Hypothesis Generation
spacering-net/codeg
Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.
Query the Reactome database (Analysis and Content Services).
Install Reactome Database
$ npx skills add google-deepmind/science-skills --skill reactome-database -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install google-deepmind/science-skills reactome-database --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/google-deepmind/science-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/reactome_database .claude/skills/reactome-database && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "reactome-database" agent skill from https://github.com/google-deepmind/science-skills/tree/main/skills/reactome_database into .claude/skills/reactome-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reactome-database", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/google-deepmind/science-skills/tree/main/skills/reactome_databaseType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add google-deepmind/science-skills --skill reactome-database -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install google-deepmind/science-skills reactome-database --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google-deepmind/science-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/reactome_database .agents/skills/reactome-database && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "reactome-database" agent skill from https://github.com/google-deepmind/science-skills/tree/main/skills/reactome_database into .agents/skills/reactome-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reactome-database", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add google-deepmind/science-skills --skill reactome-database -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install google-deepmind/science-skills reactome-database --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google-deepmind/science-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/reactome_database .cursor/skills/reactome-database && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "reactome-database" agent skill from https://github.com/google-deepmind/science-skills/tree/main/skills/reactome_database into .cursor/skills/reactome-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reactome-database", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/google-deepmind/science-skills.git --path skills/reactome_database--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add google-deepmind/science-skills --skill reactome-database -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install google-deepmind/science-skills reactome-database --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google-deepmind/science-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/reactome_database .gemini/skills/reactome-database && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "reactome-database" agent skill from https://github.com/google-deepmind/science-skills/tree/main/skills/reactome_database into .gemini/skills/reactome-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reactome-database", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install google-deepmind/science-skills reactome-databaseInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add google-deepmind/science-skills --skill reactome-database -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/google-deepmind/science-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/reactome_database .github/skills/reactome-database && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "reactome-database" agent skill from https://github.com/google-deepmind/science-skills/tree/main/skills/reactome_database into .github/skills/reactome-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reactome-database", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add google-deepmind/science-skills --skill reactome-database -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install google-deepmind/science-skills reactome-database --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google-deepmind/science-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/reactome_database .opencode/skills/reactome-database && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "reactome-database" agent skill from https://github.com/google-deepmind/science-skills/tree/main/skills/reactome_database into .opencode/skills/reactome-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reactome-database", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
reactome-database- GitHub stars
- 3.2k
- Used in
- 1 other repo
- Token cost
- ~2.8k tokens
- SKILL.md length
- 764 words
- Files
- 4 (incl. scripts, references)
- Skills in repo
- 40
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Query the Reactome database (Analysis and Content Services).
- Works in 12 steps: Database Info → Single Identifier Analysis → Batch Analysis (Enrichment) → …
- The user asks about pathway analysis
- SKILL.md covers Prerequisites, Overview, When to Use This Skill and Common Species IDs, plus 6 more sections
- Runs Python scripts from its folder; calls uv; reaches reactome.org
What it does
Reactome Database is an agent skill from google-deepmind/science-skills. Query the Reactome database (Analysis and Content Services). Use when the user asks about pathway analysis, gene list enrichment, retrieving results by token, finding unmapped or not-found identifiers, mapping identifiers, reaction participants (inputs, outputs), pathway hierarchy (including top-level pathways), diagram export, cross-reference mapping, or searching the knowledgebase.
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/api_reference.md` and `scripts/reactome_analysis.py`).
It sits in Research & Science. The repository describes itself as: GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other… The licence is Apache-2.0.
When your agent uses it
- The user asks about pathway analysis
- Gene list enrichment
- Retrieving results by token
- Finding unmapped
Example prompts
- “/reactome-database”
Requirements
- Python 3
Workflow steps
12 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 6883275. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
reactome.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Reactome Database loads about 2.8k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 764 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from google-deepmind/science-skills at commit 6883275, republished under its Apache-2.0 licence (© google-deepmind). 764 words, ~2,754 tokens.
Download SKILL.mdSave it as
.claude/skills/reactome-database/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- reactome-database
- description
- Query the Reactome database (Analysis and Content Services). Use when the user asks about pathway analysis, gene list enrichment, retrieving results by token, finding unmapped or not-found identifiers, mapping identifiers, reaction participants (inputs, outputs), pathway hierarchy (including top-level pathways), diagram export, cross-reference mapping, or searching the knowledgebase.
Reactome Analysis & Content Service
Prerequisites
uv: Read theuvskill and follow its Setup instructions to ensureuvis installed and on PATH.- User Notification: If .licenses/reactome_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://reactome.org/license and https://reactome.org/cite, then (2) create the file recording the notification text and timestamp.
Overview
Reactome is a free, open-source, curated pathway database. This skill wraps both
the Analysis Service (https://reactome.org/AnalysisService/) and the
Content Service (https://reactome.org/ContentService/) providing pathway
enrichment analysis, identifier mapping, reaction details, pathway hierarchy
navigation, diagram export, cross-reference mapping, and search.
When to Use This Skill
- Performing pathway enrichment (overrepresentation) analysis on gene/protein lists
- Retrieving analysis results using a token from previous enrichment
- Identifying which genes or proteins were not found in a pathway analysis
- Analyzing gene expression data against pathway annotations
- Mapping identifiers to Reactome entities across species
- Retrieving reaction participants (inputs, outputs, catalysts, regulators)
- Navigating pathway hierarchy and listing top-level pathways
- Finding which complexes or sets contain a protein
- Exporting pathway/reaction diagrams (PNG/SVG) with gene highlighting
- Cross-referencing identifiers across databases (UniProt, Ensembl, etc.)
- Searching the Reactome knowledgebase
- Downloading analysis reports (PDF, CSV, JSON)
- Comparing pathways across species
Common Species IDs
Reference list for common research organisms:
- Homo sapiens
- ID: 9606
- Mus musculus (Mouse)
- ID: 48892
- Rattus norvegicus (Rat)
- ID: 48895
Common Pathway IDs
Reference list for commonly used Reactome pathway stable IDs:
- Cell Cycle
- Stable ID: R-HSA-1640170
- Notes: Top-level pathway (broad)
- Cell Cycle, Mitotic
- Stable ID: R-HSA-69278
- Notes: Specific sub-pathway — use this for diagrams and drill-downs
- Immune System
- Stable ID: R-HSA-168256
- Notes: Top-level pathway
- Signal Transduction
- Stable ID: R-HSA-162582
- Notes: Top-level pathway
- Gene Expression
- Stable ID: R-HSA-74160
- Notes: Top-level pathway
- Programmed Cell Death
- Stable ID: R-HSA-5357801
- Notes: Top-level pathway
Important: When the user asks for a "Cell Cycle" diagram or analysis, prefer the specific Cell Cycle, Mitotic pathway (
R-HSA-69278) unless the user explicitly requests the top-level overview. The examples throughout this document useR-HSA-69278.
Core Rules
- Always use
--output: Every subcommand requires--output <file>to write results to a file. Never rely on stdout for large results. - Default species is Homo sapiens: Use
--speciesto override. - Tokens expire after 7 days: Store tokens from analysis results to retrieve them later without re-submitting data.
- Use
--fdrand--pvalueto filter: Enrichment results can be overwhelming. Filter with--fdr 0.05or--pvalue 0.01to focus on statistically significant pathways. - Identifier formats: Reactome auto-detects identifiers including gene symbols (TP53), UniProt (P04637), Ensembl (ENSG00000141510), ChEBI, OMIM, EntrezGene, and many more.
- Handle large outputs: For commands that return large data (like
species-comparison), use the--summaryflag to truncate lists and avoid exceeding workspace file size limits (1MB). - Notification: If this skill is used, ensure this is mentioned in the output.
Show full SKILL.md (299 more words)Show less
Tool Execution
The CLI tool is at scripts/reactome_analysis.py. Run with uv:
uv run scripts/reactome_analysis.py <command> [options] --output /tmp/out.jsonTo list all available subcommands and flags, run:
uv run scripts/reactome_analysis.py --helpUse --help to verify available subcommands or flags before executing an
unfamiliar command.
Feature Domains
1. Database Info
uv run scripts/reactome_analysis.py db-version --output /tmp/version.json
uv run scripts/reactome_analysis.py db-name --output /tmp/name.json2. Single Identifier Analysis
uv run scripts/reactome_analysis.py identifier --id TP53 --output /tmp/tp53.json
uv run scripts/reactome_analysis.py identifier-projection --id TP53 --output /tmp/tp53_proj.json3. Batch Analysis (Enrichment)
Submit a list of identifiers for overrepresentation or expression analysis:
uv run scripts/reactome_analysis.py analyze --data "TP53,BRCA1,EGFR" --output /tmp/enrich.json
uv run scripts/reactome_analysis.py analyze --file genes.txt --output /tmp/enrich.json
uv run scripts/reactome_analysis.py analyze-projection --data "TP53,BRCA1" --output /tmp/proj.json
uv run scripts/reactome_analysis.py analyze --data "TP53,BRCA1" --fdr 0.05 --output /tmp/sig.jsonCommon options: --page-size (alias --limit), --page (alias --offset),
--sort-by, --order, --resource, --species, --fdr, --pvalue.
