cross-reference SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
cross-reference from ammawla/encode-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ammawla/encode-toolkit/cross-reference@git:20260921.4ba10c6Pins git:20260921.4ba10c6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ammawla/encode-toolkit
- Path
plugin/skills/cross-reference/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260921.4ba10c6, committed Sep 21, 2026
- First version recorded
- Mar 12, 2026
- Size
- 35,760 bytes
- Repository stars
- 21
- License
- AGPL-3.0
Cross-reference ENCODE data with PubMed, bioRxiv, ClinicalTrials.gov, Open Targets, GTEx, ClinVar, GWAS Catalog, gnomAD, Ensembl, and other scientific databases. Use when the user wants to find publications, preprints, or clinical trials related to ENCODE experiments, chain ENCODE data with other scientific MCP servers, or build translational pipelines from genomic data to clinical application.
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
# Cross-Reference ENCODE with Other Databases ## When to Use - User wants to connect ENCODE data to publications, clinical trials, or other databases - User asks to "cross-reference", "link", or "connect" ENCODE with PubMed, bioRxiv, GEO, etc. - User wants to find clinical trials related to ENCODE genomic targets - User needs to build translational pipelines from ENCODE regulatory data to disease context - User asks about drugs targeting genes identified in ENCODE experiments - User wants to find variant annotations (ClinVar, gnomAD) for ENCODE regulatory regions Help the user connect ENCODE genomics data to the broader scientific literature, clinical research, drug target discovery, and variant interpretation. This skill is the central hub for all multi-database workflows in the ENCODE Toolkit. ## Cross-Reference Workflows ### ENCODE + PubMed 1. Track an ENCODE experiment to extract PMIDs from publications 2. Use `encode_get_citations` or `encode_get_references` to get PMIDs 3. Pass PMIDs to PubMed tools (`search_articles`, `get_article_metadata`, `find_related_articles`) 4. Find related literature about the same targets, biosamples, or biological questions …
Read the whole file at its exact version.
How to install
mdr add ammawla/encode-toolkit/cross-reference@sha256:fe4d92cd07e914f5The line at the top of this page pins the label git:20260921.4ba10c6, 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_qk6dt2b34sisthbw)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Mar 12, 2026 and Sep 21, 2026, about one every 64 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260921.4ba10c6 latest | 2026-09-21 | 4ba10c6 | 35,760 B | A | view · diff |
| git:20260920.6050003 | 2026-09-20 | 6050003 | 35,661 B | A | view · diff |
| git:20260920.ce7840d | 2026-09-20 | ce7840d | 35,267 B | A | view · diff |
| git:20260312.665e731 | 2026-03-12 | 665e731 | 35,265 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 (35760 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
ammawla/encode-toolkit · 21 stars · license AGPL-3.0 · pushed 2026-09-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qk6dt2b34sisthbw GET https://markdownregistry.com/api/v1/resolve?ref=ammawla/encode-toolkit/cross-reference GET https://markdownregistry.com/api/v1/blob/fe4d92cd07e914f57c33286babb73b67e1a66bf819dae488d8639289f3cc13cd
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.
More from ammawla/encode-toolkit
Every file in ammawla/encode-toolkit