Agent skill · research science · google-deepmind
encode-ccres-database
Query the ENCODE Registry of cis-Regulatory Elements (cCREs) via the SCREEN GraphQL API, or make custom queries to the ENCODE Portal REST API for experiments and files (ChIP-seq peaks, etc.). Use when you want to query regulatory annotations or raw experimental data across human cell types.
Why this skill is useful
Provides specific commands and workflows for querying the ENCODE Registry that the AI wouldn't reliably generate on its own.
What it needs
Requires jq, uv installed locally. About 4k tokens when loaded. Last updated 2026-07-07. 2,648 stars on the source repository.
What this skill does
ENCODE Database Skill This skill allows you to query the ENCODE Registry of cCREs (candidate cis-Regulatory Elements) via the SCREEN GraphQL API. It helps identify functional non-coding DNA elements (like Promoters, Enhancers, and insulators) by analyzing biochemical signatures (DNase, H3K4me3, H3K27ac, CTCF). Prerequisites 1. uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH. 2. User Notification: If .licenses/encodeccresdatabaseLICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.encodeproject.org/help/rest-api/, then (2) create the file recording the notification text and timestamp. Core Rules Use the Wrapper: ALWAYS execute the provided helper scripts to query the database rather than accessing the database directly. The scripts automatically enforce the required rate limit gracefully. Parsing Output: Do NOT use cat to read the entire JSON output file into context, as it can be extremely large. You MUST use jq to efficiently parse and extract relevant fields. Notification: If this skill is used, ensure this is mentioned in the output. Quick Start All subcommands write JSON to disk. Always save output in a temporary location like /tmp/. Identifying High-Confidence ("Type A") Biosamples Biosamples in ENCODE are often categorized by their data completeness. "Type A" (or high-confidence) biosamples are those that have experimental data for all four core epigenetic markers: DNase, H3K4me3, H3K27ac, and CTCF. The biosamples and details commands automatically enrich their output with an istypea boolean flag for each biosample. Example: Finding high-confidence cell types Parsing Output (CRITICAL) Do NOT use cat to read the entire JSON output file into context, as it can be extremely large. Instead, you MUST use jq to efficiently parse and extract the relevant fields from the JSON file saved by the script. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills google-deepmind/encode_ccres_database