4. Token-Based Result Retrieval
uv run scripts/reactome_analysis.py token-result --token TOKEN --output /tmp/result.json
uv run scripts/reactome_analysis.py token-not-found --token TOKEN --output /tmp/notfound.json
uv run scripts/reactome_analysis.py token-resources --token TOKEN --output /tmp/resources.json
uv run scripts/reactome_analysis.py token-found-entities --token TOKEN --pathway R-HSA-69278 --output /tmp/found.json
uv run scripts/reactome_analysis.py token-filter-species --token TOKEN --species-filter 9606 --output /tmp/filtered.json
uv run scripts/reactome_analysis.py token-reactions-pathway --token TOKEN --pathway R-HSA-69278 --output /tmp/rxns.json5. Download Results
uv run scripts/reactome_analysis.py download-result --token TOKEN --output /tmp/full.json
uv run scripts/reactome_analysis.py download-pathways --token TOKEN --output /tmp/pathways.csv
uv run scripts/reactome_analysis.py download-found --token TOKEN --output /tmp/found.csv
uv run scripts/reactome_analysis.py download-not-found --token TOKEN --output /tmp/notfound.csv6. Identifier Mapping
uv run scripts/reactome_analysis.py mapping --data "TP53,BRCA1" --output /tmp/mapped.json
uv run scripts/reactome_analysis.py mapping-projection --data "TP53" --output /tmp/mapped_proj.json7. Reaction Participants & Mechanism of Action
Retrieve the molecular participants of a reaction (inputs, outputs, catalysts):
uv run scripts/reactome_analysis.py participants --id R-HSA-6804194 --output /tmp/participants.json
uv run scripts/reactome_analysis.py participating-entities --id R-HSA-6804194 --output /tmp/entities.json8. Complex & Set Membership
Find which complexes or sets contain a given entity:
uv run scripts/reactome_analysis.py component-of --id R-HSA-69488 --output /tmp/complexes.json9. Pathway Hierarchy Navigation
Move up (ancestors) or down (contained events) the pathway hierarchy:
uv run scripts/reactome_analysis.py event-ancestors --id R-HSA-69278 --output /tmp/ancestors.json
uv run scripts/reactome_analysis.py contained-events --id R-HSA-69278 --output /tmp/steps.json
uv run scripts/reactome_analysis.py top-pathways --output /tmp/top.json
uv run scripts/reactome_analysis.py low-pathways --id R-HSA-69488 --output /tmp/low.json10. Diagram Export
Export pathway or reaction diagrams as PNG/SVG, with optional gene highlighting:
uv run scripts/reactome_analysis.py diagram --id R-HSA-69278 --output /tmp/diagram.png
uv run scripts/reactome_analysis.py diagram --id R-HSA-69278 --highlight TP53 --output /tmp/highlighted.png
uv run scripts/reactome_analysis.py diagram --id R-HSA-69278 --format svg --output /tmp/diagram.svg
uv run scripts/reactome_analysis.py reaction-diagram --id R-HSA-6804194 --output /tmp/rxn.png11. Cross-Reference Mapping
Resolve identifiers to Reactome internal IDs and cross-references:
uv run scripts/reactome_analysis.py xref-mapping --id TP53 --output /tmp/xref.json
uv run scripts/reactome_analysis.py xref-mapping-batch --data "TP53,BRCA1" --output /tmp/xrefs.json12. Search
uv run scripts/reactome_analysis.py search --query "TP53 apoptosis" --output /tmp/results.json13. Query Entry by ID
uv run scripts/reactome_analysis.py query --id R-HSA-69278 --output /tmp/entry.json14. Report & Species Comparison
uv run scripts/reactome_analysis.py report --token TOKEN --output /tmp/report.pdf
uv run scripts/reactome_analysis.py species-comparison --species-id 48892 --output /tmp/species.json
# Use --summary to truncate large output and avoid workspace file size limits
uv run scripts/reactome_analysis.py species-comparison --species-id 48892 --summary --output /tmp/species.jsonRecipe: Interpreting Gene Set Enrichment
A step-by-step workflow for interpreting gene set enrichment results:
Submit gene list with projection to human pathways:
bash uv run scripts/reactome_analysis.py analyze-projection \ --data "TP53,BRCA1,EGFR,MYC,PTEN" --fdr 0.05 --output /tmp/enrichment.jsonInspect top pathways — examine
pathwaysFound, top pathway names, p-values, and FDR values in the output.Drill into a pathway — get its sub-events and reaction details:
bash uv run scripts/reactome_analysis.py contained-events --id R-HSA-69278 --output /tmp/steps.json uv run scripts/reactome_analysis.py participants --id <reaction_id> --output /tmp/parts.jsonVisualise — export a diagram with your genes highlighted:
bash uv run scripts/reactome_analysis.py diagram --id R-HSA-69278 \ --highlight "TP53,BRCA1" --output /tmp/diagram.pngCheck hierarchy — navigate up to see broader biological context:
bash uv run scripts/reactome_analysis.py event-ancestors --id R-HSA-69278 --output /tmp/ancestors.jsonCross-reference — map identifiers to other databases:
bash uv run scripts/reactome_analysis.py xref-mapping --id TP53 --output /tmp/xrefs.json
Reference
For detailed API endpoint documentation, see references/api_reference.md.
