure Emerald Level Indicators

📦 In Repo

001TMF

by-epitope-analysis

Identify and score epitope interface residues from co-crystal structures for binder design.

by-database

Queries PDB, UniProt, and SAbDab via MCP servers to produce structured CSV outputs for target characterization and scaffold selection.

by-research

Automate cross-database target research for antibody campaigns with an 8-phase pipeline.

by-knowledge

Store and query campaign knowledge in a persistent graph.

by-scoring

Compute and interpret BY ipSAE, ipTM, and composite scores from PAE matrices.

by-screening

Apply hard filters and composite ranking to protein designs, outputting PASS/MARGINAL/FAIL verdicts as CSV.

by-display

Render consistent BY terminal outputs using canonical display templates.

by-causal-reasoning

Generate ranked, evidence-grounded hypotheses from diagnostic features.

by-design-workflow

Route design intents to engines and generate routing and handoff JSON artifacts.

by-campaign-optimizer

Generates next-round YAML configs from scored protein designs using Random Forest regression.

by-session

Initialize BY sessions by configuring the environment and running the first-run questionnaire.

by-deploy-compute

Deploy BY design tools to local, RunPod, Modal, or HPC compute surfaces.

Community

Advanced

Frequently Asked Questions

FAQPage Schema

How to install blatant-why?▼

Run `npx skills add 001TMF/blatant-why --all -g -y` in your terminal to install the full suite globally.

How to design a nanobody against a protein target?▼

Give the agent a target name or PDB ID and say what you want, for example "Design VHH nanobodies against PD-L1". It researches the target, picks hotspots, generates designs, and screens them automatically.

Do I need a GPU to run protein design campaigns?▼

No. A local NVIDIA GPU is the default, but you can also run on RunPod, Modal, SLURM clusters, or the Tamarind Bio cloud free tier.

Can I use blatant-why without coding experience?▼

Yes. After setup you describe your target in plain English or use guided commands like /by:plan-campaign, and the agent handles research, design, and screening.

How does blatant-why use real lab results?▼

It ingests lab readouts such as ELISA or BLI data, compares them against the in-silico predictions, and feeds the calibration back into future campaigns so each round gets smarter.