Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.
Skill
Original text · EnglishSet up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.
https://github.com/anthropics/knowledge-work-plugins/blob/main/bio-research/skills/start/SKILL.md
npx skills add anthropics/knowledge-work-plugins --skill startRepublished in full under its license, with attribution. The source is authoritative.
name: start
description: Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../../CONNECTORS.md).
You are helping a biological researcher get oriented with the bio-research plugin. Walk through the following steps in order.
Display this welcome message:
Bio-Research Plugin
Your AI-powered research assistant for the life sciences. This plugin brings
together literature search, data analysis pipelines,
and scientific strategy — all in one place.
Test which MCP servers are connected by listing available tools. Group the results:
Literature & Data Sources:
Drug Discovery & Clinical:
Visualization & AI:
Report which servers are connected and which are not yet set up.
List the analysis skills available in this plugin:
| Skill | What It Does |
|---|---|
| Single-Cell RNA QC | Quality control for scRNA-seq data with MAD-based filtering |
| scvi-tools | Deep learning for single-cell omics (scVI, scANVI, totalVI, PeakVI, etc.) |
| Nextflow Pipelines | Run nf-core pipelines (RNA-seq, WGS/WES, ATAC-seq) |
| Instrument Data Converter | Convert lab instrument output to Allotrope ASM format |
| Scientific Problem Selection | Systematic framework for choosing research problems |
Mention that two additional MCP servers are available as separate installations:
Install: Download txg-node.mcpb from https://github.com/10XGenomics/txg-mcp/releases
Install: Download tooluniverse.mcpb from https://github.com/mims-harvard/ToolUniverse/releases
These require downloading binary files and are optional.
Ask the researcher what they're working on today. Suggest starting points based on common workflows:
Wait for the user's response and guide them to the appropriate tools and skills.
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.
Sourcegithub.com/wshobson/agents/blob/main/plugins/data-engineering/skills/airflow-dag-patterns/SKILL.md
Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after a training run produces a checkpoint, when deciding whether a tuned model ships, or when a promoted model needs re-gating against updated goldens.
Sourcegithub.com/wshobson/agents/blob/main/plugins/llm-finetuning/skills/checkpoint-promotion/SKILL.md
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
Sourcegithub.com/wshobson/agents/blob/main/plugins/data-engineering/skills/data-quality-frameworks/SKILL.md
Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying chat templates, configuring sequence packing, generating synthetic training data, or writing a dataset card before a run.
Sourcegithub.com/wshobson/agents/blob/main/plugins/llm-finetuning/skills/dataset-curation/SKILL.md
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.
Sourcegithub.com/wshobson/agents/blob/main/plugins/data-engineering/skills/dbt-transformation-patterns/SKILL.md
Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines. Use when starting a fine-tuning effort, when converting traces into an eval set, or when calibrating a judge against human labels.
Sourcegithub.com/wshobson/agents/blob/main/plugins/llm-finetuning/skills/eval-harness-first/SKILL.md