Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Team-yPark/skills --skill protein-structure-predictiongit clone --depth 1 https://github.com/Team-yPark/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/team-ypark/skills/protein-structure-prediction)<a href="https://agentmods.dev/skills/team-ypark/skills/protein-structure-prediction"><img src="https://agentmods.dev/badge/skills/team-ypark/skills/protein-structure-prediction/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/team-ypark/skills/protein-structure-prediction"><img src="https://agentmods.dev/badge/skills/team-ypark/skills/protein-structure-prediction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00155 | $0.01517 |
| Opus 5 | $0.00077 | $0.00758 |
| Sonnet 5 | $0.00031 | $0.00303 |
| Haiku 4.5 | $0.00015 | $0.00152 |
Grade B, and why
protein-structure-prediction scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST --data "<AA_SEQUENCE>" https://api.esmatlas.com/foldSequence/v1/pdb/ > pred.pdb Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST --data "<AA_SEQUENCE>" https://api.esmatlas.com/foldSequence/v1/pdb/ > pred.pdb How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protein Structure Prediction from Sequence
Turn an amino-acid sequence into a usable 3D structure: pick a model for the job,
obtain the structure (look it up before predicting), and interpret it through its
confidence scores. Background biochemistry and model facts live in the knowledge
base (be-domain-expert, biochemistry/ and bioinformatics/protein-structure/);
this skill is the practical how-to.
First: does the structure already exist?
Predicting is often unnecessary. Check, in order:
- PDB (rcsb.org) — an experimental structure (X-ray/cryo-EM/NMR) beats a prediction; search by sequence (BLAST) or ID.
- AlphaFold DB (alphafold.ebi.ac.uk) — 200M+ precomputed AF2 models, keyed by
UniProt accession. If your protein is there, download it (
.pdb+ PAE JSON) instead of re-running. - ESM Metagenomic Atlas — for metagenomic/orphan sequences.
Only predict when there is no suitable existing model, the sequence is novel (variant, designed, chimera), or you need a complex/ligand state not in a DB.
Choose the model
| Situation | Use | Why |
|---|---|---|
| Single protein, has homologs (deep MSA) | ColabFold / AlphaFold2 | highest single-chain accuracy |
| Protein complex (multi-chain), or with DNA/RNA/ligand/ion | AlphaFold3 or Boltz | model the whole assembly, not lone chains |
| Open/local complex + ligand, at scale | Boltz (Boltz-1/2) | open-source AF3-class; runs locally |
| Many sequences / need speed / orphan or designed protein | ESMFold | no MSA, ~10× faster, better on shallow-MSA |
| Just a quick single fold, no setup | ESMFold API or ColabFold notebook | zero install |
Decision rationale (MSA depth, complexes, speed/accuracy trade-offs) is in the
knowledge base — consult be-domain-expert if unsure which applies.
Get a structure
Prefer a hosted notebook/API for one-offs; local install for batches.
ColabFold (AF2, MSA via MMseqs2) — the standard accessible AF2:
# local: github.com/sokrypton/ColabFold (needs GPU + colabfold_batch)
colabfold_batch input.fasta out_dir/ # FASTA: one record per chain
# complex: put chains in one record separated by ':' (SEQ1:SEQ2)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 113 lines · 155 tokens per session scan B beeb1891b5f8
protein-structure-prediction is a skill published in the GitHub repository Team-yPark/skills (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 155 tokens to every session and 1,517 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…