uniprot-protein-database SKILL.md skillA
uniprot-protein-database from jaechang-hits/sciagent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jaechang-hits/sciagent-skills/uniprot-protein-database@git:20260528.0e69cedPins git:20260528.0e69ced in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jaechang-hits/sciagent-skills
- Path
skills/proteomics-protein-engineering/uniprot-protein-database/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260528.0e69ced, committed May 28, 2026
- First version recorded
- Feb 18, 2026
- Size
- 13,829 bytes
- Repository stars
- 381
- License
- a license file GitHub does not identify
Query UniProt REST API: search by gene/protein name, fetch FASTA, map IDs (Ensembl, PDB, RefSeq), access Swiss-Prot annotations. Use bioservices for multi-DB access; alphafold-database-access for structures.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# UniProt — Protein Database ## Overview UniProt is the most comprehensive protein sequence and functional annotation database, containing 250M+ entries. This skill covers programmatic access via the UniProt REST API for protein search, sequence retrieval, ID mapping, and annotation queries. Swiss-Prot entries are manually curated; TrEMBL entries are computationally predicted. ## When to Use - Searching for proteins by gene name, accession, organism, or function keywords - Retrieving protein sequences in FASTA format for downstream analysis - Mapping identifiers between databases (UniProt ↔ Ensembl, PDB, RefSeq, KEGG) - Accessing protein annotations: GO terms, domains, post-translational modifications - Batch retrieving multiple protein entries for comparative analysis - Downloading reviewed (Swiss-Prot) protein datasets for a specific organism - For **unified access to 40+ databases**, use bioservices instead - For **protein 3D structures**, use alphafold-database-access or pdb-database ## Prerequisites ```bash pip install requests pandas ``` …
Read the whole file at its exact version.
How to install
mdr add jaechang-hits/sciagent-skills/uniprot-protein-database@sha256:201073aa8ca8dca4The line at the top of this page pins the label git:20260528.0e69ced, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_pykdnk3ucqe6zvja)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Feb 18, 2026 and May 28, 2026, about one every 49 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260528.0e69ced latest | 2026-05-28 | 0e69ced | 13,829 B | A | view · diff |
| git:20260428.81ea2d2 | 2026-04-28 | 81ea2d2 | 13,808 B | A | view · diff |
| git:20260218.8df1694 | 2026-02-18 | 8df1694 | 13,884 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13829 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jaechang-hits/sciagent-skills · 381 stars · license a license file GitHub does not identify · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pykdnk3ucqe6zvja GET https://markdownregistry.com/api/v1/resolve?ref=jaechang-hits/sciagent-skills/uniprot-protein-database GET https://markdownregistry.com/api/v1/blob/201073aa8ca8dca40f44c087115e44a58483e795e6e444ebf8162516f3e7de6c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.