© google-deepmind, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (scripts, references) in skills/reactome_database of google-deepmind/science-skills.
- SKILL.md
- references/api_reference.md
- references/citation.bib
- scripts/reactome_analysis.py
Open the folder on GitHubat commit 6883275
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in google-deepmind/science-skills, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Reactome Database next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Reactome Database this skillgoogle-deepmind/science-skills | 3.2k | 1 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Hypothesis Generationspacering-net/codeg | 3.8k | 15 repos | ~3.6k | Automated safety check: Notes | MIT | |
| GitHub Deep Researchbytedance/deer-flow | 83k | 5 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Nature Paper CardYuan1z0825/nature-skills | 46k | 2 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Read arXiv Paperkarpathy/nanochat | 58k | 2 repos | ~494 | Automated safety check: Pass | MIT | |
| Content Research Writerweapp-tailwindcss/weapp-tailwindcss | 1.9k | 25 repos | ~3.5k | Automated safety check: Pass | MIT |
Similar skills
GitHub Deep Research
bytedance/deer-flow
Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.
Nature Paper Card
Yuan1z0825/nature-skills
Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.
Read arXiv Paper
karpathy/nanochat
Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.
Content Research Writer
weapp-tailwindcss/weapp-tailwindcss
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.
Peer Review
spacering-net/codeg
Structured manuscript/grant review with checklist-based evaluation.
More from google-deepmind/science-skills
All 40 skills in this repoAlphafold Database Fetch And Analyze
google-deepmind/science-skills
Retrieve and analyze AlphaFold predicted structures for a protein.
Alphagenome Single Variant Analysis
google-deepmind/science-skills
Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API.
Chembl Database
google-deepmind/science-skills
Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures.
Clinical Trials Database
google-deepmind/science-skills
Query ClinicalTrials.gov via APIv2. An agent skill from google-deepmind/science-skills.
Clinvar Database
google-deepmind/science-skills
A skill your agent uses when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding "hard positive" benchmark controls…
Dbsnp Database
google-deepmind/science-skills
A skill your agent uses when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database.
Related
Categories
Questions about Reactome Database
What does Reactome Database do?
Query the Reactome database (Analysis and Content Services). Reactome Database is an agent skill from google-deepmind/science-skills. Query the Reactome database (Analysis and Content Services).
When should I use Reactome Database?
Reactome Database fits situations like: the user asks about pathway analysis; gene list enrichment; retrieving results by token; finding unmapped.
How do I install Reactome Database in Claude Code?
Run `npx skills add google-deepmind/science-skills --skill reactome-database -a claude-code`. Or copy the skill folder (skills/reactome_database in google-deepmind/science-skills) into .claude/skills/reactome-database in your project. Claude Code loads it when a task matches its description.
How do I install Reactome Database in Codex?
Run `npx skills add google-deepmind/science-skills --skill reactome-database -a codex`. Or copy the skill folder (skills/reactome_database in google-deepmind/science-skills) into .agents/skills/reactome-database in your project. Codex loads it when a task matches its description.
Can I use Reactome Database in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add google-deepmind/science-skills --skill reactome-database -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reactome-database, .gemini/skills/reactome-database, .github/skills/reactome-database and .opencode/skills/reactome-database in your project.
What does Reactome Database need to run?
Going by SKILL.md and its folder, Reactome Database needs Python for the scripts in its folder and the command-line tools its instructions call (uv). Our summary lists: Python 3.
Does Reactome Database access the network?
SKILL.md names 1 domain. In commands or code: reactome.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Reactome Database safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Reactome Database use?
Reactome Database is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Reactome Database use?
About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.
What are the alternatives to Reactome Database?
Skills that share tags, products or a category with Reactome Database: Hypothesis Generation (spacering-net/codeg, 3.8k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars), Nature Paper Card (Yuan1z0825/nature-skills, 46k stars) and Read arXiv Paper (karpathy/nanochat, 58k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Reactome Database?
google-deepmind (a GitHub organization) maintains it in google-deepmind/science-skills, which has 3,216 GitHub stars. The repository holds 40 skills in this directory. The repository was last updated on September 15, 2026.
Source: google-deepmind/science-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.