all publishers

001TMF

@001tmf source repo

23 published skills

  1. ▌
    Boltzgen · 001tmf bundle
    BoltzGen — Antibody / Nanobody / Binder Design
    120 repo stars
  2. ▌
    Protenix · 001tmf bundle
    Protenix — Structure Prediction Skill
    120 repo stars
  3. ▌
    Pxdesign · 001tmf bundle
    PXDesign — De Novo Protein Binder Design
    120 repo stars
  4. ▌
    By Display · 001tmf bundle
    BY Display Patterns
    120 repo stars
  5. ▌
    By Scoring · 001tmf bundle
    BY Scoring Skill
    120 repo stars
  6. ▌
    By Session · 001tmf bundle
    BY Session Skill
    120 repo stars
  7. ▌
    By Database · 001tmf bundle
    Skill: by-database
    120 repo stars
  8. ▌
    By Research · 001tmf bundle
    BY Research Skill
    120 repo stars
  9. ▌
    By Knowledge · 001tmf bundle
    BY Knowledge Graph
    120 repo stars
  10. ▌
    By Screening · 001tmf bundle
    BY Screening Skill
    120 repo stars
  11. ▌
    By Deploy Compute · 001tmf bundle
    BY Deploy Compute Skill
    120 repo stars
  12. ▌
    By Design Workflow · 001tmf bundle
    BY Design Workflow — Master Orchestration Skill
    120 repo stars
  13. ▌
    By Campaign Manager · 001tmf bundle
    BY Campaign Manager
    120 repo stars
  14. ▌
    By Causal Reasoning · 001tmf bundle
    BY Causal Reasoning Skill
    120 repo stars
  15. ▌
    By Epitope Analysis · 001tmf bundle
    Skill: BY Epitope Analysis
    120 repo stars
  16. ▌
    By Failure Diagnosis · 001tmf bundle
    BY Failure Diagnosis Skill
    120 repo stars
  17. ▌
    By Hypothesis Debate · 001tmf bundle
    BY Hypothesis-Debate Skill
    120 repo stars
  18. ▌
    By Campaign Optimizer · 001tmf bundle
    BY Campaign Optimizer (Active Learning)
    120 repo stars
  19. ▌
    By Experiment Results · 001tmf bundle
    BY Experiment Results Skill
    120 repo stars
  20. ▌
    Pinakes Verifiable Retrieval · 001tmf bundle
    Retrieve reproducible, complete, verifiable records from 26 public biomedical sources (PDB, UniProt, NCBI Protein/Virus/Datasets, ClinVar, Ensembl, gnomAD, PubChem, AlphaFold, ClinicalTrials, openFDA, Open Targets, Reactome, GTEx, GWAS Catalog, and more — run `catalog` for the full list) via Pinakes — the same 8 verbs over an MCP server (pinakes_<verb> tools) or the identical pinakes CLI. Use when an agent must pull biomedical data that has to be reproducible, deterministic, byte-identical, complete-or-fail, or independently verifiable; when a record count, cited fact, or dataset must carry provenance a reviewer can re-derive offline; when pinning a content-addressed snapshot; reading a manifest's completeness or reproducible flag; verifying before citing; or self-correcting a rejected filter. Teaches the judgement the tool schemas do not: pin-or-no-determinism, complete vs best_effort, and verify-before-cite.
    120 repo stars
  21. ▌
    Render Protein · 001tmf bundle
    Render and display protein structures with ProteinView FullHD pixel graphics. Use whenever a user asks to show, view, visualize, inspect, or render a Protein Data Bank/PDB identifier (for example, "show me 1UBQ PDB protein") or a local .pdb/.cif/.mmcif structure file.
    120 repo stars
  22. ▌
    Radio · 001tmf
    Create and operate Radio rooms of named cross-harness @personas. Use when the user asks to delegate work to Claude Code, Codex, OMP, Pi, or DeepSeek agents; arrange who may communicate; send compact requests; or wait for correlated replies.
    120 repo stars
  23. ▌
    Meta Harness · 001tmf bundle
    Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method nativ
    120 repo stars