COSMIC (Catalogue of Somatic Mutations in Cancer) is the world's largest and most comprehensive database for exploring somatic mutations in human cancer. Access COSMIC's extensive collection of cancer genomics data, including millions of mutations across thousands of cancer types, curated gene lists, mutational signatures, and clinical annotations programmatically.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versioncosmic-databaseExecute the skills CLI command in your project's root directory to begin installation:
Fetches cosmic-database from davila7/claude-code-templates and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate cosmic-database. Access via /cosmic-database in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
24.2K
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
24.2K
stars
COSMIC (Catalogue of Somatic Mutations in Cancer) is the world's largest and most comprehensive database for exploring somatic mutations in human cancer. Access COSMIC's extensive collection of cancer genomics data, including millions of mutations across thousands of cancer types, curated gene lists, mutational signatures, and clinical annotations programmatically.
This skill should be used when:
COSMIC requires authentication for data downloads:
uv pip install requests pandas
Use the scripts/download_cosmic.py script to download COSMIC data files:
from scripts.download_cosmic import download_cosmic_file
# Download mutation data
download_cosmic_file(
email="[email protected]",
password="your_password",
filepath="GRCh38/cosmic/latest/CosmicMutantExport.tsv.gz",
output_filename="cosmic_mutations.tsv.gz"
)
# Download using shorthand data type
python scripts/download_cosmic.py [email protected] --data-type mutations
# Download specific file
python scripts/download_cosmic.py [email protected] \
--filepath GRCh38/cosmic/latest/cancer_gene_census.csv
# Download for specific genome assembly
python scripts/download_cosmic.py [email protected] \
--data-type gene_census --assembly GRCh37 -o cancer_genes.csv
import pandas as pd
# Read mutation data
mutations = pd.read_csv('cosmic_mutations.tsv.gz', sep='\t', compression='gzip')
# Read Cancer Gene Census
gene_census = pd.read_csv('cancer_gene_census.csv')
# Read VCF format
import pysam
vcf = pysam.VariantFile('CosmicCodingMuts.vcf.gz')
Download comprehensive mutation data including point mutations, indels, and genomic annotations.
Common data types:
mutations - Complete coding mutations (TSV format)mutations_vcf - Coding mutations in VCF formatsample_info - Sample metadata and tumor information# Download all coding mutations
download_cosmic_file(
email="[email protected]",
password="password",
filepath="GRCh38/cosmic/latest/CosmicMutantExport.tsv.gz"
)
Access the expert-curated list of ~700+ cancer genes with substantial evidence of cancer involvement.
# Download Cancer Gene Census
download_cosmic_file(
email="[email protected]",
password="password",
filepath="GRCh38/cosmic/latest/cancer_gene_census.csv"
)
Use cases:
Download signature profiles for mutational signature analysis.
# Download signature definitions
download_cosmic_file(
email="[email protected]",
password="password",
filepath="signatures/signatures.tsv"
)
Signature types:
Access gene fusion data and structural rearrangements.
Available data types:
structural_variants - Structural breakpointsfusion_genes - Gene fusion events# Download gene fusions
download_cosmic_file(
email="[email protected]",
password="password",
filepath="GRCh38/cosmic/latest/CosmicFusionExport.tsv.gz"
)
Retrieve copy number alterations and gene expression data.
Available data types:
copy_number - Copy number gains/lossesgene_expression - Over/under-expression data# Download copy number data
download_cosmic_file(
email="[email protected]",
password="password",
filepath="GRCh38/cosmic/latest/CosmicCompleteCNA.tsv.gz"
)
Access drug resistance mutation data with clinical annotations.
# Download resistance mutations
download_cosmic_file(
email="[email protected]",
password="password",
filepath="GRCh38/cosmic/latest/CosmicResistanceMutations.tsv.gz"
)
COSMIC provides data for two reference genomes:
Specify the assembly in file paths:
# GRCh38 (recommended)
filepath="GRCh38/cosmic/latest/CosmicMutantExport.tsv.gz"
# GRCh37 (legacy)
filepath="GRCh37/cosmic/latest/CosmicMutantExport.tsv.gz"
latest in file paths to always get the most recent releasev102, v101, etc.Filter mutations by gene:
import pandas as pd
mutations = pd.read_csv('cosmic_mutations.tsv.gz', sep='\t', compression='gzip')
tp53_mutations = mutations[mutations['Gene name'] == 'TP53']
Identify cancer genes by role:
gene_census = pd.read_csv('cancer_gene_census.csv')
oncogenes = gene_census[gene_census['Role in Cancer'].str.contains('oncogene', na=False)]
tumor_suppressors = gene_census[gene_census['Role in Cancer'].str.contains('TSG', na=False)]
Extract mutations by cancer type:
mutations = pd.read_csv('cosmic_mutations.tsv.gz', sep='\t', compression='gzip')
lung_mutations = mutations[mutations['Primary site'] == 'lung']
Work with VCF files:
import pysam
vcf = pysam.VariantFile('CosmicCodingMuts.vcf.gz')
for record in vcf.fetch('17', 7577000, 7579000): # TP53 region
print(record.id, record.ref, record.alts, record.info)
For comprehensive information about COSMIC data structure, available files, and field descriptions, see references/cosmic_data_reference.md. This reference includes:
Use this reference when:
The download script includes helper functions for common operations:
from scripts.download_cosmic import get_common_file_path
# Get path for mutations file
path = get_common_file_path('mutations', genome_assembly='GRCh38')
# Returns: 'GRCh38/cosmic/latest/CosmicMutantExport.tsv.gz'
# Get path for gene census
path = get_common_file_path('gene_census')
# Returns: 'GRCh38/cosmic/latest/cancer_gene_census.csv'
Available shortcuts:
mutations - Core coding mutationsmutations_vcf - VCF format mutationsgene_census - Cancer Gene Censusresistance_mutations - Drug resistance datastructural_variants - Structural variantsgene_expression - Expression datacopy_number - Copy number alterationsfusion_genes - Gene fusionssignatures - Mutational signaturessample_info - Sample metadatalatest for the most recent versionCOSMIC data integrates well with:
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
davila7/claude-code-templates
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
ailabs-393/ai-labs-claude-skills
Keeps context tight: cosmic-database is the kind of skill you can hand to a new teammate without a long onboarding doc.
I recommend cosmic-database for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Solid pick for teams standardizing on skills: cosmic-database is focused, and the summary matches what you get after install.
Registry listing for cosmic-database matched our evaluation — installs cleanly and behaves as described in the markdown.
cosmic-database has been reliable in day-to-day use. Documentation quality is above average for community skills.
cosmic-database fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
cosmic-database reduced setup friction for our internal harness; good balance of opinion and flexibility.
We added cosmic-database from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Useful defaults in cosmic-database — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Registry listing for cosmic-database matched our evaluation — installs cleanly and behaves as described in the markdown.
showing 1-10 of 61