Skip to content

K-Dense-AI/scientific-agent-skills / skills/gget

Queries 20+ bioinformatics resources through CLI/Python. Supports quick lookups of gene info, BLAST/BLAT, viral sequence downloads, PDB/mmCIF structures, G2P residue annotations, enrichment analysis, OpenTargets, COSMIC, CELLxGENE, and 8cube mouse specificity/expression data. Best for interactive exploration and simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.

FileKindSize
SKILL.mdskill md11.0 KB
references/common_workflows.mdmarkdown2.5 KB
references/database_info.mdmarkdown13.3 KB
references/module_catalog.mdmarkdown26.0 KB
references/module_reference.mdmarkdown23.8 KB
references/workflows.mdmarkdown9.6 KB
scripts/batch_sequence_analysis.pyexecutablescript6.6 KB
scripts/enrichment_pipeline.pyexecutablescript7.7 KB
scripts/gene_analysis.pyexecutablescript7.4 KB

references/common_workflows.md

View on GitHub
# Common gget workflows

Use [workflows.md](workflows.md) for current 0.30.8 integration examples and their
verification boundaries. Use [database_info.md](database_info.md) for service,
authentication, pagination, and return-shape details.

| Task | Sequence of operations | Check before interpretation |
| --- | --- | --- |
| Gene characterization | `search` -> unique exact `gene_name` -> `info` / `seq` | Preserve Ensembl index; inspect service failures; distinguish genomic sequence from CDS. |
| Ortholog comparison | `bgee` -> select species/ortholog -> `seq` -> FASTA file -> `muscle(out=...)` | Reject ambiguous orthology and nested FASTA lists. MUSCLE returns None. |
| Structures and residue features | `g2p` with exact accession -> inspect isoform/PDB map -> `pdb(resource="mmcif")` | Match chain/residue coverage; predicted features are not experimental validation. |
| Expression | `archs4` or scoped `cellxgene` query | Human-only ARCHS4 correlations; species-specific tissue query; Census metadata counts cells. |
| Enrichment | selected genes + measured background -> `enrichr` with full library -> adjusted-p-value filter | Species/library compatibility, mapped IDs, selection universe, and returned `adj_p_val`. |
| Disease/drug exploration | human Ensembl ID -> `opentargets` resources | Dot-separated columns, local filtering after limit, partial pages, association versus causation. |
| Cancer data | chosen cBioPortal studies -> `cbio_plot`; licensed local COSMIC TSV -> `cosmic` | Study denominators, project/release/assembly, download completeness. |
| Reference preparation | `ref` with release -> CLI `-d` download -> checksums -> downstream index | `which` is comma-separated on CLI; Python has no download parameter. |

Bundled scripts (run from the skill root):

```bash
python scripts/gene_analysis.py TP53
python scripts/enrichment_pipeline.py selected.txt --background tested.txt --no-plot
python scripts/enrichment_pipeline.py fly_genes.txt --species fly --database SPECIES_SPECIFIC_LIBRARY --no-plot
python scripts/batch_sequence_analysis.py proteins.fasta --database swissprot
```

These network invocations are illustrative. Confirm that a species-specific
library exists before submitting it; its example name is not a freshness claim.
The script suite verifies local control flow with mocked responses. The gene
pipeline depends on the Ensembl REST adapter, which failed during the current
public probe. The batch script is for small exploratory queries and never runs
AlphaFold; large searches should use local alignment tooling.
deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall