Tencent tFold Antigen Antibody Complex Structure Prediction Model
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @tencent-adm/tfold-collection-skill.
About this skill
Problem
Nextflow omics apps such as tFold Collection (Nextflow) usually require checking login state, project configuration, sub-app AppId, Nextflow version, and import name before submission. Manual command assembly can accidentally use the collection AppId as a runnable app, or import a duplicate name and fail.
How It Works
- Scoped collection: only runs the 4 sub-apps in
tFold Collection (Nextflow), includingtFold_ab_predict,tFold_ag_predict,tFold_ag_predict_icf, andtFold_tcr_predict. - Preflight checks: verifies
omicsCLI,whoami, andconfig show; C-end users also get quota checks before the first submission and before each run. - Execution guardrails: matches a target from the hardcoded sub-app list, blocks running the collection directly, performs duplicate-name checks, and asks for confirmation before
omics run. - Failure handling: gives explicit guidance for
DUPLICATE_APP_NAME, missingnf-version, and authentication failures, and reminds users of theoutdirresult path.
Boundaries
This skill targets public app runs on the Tencent Health Omics Platform. It does not cover other platforms, project-owned apps, or out-of-scope direct CLI usage. Local file inputs must be uploaded to the user's bound COS bucket first.
Use Cases
- Select a tFold antibody, antigen, or TCR sub-app on Tencent Health Omics and submit a Nextflow structure prediction job.
- Verify login, project, and COS bucket settings before submission while avoiding collection AppId misuse or duplicate imports.
- Check remaining trial days and today's run quota before C-end users submit tFold jobs to prevent quota exhaustion.
- Upload AI-generated or local FASTA files to the bound COS bucket first, then use them as inputs for tFold sub-apps.
Best For
- Structural biology engineers: need to submit tFold antibody, antigen, ICF, or TCR prediction jobs to the omics platform accurately.
- B-end Tencent Health Omics project members: need to verify project, environment, and COS bucket before running public Nextflow apps.
- C-end trial users: want to run tFold predictions within trial quota and understand remaining days and daily runs.
- Platform ops or app owners: need to manage submissions using fixed sub-app lists, duplicate checks, and run confirmation.
Related Skills
Aggregates monthly broker top picks via the Wind Alice Agent to analyze consensus heat, industry themes, and stock-specific recommendation logic.
Analyzes call content for fraud scripts, assesses risk, and generates a structured Anti-Fraud Guardian report.
Generates a self-contained HTML daily A-share snapshot from Tencent market data and authoritative news, focusing on objective recap rather than forecasts.
Turns competing patent claims into structured analysis: element decomposition, scope interpretation, equivalence prediction, and prosecution history limitations.