diff --git a/.agents/skills/pr-checklist/SKILL.md b/.agents/skills/pr-checklist/SKILL.md
index c3b7da3f4b8..e1f772680ab 100644
--- a/.agents/skills/pr-checklist/SKILL.md
+++ b/.agents/skills/pr-checklist/SKILL.md
@@ -70,6 +70,12 @@ Add a changelog fragment under `.nextchanges/` when your change is user-visible.
 
 **How to add:**
 - Create `.nextchanges/<section>/<name>.md`, picking the section folder that fits: `cli`, `bundles`, `dependency-updates`, `notable-changes`, or `api-changes`. `<name>` is arbitrary (a feature name or your PR number) — just keep it unique.
-- Write a single line in user-facing language, no Jira links: start it with a `* ` bullet marker and end it with a period. Match the voice and tense of existing changelog entries.
+- Write a single line in user-facing language, no Jira links: start it with a `* ` bullet marker and end it with a period.
+- **Voice and tense: imperative mood, active voice.** Lead with a verb that names the change — `Add`, `Fix`, `Bump`, `Remove`, `Deprecate`, `Support`, `Reject`, `Warn` — and describe the user-facing effect, not the implementation. Never use past tense (`Added`/`Fixed`) or first person (`we`/`I`/`our`). When a change reads better as a resulting behavior than as a verb, lead with the affected command, flag, or field in the present tense with "now".
+  - GOOD: Add support for the `cluster_policies` resource type.
+  - GOOD: Fix `--force-lock` being ignored when set in `databricks.yml`.
+  - GOOD: `bundle plan` now ignores the output-only `securable_kind` field during drift detection.
+  - BAD: Added support for cluster policies. — past tense; write "Add".
+  - BAD: We now reject secret scopes that name no principal. — first person; write "Reject secret scopes that name no principal."
 - A trailing PR link is required whenever the change is associated with a PR, and the introducing PR must be among the linked ones (the checker infers it and fails if it's missing) — enforced in CI (every PR and `main`) and locally once your branch has an open PR. Write the full markdown link at the very end, after the period: `([#NNNN](https://github.com/databricks/cli/pull/NNNN))` (your PR number). For an entry spanning several PRs, list them comma-separated: `([#NNNN](…), [#MMMM](…))`. Every `#NNNN` reference must be a full markdown link — a bare or paren-wrapped `#NNNN` is rejected.
 - See `.nextchanges/README.md` for details.
diff --git a/.nextchanges/README.md b/.nextchanges/README.md
index f475d66d25e..a759579d823 100644
--- a/.nextchanges/README.md
+++ b/.nextchanges/README.md
@@ -10,7 +10,7 @@ shared changelog file.
 Create `.nextchanges/<section>/<name>.md` and write what changed:
 
 ```
-* Added the `databricks quickstart` command.
+* Add the `databricks quickstart` command.
 ```
 
 You can do this straight from the GitHub UI: **Add file → Create new file**,
diff --git a/tools/validate_nextchanges.py b/tools/validate_nextchanges.py
index 71e0423b8c8..16960d2b5f9 100755
--- a/tools/validate_nextchanges.py
+++ b/tools/validate_nextchanges.py
@@ -365,7 +365,7 @@ def main(argv=None):
             print(f"{path}: {msg}", file=sys.stderr)
         print(f"\nFragments must live at {CHANGELOG_DIR}/<section>/<name>.md", file=sys.stderr)
         print("and be a single line with a `* ` bullet marker and a trailing period, e.g.", file=sys.stderr)
-        print("  * Added the `databricks quickstart` command.", file=sys.stderr)
+        print("  * Add the `databricks quickstart` command.", file=sys.stderr)
         print(f"Valid sections: {', '.join(sections)}", file=sys.stderr)
         print(f"{CHANGELOG_DIR}/{VERSION_FILE} must hold the next release version.", file=sys.stderr)
         sys.exit(1)