Agent Claude Code
Parallel target structure research via PDB. Finds best resolution crystal structures, identifies chains, interfaces, binding surfaces, and downloads the optimal structure for design.
114 15d ago A 37 tokens
original MIT
by-verifier
26Agent Claude Code
Independent quality gate checker. Verifies structural metrics, screening completeness, and candidate integrity before results are presented to the user.
114 15d ago A 28 tokens
original MIT
Agent Claude Code
Generate PyMOL and ChimeraX session scripts for structural visualization. Creates publication-quality views of targets, designed complexes, interfaces, CDR loops, electrostatic surfaces, and clash detection.
114 15d ago A 43 tokens
original MIT
Command Claude Code
Approve lab submission to Adaptyv Bio (triple-gated).
114 15d ago A 21 tokens
original MIT
Command Claude Code
Full autonomous campaign — research, design, screen, rank with minimal interruption.
114 15d ago A 19 tokens
original MIT
by:load
30Command Claude Code
Load a protein target and analyze it for design.
114 15d ago A 13 tokens
original MIT
Command Claude Code
Pre-campaign discussion -- capture design preferences before launching.
114 15d ago A 16 tokens
original MIT
by:resume
32Command Claude Code
Resume an interrupted campaign from the last checkpoint.
114 15d ago A 12 tokens
original MIT
Command Claude Code
Switch model profile (quality/balanced/budget).
114 15d ago A 15 tokens
original MIT
by:setup
34Command Claude Code
Discover and configure compute environment.
114 15d ago A 9 tokens
original MIT
by:view
35Command Claude Code
View a protein structure in ProteinView (opens tmux split pane).
114 15d ago A 17 tokens
original MIT
by:welcome
36Command Claude Code
First-run orientation -- what BY can do and where to start.
114 15d ago A 16 tokens
original MIT
SessionStart
37Hook Claude Code
Runs when a session starts, executing env-loader.js via node. From 001TMF/blatant-why.
114 15d ago A
tokens not measured
original MIT
PostToolUse
38Hook Claude Code
Runs after a tool call finishes, executing statusline.js and campaign-tracker.js via node (2 commands). From 001TMF/blatant-why.
114 15d ago A
tokens not measured
original MIT
PreToolUse
39Hook Claude Code
Runs before the agent uses a tool for mcp__by-adaptyv__adaptyv_confirm_submission tool calls, executing safety-gate.js via node. From 001TMF/blatant-why.
114 15d ago A
tokens not measured
original MIT
boltzgen
40Skill Claude CodeCodex
BoltzGen is an all-atom diffusion model that generates antibody, nanobody, and de novo miniprotein backbones conditioned on a target structure and a set of binding (hotspot) residues. Sequences are assigned by AntiFold, then each design is independently refolded with Protenix to produce ipTM, pTM, pLDDT, ipSAE, and…
114 15d ago A 3 tokens
original MIT
Skill Claude CodeCodex
Plan, execute, monitor, and assess protein/antibody design campaigns. This skill governs how to size a campaign, track run state, coordinate multi-run efforts, estimate cost and time on each compute target (local GPU, HPC, Tamarind), monitor progress, and evaluate campaign health.
114 15d ago A 4 tokens
original MIT
Skill Claude CodeCodex
Multi-round design campaigns generate scored designs at every iteration. This skill turns that scoring history into actionable parameter changes for the next round — training a lightweight Random Forest on the designs you already have, ranking which features actually discriminate good from bad, and proposing…
114 15d ago A 5 tokens
original MIT
Skill Claude CodeCodex
Most "AI scientist" demos fake reasoning by chaining LLM calls and calling the chain a hypothesis. This skill does the opposite: it constrains the LLM with structured evidence retrieved from the BY knowledge graph and forces every claim to cite an existing entity with a defined evidence tier. The output is a short…
114 15d ago A 6 tokens
original MIT
by-database
44Skill Claude CodeCodex
Use the BY MCP database tools to query PDB, UniProt, and SAbDab for target characterization, antibody scaffold selection, and competition analysis.
114 15d ago A 3 tokens
original MIT
Skill Claude CodeCodex
BY is a local-first agent. The default compute provider is "local" (see .by/config.json → compute.defaultprovider). This skill teaches you how to stand up each design and folding tool on hardware the user owns or pays for directly — a personal GPU workstation, a RunPod pod, a Modal app, or a generic SLURM/PBS cluster…
114 15d ago B 5 tokens
original MIT
Skill Claude CodeCodex
Skill "by-design-workflow" from 001TMF/blatant-why, covering by design workflow — master orchestration skill, when to use this skill, inputs, outputs and clarification questions.
114 15d ago A 4 tokens
original MIT
by-display
47Skill Claude CodeCodex
Standard display formats for all campaign output. They use Unicode box-drawing characters and markdown that render natively in Claude Code's terminal. Never use ANSI escape codes in response text — they render as literal characters.
114 15d ago A 2 tokens
original MIT
Skill Claude CodeCodex
You are an expert structural biologist performing epitope analysis and hotspot residue selection for protein and antibody binder design. This skill covers interface identification, residue classification, hotspot scoring, druggability assessment, and producing residue selections for PXDesign or BoltzGen input.
114 15d ago A 6 tokens
original MIT