skills.rest
CultureBotAI
CultureBotAIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

deep-research-medium

Run a two-phase Edison literature workflow to extract organism growth evidence and recipe details for CultureMech media.

10|3|Updated Jan 28, 2026
Search Tags:#knowledge graph#entity extraction#literature mining#ontology grounding#microbial culture media#API-based research
One-click install
npx skills add https://github.com/CultureBotAI/CultureMech --skill deep-research-medium
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-research-medium
Source: https://github.com/CultureBotAI/CultureMech/tree/main/.claude/skills/deep-research-medium
Command: npx skills add https://github.com/CultureBotAI/CultureMech --skill deep-research-medium

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires edison-client, and includes scripts (resource) components.

What problem does it solve?

Reduces curator time spent manually searching literature to enrich a single CultureMech medium record with organism-specific recipes, culture conditions, identifiers, and citation metadata.

Core Features & Use Cases

  • Two-phase Edison deep research: runs a medium-level organism candidate search, then performs per-organism follow-ups to extract recipes and growth evidence from primary publications.
  • Curation-focused outputs: generates a single roll-up report containing proposed YAML changes ready for curator review rather than unstructured notes.
  • Safety guardrails for research spend: supports dry-run query rendering, detects existing research outputs to avoid accidental re-billing, and caps per-medium organism follow-ups by default.
  • Auditability and provenance: writes per-task meta, full response payloads, parsed citations, and artifact inventories so results can be re-checked without re-querying.

Quick Start

Run a two-phase deep research for the medium file and produce the curator hand-off report with: uv run --extra dev python -m scripts.deep_research_medium --input <slug-or-id-or-path> --dry-run

Frequently Asked Questions about deep-research-medium

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract microbial culture media recipes from research literature?▼

Microbial culture media recipes are extracted by running a two-phase Edison literature workflow that identifies candidate organisms and then extracts per-organism ingredients, culture conditions, and identifiers for proposed YAML updates.

How do I automate literature mining for organism-specific growth evidence?▼

Literature mining for organism-specific growth evidence is automated through a two-phase Edison deep research process, searching primary publications for candidate organisms and extracting recipes, conditions, and citation metadata.

Can I dry-run Edison literature queries to preview research spend?▼

Yes, Edison queries can be rendered in dry-run mode to preview research spend, and existing research outputs are detected to prevent accidental re-billing during literature mining tasks.

Does deep-research-medium require a normalized YAML file to process culture media?▼

Yes, deep-research-medium requires resolving the target medium to a normalized YAML file before extracting organism-specific ingredients, culture conditions, identifiers, and citation metadata.

What audit trails are generated when extracting culture media recipes from publications?▼

Audit trails include per-task meta files, full response payloads, parsed citations, and artifact inventories, ensuring literature mining results can be re-checked without re-querying.

What is the best way to curate organism-specific culture conditions from primary publications?▼

The best way to curate organism-specific culture conditions is generating a single roll-up report containing proposed YAML changes ready for curator review, rather than unstructured notes.

Related Skills

Explore More Education & Research Skills→
Dach-CoinDach-Coin
33

skd-compile

Compile 1C Data Composition Schema Template.xml from a compact JSON DSL.

Community
Advanced
CultureBotAICultureBotAI
10

match-kg-microbe

Align CHEBI-annotated ingredient sets to KG-Microbe medium nodes and populate kg_microbe_match.

Official
Intermediate
wsxwj123wsxwj123
7

literature-review

Search multiple databases and generate systematic literature reviews with verified citations.

Community
Advanced
daffy0208daffy0208
34

Knowledge Graph Builder

Design, implement, and maintain knowledge graphs for complex entity relationships.

Community
Advanced