plugins/tooluniverse/skills/tooluniverse-plant-genomics/SKILL.md
Plant genomics and biology research — PlantReactome pathways, Ensembl Plants gene structure, POWO species taxonomy, UniProt annotation, KEGG plant pathways. Handles polyploidy (wheat hexaploidy etc.) and homeologous gene copies. Use for crop-gene annotation, plant secondary metabolism queries, and plant-disease/stress-response biology.
npx skillsauth add mims-harvard/tooluniverse tooluniverse-plant-genomicsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Pipeline for investigating plant genes, metabolic pathways, species taxonomy, and comparative plant biology using ToolUniverse tools.
Plant genomes are large (wheat is ~17 Gb, vs. 3 Gb for human) and often polyploid — wheat is hexaploid (AABBDD), meaning there are three homeologous copies of most genes. When comparing plant genes to Arabidopsis, always account for whole-genome duplications: a single Arabidopsis gene may have 2–4 paralogs in a crop species, all potentially with diverged functions. Gene families are massively expanded in plants relative to animals (e.g., receptor-like kinases, cytochrome P450s, transcription factors) — a BLAST hit does not mean functional equivalence. Arabidopsis thaliana is the primary model, but its small genome and rapid life cycle mean some features (wood formation, nitrogen fixation symbiosis, C4 photosynthesis) are absent and must be studied in other species.
LOOK UP DON'T GUESS: Do not assume gene function by sequence similarity alone in polyploid species; look up functional validation evidence via UniProt (reviewed entries) or PlantReactome. Do not assume KEGG organism codes — use the table or query kegg_search_pathway with the species name to confirm availability.
Key principles:
Not this skill: For general pathway analysis (human/mouse), use tooluniverse-systems-biology. For phylogenetics, use tooluniverse-phylogenetics.
| Tool | Use For |
|------|---------|
| PlantReactome_search_pathways | Search plant-specific pathways by keyword |
| PlantReactome_get_pathway | Get pathway details (genes, reactions, species) |
| PlantReactome_list_species | List all species covered by PlantReactome |
| POWO_search_plants | Search Plants of the World Online (taxonomy, distribution) |
| USDA_plants_get_profile | US plant profile by PLANTS symbol (e.g., symbol="ABBA") — taxonomy, growth habit, duration, native status; use for North American flora |
| USDA_plants_get_characteristics | Morphology/physiology trait records for a PLANTS symbol — use when a question needs growth-form or physiological traits |
| ensembl_lookup_gene | Gene lookup — use with plant species (e.g., species="arabidopsis_thaliana") |
| kegg_search_pathway | Search KEGG pathways (use plant organism codes: ath, osa, zma) |
| KEGG_get_pathway_genes | Get genes in a plant pathway (e.g., pathway_id="ath00941" for flavonoid in Arabidopsis) |
| UniProt_search | Search plant protein sequences (add taxonomy_id:3702 for Arabidopsis) |
| UniProt_get_function_by_accession | Get protein function annotation |
| PubMed_search_articles | Plant biology literature |
| EnsemblCompara_get_orthologues | Cross-species plant gene comparison |
Phase 0: Species & Gene Identification
Species name → POWO taxonomy; Gene symbol → Ensembl/UniProt IDs
|
Phase 1: Gene Function & Annotation
UniProt function, Ensembl annotation, InterPro domains
|
Phase 2: Pathway Analysis
PlantReactome → plant-specific pathways; KEGG → metabolism
|
Phase 3: Cross-Species Comparison
Ensembl Compara → orthologs in other plant species
|
Phase 4: Literature & Report
PubMed → published studies; synthesis
# Look up an Arabidopsis gene
ensembl_lookup_gene(gene_symbol="CHS", species="arabidopsis_thaliana")
# Get protein function
UniProt_search(query="CHS AND taxonomy_id:3702 AND reviewed:true")
Key plant-specific KEGG pathways:
