plain-language-guidelines
reference corpus · status live · domain WRITE (Writing and copy) · lane A · refresh pinned · tags US · PLAIN-LANGUAGE · GOVERNMENT · GUIDELINES · EDITORIAL · WRITING
What an agent uses it for
An agent rewriting bureaucratic or legalese text into plain language queries this for the U.S. Federal Plain Language Guidelines and their before/after examples.
curl -fsSLO https://raw.githubusercontent.com/xerj-org/xerj/corpus-hub/tools/xerj-code/hub/plain-language-guidelines.jsonxerj corpus add --from ./plain-language-guidelines.jsonxerj corpus index plain-language-guidelines then xerj code plain-language-guidelines "your question"Needs the xerj CLI and a local node running; the copy prompt covers both, checks each step, and shows how to stop only the node you started. No shell: the MCP tool xerj_code_search with corpus: "plain-language-guidelines", once the corpus is indexed on the node.
Sources and pins
| source | pin | licence | size | review note |
|---|---|---|---|---|
| plainlanguage.gov | fd7694740f19 | CC0-1.0 | 64.8 MB / 368 files | Decoded LICENSE.md directly (GitHub API returns NOASSERTION only because the licence is Markdown with YAML front-matter): it is a US-Government public-domain work PLUS an explicit CC0 1.0 Universal worldwide dedication - genuinely CC0-1.0, copy/modify allowed even commercially. Repo is ARCHIVED/read-only but fully present and cloneable (~79.8MB git size); corpus value is the guidelines markdown, n |
64.8 MB across 368 files. Added 2026-10-13.
Rights
CC0-1.0. Redistribution permitted with attribution per the licence review. The review block records a human opening each licence file at the pin. Detector output is a hint, never the verdict.
Retrieval spot-check (G7)
Not yet spot-checked. Queries are pre-registered in the registry before grading.