.changeset/small-words-show.md (1)

5-5: Tighten the changeset copy, add examples, and fix the link.

• Use past tense, proper naming (“eslint‑plugin‑react”), and end sentences with a period.
• Add tiny valid/invalid examples.
• Point to the correct rule page; the current slug likely collides with the CSS rule page. Update once the docs page exists.

Apply this diff:

-Added the new rule [`no-unknown-property`](https://biomejs.dev/linter/rules/no-unknown-property/)  from eslint react
+#### Lint rules.
+
+Added the new nursery rule [`noUnknownProperty`](<update-with-correct-docs-url>) ported from `eslint-plugin-react`.
+
+Examples:
+
+```jsx
+/* valid */
+<App class="foo" /><div data-foo="bar" />
+```
+
+```jsx
+/* invalid */
+<div class="foo" /><div data-testID="bar" />
+```

As per coding guidelines.

crates/biome_js_analyze/tests/specs/nursery/noUnknownProperty/ignore/valid.jsx (1)

1-6: Nice focused “ignore” case.

Consider adding a sibling negative case (property not on the ignore list) to prove the rule still fires.

crates/biome_js_analyze/tests/specs/nursery/noUnknownProperty/lowercase/invalid.jsx (1)

1-4: Confirm parity on custom components.

Do we intend requireDataLowercase to apply to custom components like <App />? ESLint’s rule often limits DOM‑prop checks to host elements. If we want parity, scope this to intrinsic elements; if we want stricter Biome behaviour, keep as is and document it.

crates/biome_js_analyze/tests/specs/nursery/noUnknownProperty/valid.jsx (1)

1-204: Big omnibus “valid” test – consider splitting by theme.

Smaller themed fixtures (events, SVG, boolean attrs, data/aria, legacy attrs) make diffs and failures easier to triage. Also keep the React 19 popover block gated in a dedicated future test.

Quick sweep for potential tag‑specific mismatches (e.g. allowFullScreen on non‑iframe) would be good to double‑check against the rule’s allowed‑tags map.

crates/biome_js_analyze/tests/specs/nursery/noUnknownProperty/invalid.jsx (2)

21-38: Add popover/onBeforeToggle cases to lock React 19 support

Please add invalid/valid cases for popover API:

• Attributes: popover, popovertarget, popovertargetaction.
• Events: onBeforeToggle/onToggle on allowed tags.
  This prevents regressions and aligns with your commented code in the rule.

---

1-3: Consider a companion valid case for custom elements

Add a valid fixture using a custom element (e.g., ) to assert the rule skips custom elements and tags with an is attribute. This documents intent.

crates/biome_js_analyze/src/lint/nursery/no_unknown_property.rs (5)

1065-1077: Avoid avoidable allocations for attribute names

name/value_token().text_trimmed().to_string() and the manual namespace concatenation allocate on every attribute. Use TokenText and Cow to allocate only for namespaced cases.

@@
-        let node_name = match node.name().ok()? {
-            AnyJsxAttributeName::JsxName(name) => {
-                name.value_token().ok()?.text_trimmed().to_string()
-            }
-            AnyJsxAttributeName::JsxNamespaceName(name) => {
-                let namespace = name.namespace().ok()?.value_token().ok()?;
-                let name = &name.name().ok()?.value_token().ok()?;
-                // There could be better way, but i couldn't extract namespaced attributes
-                // For e.g xlink:href
-                // without manually concatenating with ':'
-                namespace.text_trimmed().to_string() + ":" + name.text_trimmed()
-            }
-        };
+        use std::borrow::Cow;
+        let node_name: Cow<'_, str> = match node.name().ok()? {
+            AnyJsxAttributeName::JsxName(name) => {
+                Cow::Borrowed(name.value_token().ok()?.text_trimmed())
+            }
+            AnyJsxAttributeName::JsxNamespaceName(name) => {
+                let ns = name.namespace().ok()?.value_token().ok()?.text_trimmed();
+                let local = name.name().ok()?.value_token().ok()?.text_trimmed();
+                Cow::Owned(format!("{ns}:{local}"))
+            }
+        };
@@
-        if options.ignore.contains(&node_name) {
+        if options.ignore.iter().any(|s| s == &*node_name) {
             return None;
         }
@@
-        let name = normalize_attribute_case(&node_name);
+        let name = normalize_attribute_case(&node_name);

Also applies to: 1079-1081

---

1009-1014: Simplify tag_name_has_dot signature

This always returns Some(..). Make it return bool and drop ? at call sites; avoids needless Option churn.

-fn tag_name_has_dot(node: &AnyJsxElement) -> Option<bool> {
-    Some(matches!(
-        node.name().ok()?,
-        AnyJsxElementName::JsxMemberName(_)
-    ))
-}
+fn tag_name_has_dot(node: &AnyJsxElement) -> bool {
+    matches!(node.name().ok(), Ok(AnyJsxElementName::JsxMemberName(_)))
+}
@@
-        if tag_name_has_dot(&element)? {
+        if tag_name_has_dot(&element) {
             return None;
         }

---

1167-1183: Minor copy tweak

The diagnostic says “for React components”, but this rule validates DOM elements after gating out components. Suggest “in JSX” to avoid confusion.

-                    "Use '"{standard_name}"' instead of '"{name}"' for React components."
+                    "Use '"{standard_name}"' instead of '"{name}"' in JSX."

---

1484-1510: Use case‑insensitive check for data‑ only after the prefix*

Current has_uppercase(name) flags any uppercase anywhere, which is fine, but the option intent is about the part after data-. Consider restricting the scan to the suffix to keep the message crisp for odd inputs.

-            if options.require_data_lowercase && has_uppercase(&name) {
+            if options.require_data_lowercase {
+                let suffix = &name["data-".len()..];
+                if has_uppercase(suffix) {
                     return Some(NoUnknownPropertyDiagnostic::DataLowercaseRequired {
                         name: name.to_string(),
                         lowercase_name: name.to_lowercase(),
                     });
-            }
+                }
+            }

---

226-231: Keys are sorted — guard test is defensive, not critical

The ATTRIBUTE_TAGS_MAP keys are currently sorted and the code is correct. However, the suggestion to add a guard test is reasonable: without one, future edits could accidentally break sort order without triggering a compile-time error, and binary_search_by_key would silently fail at runtime.

Consider adding a simple unit test at the end of the file to assert the map remains sorted:

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn attribute_tags_map_is_sorted() {
        let keys: Vec<_> = ATTRIBUTE_TAGS_MAP.iter().map(|(k, _)| k).collect();
        let mut sorted = keys.clone();
        sorted.sort();
        assert_eq!(keys, sorted, "ATTRIBUTE_TAGS_MAP keys must remain sorted for binary_search_by_key");
    }
}

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Learnt from: CR
PR: biomejs/biome#0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:20:19.139Z
Learning: Applies to crates/biome_analyze/crates/biome_rule_options/lib/**/*.rs : For options types, derive Serialize, Deserialize, Deserializable (and JsonSchema under the schema feature) and use #[serde(rename_all="camelCase", deny_unknown_fields, default)] with skip_serializing_if where appropriate

Learnt from: CR
PR: biomejs/biome#0
File: crates/biome_formatter/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:22:15.851Z
Learning: Applies to crates/biome_formatter/tests/specs/**/options.json : Use options.json files colocated with test inputs to override formatting options for all files in that folder

Learnt from: dyc3
PR: biomejs/biome#7081
File: packages/@biomejs/biome/configuration_schema.json:7765-7781
Timestamp: 2025-08-05T14:43:29.581Z
Learning: The file `packages/biomejs/biome/configuration_schema.json` is auto-generated and should not be manually edited or reviewed for schema issues; any changes should be made at the code generation source.

Learnt from: CR
PR: biomejs/biome#0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:20:19.139Z
Learning: Applies to crates/biome_analyze/**/tests/specs/**/*.{js,jsx,ts,tsx} : Place snapshot test cases under tests/specs/<group>/<ruleName>/ with files typically prefixed by invalid/ or valid/

Learnt from: CR
PR: biomejs/biome#0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:20:19.139Z
Learning: A rule’s diagnostic should explain what the error is, why it’s triggered, and what to do (ideally via a code action or a note)

Learnt from: CR
PR: biomejs/biome#0
File: crates/biome_diagnostics/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:21:24.116Z
Learning: A diagnostic must explain why something went wrong, using log advices and links to documentation when helpful

crates/biome_js_analyze/src/lint/nursery/no_unknown_property.rs (1)

713-714: Event casing: add onBeforeToggle; drop ontoggle; prefer camelCase suggestions

Current list includes lowercase "onbeforetoggle" and "ontoggle", but misses the canonical React props "onBeforeToggle" and (already present) "onToggle". As written, ontoggle/onbeforetoggle will be accepted and won’t auto‑fix to camelCase.

-    "onbeforetoggle",
+    "onBeforeToggle",
@@
-    "ontoggle",
+    // Intentionally omit lowercase "ontoggle" so it maps to "onToggle"

Add tests asserting:

• <div onbeforetoggle={() => {}} /> → diagnostic suggesting onBeforeToggle
• <div ontoggle={() => {}} /> → diagnostic suggesting onToggle

This keeps behaviour aligned with React 19’s events and improves auto‑fix.

Also applies to: 847-848

crates/biome_js_analyze/src/lint/nursery/no_unknown_property.rs (3)

1065-1077: Avoid unnecessary allocations for attribute names; make ignore check case‑insensitive

You allocate for every attribute (to_string, manual concat). We can avoid allocations in the common case and only allocate for namespaced attributes, while matching ignore without allocating.

+use std::borrow::Cow;
@@
-        let node_name = match node.name().ok()? {
-            AnyJsxAttributeName::JsxName(name) => {
-                name.value_token().ok()?.text_trimmed().to_string()
-            }
-            AnyJsxAttributeName::JsxNamespaceName(name) => {
-                let namespace = name.namespace().ok()?.value_token().ok()?;
-                let name = &name.name().ok()?.value_token().ok()?;
-                // There could be better way, but i couldn't extract namespaced attributes
-                // For e.g xlink:href
-                // without manually concatenating with ':'
-                namespace.text_trimmed().to_string() + ":" + name.text_trimmed()
-            }
-        };
+        let node_name_text: Cow<'_, str> = match node.name().ok()? {
+            AnyJsxAttributeName::JsxName(name) => {
+                Cow::Borrowed(name.value_token().ok()?.text_trimmed())
+            }
+            AnyJsxAttributeName::JsxNamespaceName(name) => {
+                let ns = name.namespace().ok()?.value_token().ok()?.text_trimmed();
+                let nm = name.name().ok()?.value_token().ok()?.text_trimmed();
+                Cow::Owned(format!("{ns}:{nm}"))
+            }
+        };
@@
-        if options.ignore.contains(&node_name) {
+        if options
+            .ignore
+            .iter()
+            .any(|s| s.eq_ignore_ascii_case(node_name_text.as_ref()))
+        {
             return None;
         }
@@
-        let name = normalize_attribute_case(&node_name);
+        let name = normalize_attribute_case(node_name_text.as_ref());

This removes hot‑path allocations and makes ignore friendlier. If ignore is meant to be case‑sensitive, drop eq_ignore_ascii_case.

Also applies to: 1079-1084

---

972-973: Redundant use inside function

use biome_string_case::StrOnlyExtension; is already imported at the module level. Remove the inner use.

-    use biome_string_case::StrOnlyExtension;

---

1169-1177: Offer quick‑fixes in diagnostics (rename)

You already tell users what to do; wire in code actions to auto‑rename to standard_name and lower‑case data-* attributes.

Happy to sketch the .action plumbing if useful.

Also applies to: 1205-1213

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Learnt from: CR
PR: biomejs/biome#0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:20:19.139Z
Learning: A rule’s diagnostic should explain what the error is, why it’s triggered, and what to do (ideally via a code action or a note)

Learnt from: CR
PR: biomejs/biome#0
File: crates/biome_diagnostics/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:21:24.116Z
Learning: A diagnostic must explain why something went wrong, using log advices and links to documentation when helpful

crates/biome_js_analyze/src/lint/nursery/no_unknown_attribute.rs (4)

107-113: Remove commented-out code or implement Popover API support.

This commented block has been sitting here—either implement React 19 Popover API prop validation or remove it to keep the codebase tidy.

---

115-226: Consider sorting ATTRIBUTE_TAGS_MAP alphabetically for maintainability.

The map entries aren't alphabetically sorted (e.g., "onCancel" appears after "onCanPlay", "onLoadedData" after "onLoadStart"). Whilst the HashMap lookup (line 1110) is unaffected, keeping the source sorted makes future edits less error-prone.

---

969-969: Remove redundant import.

StrOnlyExtension is already imported at the module level (line 8); this local import is unnecessary.

Apply this diff:

 fn is_valid_data_attribute(name: &str) -> bool {
-    use biome_string_case::StrOnlyExtension;
     if !name.starts_with("data-") {

---

1188-1188: Improve formatting of allowed tags list.

Add a space after the comma for better readability in the diagnostic message.

Apply this diff:

-                       "This attribute is only allowed on: "{allowed_tags.join(",")}
+                       "This attribute is only allowed on: "{allowed_tags.join(", ")}

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Learnt from: CR
PR: biomejs/biome#0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.631Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : If a rule is inspired by an external source, populate sources in declare_lint_rule! with RuleSource::{Eslint,...} and same()/inspired()

crates/biome_js_analyze/src/lint/nursery/no_unknown_attribute.rs (5)

68-68: Update documentation example to match corrected rule name.

The rule identifier should be noUnknownProperty throughout.

-  "noUnknownAttribute": {
+  "noUnknownProperty": {

---

85-85: Update documentation example to match corrected rule name.

Same as above—align with noUnknownProperty.

-  "noUnknownAttribute": {
+  "noUnknownProperty": {

---

95-95: Rule name must match tests and options configuration.

The published rule ID noUnknownAttribute conflicts with test fixtures and option definitions that expect noUnknownProperty.

-        name: "noUnknownAttribute",
+        name: "noUnknownProperty",

---

1101-1104: requireDataLowercase option is defined but never enforced.

The option exists in the schema and has diagnostic logic, but you never check options.require_data_lowercase before returning None here.

Add before the early return:

 if is_valid_data_attribute(name) {
+    if options.require_data_lowercase.unwrap_or(false) 
+        && name != &name.to_lowercase() 
+    {
+        return Some(NoUnknownAttributeState::DataLowercaseRequired {
+            name: (*name).into(),
+        });
+    }
     return None;
 }

Note: You'll also need to add the DataLowercaseRequired variant to NoUnknownAttributeState and implement its diagnostic.

---

1126-1126: TokenText doesn't have a trim() method.

tag_name is TokenText (line 1111). Use .text() instead.

-            if !allowed_tags.contains(&tag_name.trim()) {
+            if !allowed_tags.contains(&tag_name.text()) {

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/tests/specs/**/*.jsonc : .jsonc snapshot test files must contain an array of code strings and are interpreted as script (no ESM import/export)

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/tests/specs/**/{invalid*,valid*}.* : Name snapshot test files with invalid* and valid* prefixes to indicate reported vs non-reported cases

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Set the language field in declare_lint_rule! to the most appropriate dialect (js/jsx/ts/tsx)

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/lint/nursery/**/*.rs : Place all new rules in the nursery group

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/a11y/**/*.rs : Rules in a11y group must have severity: error

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Rule documentation: first paragraph must be a single line summary

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : If a rule is inspired by an external source, populate sources in declare_lint_rule! with RuleSource::{Eslint,...} and same()/inspired()

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : In declare_lint_rule! macros, set version: "next"

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Provide informative diagnostics: explain what the error is, why it triggers, and what to do (prefer a code action or a note)

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : If a rule provides a code action, add fix_kind to declare_lint_rule! (FixKind::Safe or ::Unsafe)

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Rule names should use no<Concept> when forbidding a single concept (e.g., noDebugger)

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Use rule_category! macro to reference the diagnostic category created by declare_lint_rule!

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Prefer conventional naming families when applicable: use<Framework>..., noConstant<Concept>, noDuplicate<Concept>, noEmpty<Concept>, noExcessive<Concept>, noRedundant<Concept>, noUnused<Concept>, noUseless<Concept>, noInvalid<Concept>, useValid<Concept>, noUnknown<Concept>, noMisleading<Concept>, noRestricted<Concept>, noUndeclared<Concept>, noUnsafe<Concept>, useConsistent<Concept>, useShorthand<Concept>

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Rule names should use use<Concept> when mandating a single concept (e.g., useValidLang)

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/style/**/*.rs : Rules in style group must have severity: info or warn (prefer info if unsure)

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/suspicious/**/*.rs : Rules in suspicious group must have severity: warn or error (prefer warn if unsure)

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/biome_rule_options/lib/**/*.rs : Place per-rule options types in biome_rule_options crate under lib/, one file per rule

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Avoid avoidable string allocations; compare against &str or TokenText rather than allocating Strings

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_js_formatter/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:22:46.002Z
Learning: Applies to crates/biome_js_formatter/**/*.rs : Do not attempt to fix code; if a mandatory token/node is missing, return `None` instead

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_js_formatter/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:22:46.002Z
Learning: Applies to crates/biome_js_formatter/**/*.rs : For non-mandatory tokens, use the provided helper constructors (e.g., `token`, `space_token`, `dynamic_token`)

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_js_formatter/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:22:46.002Z
Learning: Applies to crates/biome_js_formatter/**/*.rs : When a token is mandatory and present in the AST, use the AST-provided token (e.g., `node.l_paren_token().format()`) instead of emitting a static token

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : In ### Invalid doc examples, each snippet must use the expect_diagnostic modifier and emit exactly one diagnostic

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Documentation must include a ## Examples section with ### Invalid before ### Valid

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/*_analyze/**/src/**/lint/**/*.rs : Avoid deep indentation by using combinators (map, filter, and_then) rather than nested if-let/unwrap chains

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_analyze/CONTRIBUTING.md:0-0
Timestamp: 2025-10-24T21:24:58.650Z
Learning: Applies to crates/biome_analyze/crates/biome_rule_options/lib/**/*.rs : Prefer Box<[Box<str>]> over Vec<String> for options string lists to reduce memory usage

Learnt from: CR
Repo: biomejs/biome PR: 0
File: crates/biome_formatter/CONTRIBUTING.md:0-0
Timestamp: 2025-10-15T09:22:15.851Z
Learning: Applies to crates/biome_formatter/src/**/*.rs : After generation, remove usages of `format_verbatim_node` and implement real formatting with biome_formatter utilities