| Pathway | KEGG ID (Arabidopsis) | Biological Significance | |---------|----------------------|------------------------| | Photosynthesis | ath00195 | Light reactions, electron transport | | Carbon fixation (Calvin cycle) | ath00710 | CO2 → sugar | | Flavonoid biosynthesis | ath00941 | UV protection, pigmentation, defense | | Carotenoid biosynthesis | ath00906 | Photoprotection, vitamin A precursors | | Auxin signaling | ath04075 | Growth, tropisms | | Brassinosteroid signaling | ath04712 | Cell elongation, stress response | | Circadian rhythm (plant) | ath04712 | Photoperiod, flowering time | | Terpenoid backbone | ath00900 | Secondary metabolite precursors | | Starch/sucrose metabolism | ath00500 | Carbon partitioning | | Nitrogen metabolism | ath00910 | Nitrogen assimilation |
# Search PlantReactome for flavonoid pathway
PlantReactome_search_pathways(query="flavonoid")
# Get genes in Arabidopsis flavonoid biosynthesis
KEGG_get_pathway_genes(pathway_id="ath00941")
KEGG organism codes for major crops:
| Species | Code | Common Name | |---------|------|-------------| | Arabidopsis thaliana | ath | Thale cress (model plant) | | Oryza sativa | osa | Rice | | Zea mays | zma | Maize/corn | | Triticum aestivum | tae | Wheat | | Glycine max | gmx | Soybean | | Solanum lycopersicum | sly | Tomato | | Nicotiana tabacum | nta | Tobacco | | Medicago truncatula | mtr | Barrel medic (legume model) |
Evidence grading: T1 = mutant phenotype confirms function; T2 = expression/localization data; T3 = ortholog has validated function in model species; T4 = computational annotation only (domain/GO term). Prioritize T1/T2 evidence; treat T3/T4 as hypotheses requiring further validation.
tools
Generate the success criteria for a task or question, then review work against them. Given a task, goal, or open-ended question, decompose it into scenarios, evaluation perspectives, and fine-grained weighted YES/NO criteria using the Recursive Expansion Tree (RET) method; if work is supplied, score it criterion-by-criterion and surface what is missing or could be better. Use when asked to self-review or check your own work, judge whether a task is done well or completely, build a definition-of-done or completeness checklist, create an evaluation rubric or grading criteria, score or grade answers to a question, set up an LLM-as-judge rubric, or when the user mentions self-review, completeness check, success criteria, evaluation criteria, scoring rubric, Qworld, or the RET algorithm.
tools
Find the real protein target(s) of a peptide from its sequence — peptide target deorphanization / off-target identification, for ANY target class (GPCR, ion channel, protease, cytokine/growth-factor receptor, enzyme, integrin), not only GPCRs. Use when a peptide has a phenotype but does not bind its hypothesized target, when a peptide binds a target in one species or assay but not another, or to screen candidate targets for an orphan peptide. A target-class router steers a multi-route keyless pipeline (PROSITE/ELM motif, BLAST homology, HGNC/InterPro/GPCRdb/GtoPdb target-family enumeration, OpenTargets phenotype anchor, EnsemblCompara/Alliance cross-species reconciliation) plus optional NVIDIA-NIM co-folding (Boltz2, AlphaFold2-Multimer, OpenFold3) for structural confirmation.
tools
Install or update ToolUniverse in Claude Science — create the conda env, install the tooluniverse pip package, and (re)build the tooluniverse-research skill by fetching the current workflow library from GitHub. Use for first-time setup, upgrading the ToolUniverse version, refreshing the bundled workflows after an upstream release, or reinstalling on a new machine.
tools
Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on OpenAI Codex. ALWAYS consult this skill for any of those — don't answer from memory, because the exact marketplace name (mims-harvard/ToolUniverse), the "codex plugin marketplace add" then "codex plugin add -m tooluniverse" flow, Codex's startup auto-upgrade behavior, the uvx tooluniverse MCP server, and the API-key env vars are easy to get wrong. Use it whenever someone wants to get ToolUniverse (or "the 1000+ scientific tools" / "the harvard tools") working on Codex, says the Codex plugin or its tools/skills won't load, hits a uvx or MCP-server startup error, asks how Codex updates it, wants to pin or remove it, or finds it running an old tool version — even if they never say the word "plugin". Not for the Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills.