diff --git a/.gitignore b/.gitignore
index 6bfe303..d000526 100644
--- a/.gitignore
+++ b/.gitignore
@@ -95,6 +95,9 @@ venv.bak/
 .spyderproject
 .spyproject
 
+# pycharm project settings
+.idea
+
 # Rope project settings
 .ropeproject
 
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index de8a08f..c1efb63 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -73,3 +73,7 @@ repos:
     rev: v1.15.0
     hooks:
       - id: mypy
+  - repo: https://github.com/citation-file-format/cffconvert
+    rev: 054bda51dbe278b3e86f27c890e3f3ac877d616c
+    hooks:
+      - id: validate-cff
diff --git a/CITATION.cff b/CITATION.cff
new file mode 100644
index 0000000..e5135c3
--- /dev/null
+++ b/CITATION.cff
@@ -0,0 +1,27 @@
+cff-version: 1.2.0
+title: "Zarr benchmarks"
+version: 1
+license: "BSD-3-Clause"
+type: software
+abstract:
+  "This repository provides advice on how to set Zarr array configuration
+  options. These options all have an impact on data compression, read times, and
+  write times. The advice here is based on a series of benchmarks, which are
+  presented in the report."
+message: "If you use this software, please cite it as below."
+authors:
+  - given-names: David
+    family-names: Stansby
+    affiliation: University College London
+    orcid: "https://orcid.org/0000-0002-1365-1908"
+  - given-names: Kimberly
+    family-names: Meechan
+    affiliation: University College London
+    orcid: "https://orcid.org/0000-0003-4939-4170"
+  - given-names: Ruaridh
+    family-names: Gollifer
+    affiliation: University College London
+    orcid: "https://orcid.org/0000-0001-9319-936X8"
+keywords:
+  - zarr
+  - data compression