← all publishers

001TMF

@001tmf source repo

Report this profile Claim this profile

• 23 skills
• 0 followers
• 6 hours ago last updated

1. ▌
   Boltzgen · 001tmf bundle

   BoltzGen — Antibody / Nanobody / Binder Design
   0
   installs
2. ▌
   Protenix · 001tmf bundle

   Protenix — Structure Prediction Skill
   0
   installs
3. ▌
   Pxdesign · 001tmf bundle

   PXDesign — De Novo Protein Binder Design
   0
   installs
4. ▌
   By Display · 001tmf bundle

   BY Display Patterns
   0
   installs
5. ▌
   By Scoring · 001tmf bundle

   BY Scoring Skill
   0
   installs
6. ▌
   By Session · 001tmf bundle

   BY Session Skill
   0
   installs
7. ▌
   By Database · 001tmf bundle

   Skill: by-database
   0
   installs
8. ▌
   By Research · 001tmf bundle

   BY Research Skill
   0
   installs
9. ▌
   By Knowledge · 001tmf bundle

   BY Knowledge Graph
   0
   installs
10. ▌
    By Screening · 001tmf bundle

    BY Screening Skill
    0
    installs
11. ▌
    By Deploy Compute · 001tmf bundle

    BY Deploy Compute Skill
    0
    installs
12. ▌
    By Design Workflow · 001tmf bundle

    BY Design Workflow — Master Orchestration Skill
    0
    installs
13. ▌
    By Campaign Manager · 001tmf bundle

    BY Campaign Manager
    0
    installs
14. ▌
    By Causal Reasoning · 001tmf bundle

    BY Causal Reasoning Skill
    0
    installs
15. ▌
    By Epitope Analysis · 001tmf bundle

    Skill: BY Epitope Analysis
    0
    installs
16. ▌
    By Failure Diagnosis · 001tmf bundle

    BY Failure Diagnosis Skill
    0
    installs
17. ▌
    By Hypothesis Debate · 001tmf bundle

    BY Hypothesis-Debate Skill
    0
    installs
18. ▌
    By Campaign Optimizer · 001tmf bundle

    BY Campaign Optimizer (Active Learning)
    0
    installs
19. ▌
    By Experiment Results · 001tmf bundle

    BY Experiment Results Skill
    0
    installs
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.
    0
    installs
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.
    0
    installs
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.
    0
    installs
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
    2
    installs