Alterlab Latchbio
Authors bioinformatics pipelines with the Latch SDK — @workflow/@task decorators, LatchFile/LatchDir I/O, CPU/GPU task sizing, the Latch Registry, and Nextflow/Snakemake wrapping — and validates them with no account, type-checking the decorators and workflow graph at import, running task functions locally on plain files, and inspecting the no-code UI metadata offline. Registering and running the workflow on LatchBio is an optional step with the user's own latch login and Docker. Use when developing a Latch SDK workflow, sizing task resources, checking a workflow before latch register, working
Install
/plugin marketplace add AlterLab-IEU/AlterLab-Academic-SkillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-latchbiogit clone --depth 1 https://github.com/AlterLab-IEU/AlterLab-Academic-Skills.git /tmp/AlterLab-Academic-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/AlterLab-Academic-Skills/skills/lab-integrations/alterlab-latchbio ~/.claude/skills/alterlab-latchbioPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# LatchBio Integration
## Overview
Latch is a Python framework for building and deploying bioinformatics workflows as serverless pipelines. Built on Flyte, create workflows with @workflow/@task decorators, manage cloud data with LatchFile/LatchDir, configure resources, and integrate Nextflow/Snakemake pipelines. Authoring and validating the workflow needs no account; only `latch register` and running it on the platform use the user's login.
## Keyless Path (default — no LatchBio account)
1. **Write the workflow** against the real SDK (`uv run --with latch python ...`) and confirm decorator and API names with `inspect` rather than memory. Verified in latch 2.77.2 (2026-10-22): resource decorators are `small_task`/`medium_task`/`large_task`, `small_gpu_task` (7 CPU, 30Gi, 1 GPU) / `large_gpu_task` (63 CPU, 245Gi, 1 GPU), `v100_x{1,4,8}_task`, `g6e_*_task`; `custom_task(cpu, memory, *, storage_gib=500, timeout=0)`.
2. **Let import type-check the graph.** Decorating and composing the workflow runs Latch's/Flyte's own validation with no login. Verified offline, these fail at import (so they are caught keyless):
- `@custom_task(cpu=8, memory=32, gpu=1)` -> `TypeError: task() got an unexpected keyword argument 'gpu'` (custom_task has no `gpu`/`gpu_type`; a GPU comes from a GPU decorator).
- a `@workflow` whose body calls a task but whose signature has no return annotation -> `ValueError` while building the interface.Details
- Skill name
alterlab-latchbio- Repository
- AlterLab-IEU/AlterLab-Academic-Skills
- Path
skills/lab-integrations/alterlab-latchbio/SKILL.md- License
- MIT
- Repo updated
- 11 November 2026
- Listed in
- BehiSecc/awesome-claude-skills
FAQ
What does the Alterlab Latchbio skill do?
Authors bioinformatics pipelines with the Latch SDK — @workflow/@task decorators, LatchFile/LatchDir I/O, CPU/GPU task sizing, the Latch Registry, and Nextflow/Snakemake wrapping — and validates them with no account, type-checking the decorators and workflow graph at import, running task functions locally on plain files, and inspecting the no-code UI metadata offline. Registering and running the workflow on LatchBio is an optional step with the user's own latch login and Docker. Use when developing a Latch SDK workflow, sizing task resources, checking a workflow before latch register, working
How do I install the Alterlab Latchbio skill?
Claude Code plugin: /plugin marketplace add AlterLab-IEU/AlterLab-Academic-Skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Alterlab Latchbio popular?
It lives in AlterLab-IEU/AlterLab-Academic-Skills, which has 87 GitHub stars and 18 forks, and is included in 1 curated skill list.
Related skills
Alterlab Abm Mesa
87AlterLab-IEU/AlterLab-Academic-Skills
Builds agent-based models of social systems with Mesa 3 — the current AgentSet API (model.agents.shuffle_do('step'), auto-assigned unique_id, mandatory super().__init__(rng=...)), cell spaces (mesa.discrete_space OrthogonalMooreGrid / classic mesa.space grids), the DataCollector, batch_run parameter sweeps, and SolaraViz — for emergence, segregation, diffusion, opinion dynamics, and cooperation models. It uses the Mesa 3.x API (the old mesa.time schedulers like RandomActivation are removed) and treats the model as a generative theory to be validated, not just run. Use when the request mentions
Alterlab Academic Career
87AlterLab-IEU/AlterLab-Academic-Skills
Prepares academic career documents and professional-development materials for faculty and researchers. Use when drafting academic CVs, research statements, teaching philosophies, diversity statements, faculty-position cover letters, tenure dossiers, promotion narratives, academic portfolios, or mentorship statements, and when planning conference-networking strategy, building academic web presence, setting up ORCID profiles, or understanding impact metrics. Part of the AlterLab Academic Skills suite.
Alterlab Accreditation Aol
87AlterLab-IEU/AlterLab-Academic-Skills
Scaffolds program-level Assurance-of-Learning (AoL) documentation for AACSB (Standard 5 in the 2020 standards and the 2026 Global Standards) and ABET (Criterion 3 Student Outcomes, Criterion 4 Continuous Improvement) accreditation — program learning outcomes / competency goals, curriculum-to-outcome mapping matrices, direct- and indirect-assessment plans, rubric design, and closing-the-loop continuous-improvement narratives — and validates the structure of an outcome-mapping matrix with scripts/aol_matrix.py. Use when the user needs AACSB or ABET assurance-of-learning material, a program-learn
Alterlab Research Workflows
87AlterLab-IEU/AlterLab-Academic-Skills
Runs AlterLab's packaged multi-agent academic workflows — citation audit, peer-review panel of separate reviewers, claim stress-test, PRISMA dual-screening for systematic reviews, point-by-point rebuttal, grant mock panel, and literature map. In Claude Code they run as dynamic workflows (/alterlab-workflows:<name>) with separate agent contexts, adversarial re-checks, tallies computed in code, and an explicit complete/partial/blocked status; on claude.ai, the API, or anywhere without the Workflow runtime this skill runs the same stages as a staged playbook. Use when a research task needs many s
Alterlab Benchling
87AlterLab-IEU/AlterLab-Academic-Skills
Writes Benchling integration code against the official benchling-sdk — registry DNA/protein entities, inventory, ELN entries, workflow tasks, Benchling Apps, Data Warehouse SQL — and validates every create/update payload offline by building the SDK's typed models and serializing them, with no Benchling account; analyses Benchling CSV/warehouse exports locally. Running the code against a tenant is an optional step with the user's own API key or OAuth app. Use when scripting a Benchling registry import, inventory audit, ELN entry or workflow task, checking a Benchling payload or script before it
Alterlab Skill Finder
87AlterLab-IEU/AlterLab-Academic-Skills
The AlterLab front door and multi-agent launcher — routes a task to the right AlterLab skill(s) when the user invokes the suite without naming one, and for a multi-stage goal (or on the keyword 'alterflow', aliases 'alterresearch' / 'ultralab') it clarifies the goal with a few questions before anything runs, selects the skills the task needs, and runs a multi-agent workflow composing them (a packaged alterlab-workflows workflow, alterlab-research-pipeline, alterlab-ssci-orchestrator, or a bespoke plan via alterlab-workflow-orchestration). Triggers on 'use AlterLab skills', 'which AlterLab skil
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.