diff --git a/shortcuts/base/base_dryrun_ops_test.go b/shortcuts/base/base_dryrun_ops_test.go
index 5b9b7a36f..64d53bdfd 100644
--- a/shortcuts/base/base_dryrun_ops_test.go
+++ b/shortcuts/base/base_dryrun_ops_test.go
@@ -104,6 +104,8 @@ func TestDryRunRecordOps(t *testing.T) {
 		nil, nil,
 	)
 	assertDryRunContains(t, dryRunRecordUpsert(ctx, upsertCreateRT), "POST /open-apis/base/v3/bases/app_x/tables/tbl_1/records")
+	assertDryRunContains(t, dryRunRecordBatchCreate(ctx, upsertCreateRT), "POST /open-apis/base/v3/bases/app_x/tables/tbl_1/records/batch_create")
+	assertDryRunContains(t, dryRunRecordBatchUpdate(ctx, upsertCreateRT), "POST /open-apis/base/v3/bases/app_x/tables/tbl_1/records/batch_update")
 
 	rt := newBaseTestRuntime(
 		map[string]string{"base-token": "app_x", "table-id": "tbl_1", "record-id": "rec_1", "json": `{"Name":"B"}`},
diff --git a/shortcuts/base/base_execute_test.go b/shortcuts/base/base_execute_test.go
index 374afb034..3698d3994 100644
--- a/shortcuts/base/base_execute_test.go
+++ b/shortcuts/base/base_execute_test.go
@@ -664,6 +664,75 @@ func TestBaseRecordExecuteReadCreateDelete(t *testing.T) {
 		}
 	})
 
+	t.Run("batch create", func(t *testing.T) {
+		factory, stdout, reg := newExecuteFactory(t)
+		reg.Register(&httpmock.Stub{
+			Method: "POST",
+			URL:    "/open-apis/base/v3/bases/app_x/tables/tbl_x/records/batch_create",
+			Body: map[string]interface{}{
+				"code": 0,
+				"data": map[string]interface{}{
+					"fields":         []interface{}{"Name"},
+					"record_id_list": []interface{}{"rec_1", "rec_2"},
+					"data":           []interface{}{[]interface{}{"Alice"}, []interface{}{"Bob"}},
+				},
+			},
+		})
+		if err := runShortcut(t, BaseRecordBatchCreate, []string{"+record-batch-create", "--base-token", "app_x", "--table-id", "tbl_x", "--json", `{"fields":["Name"],"rows":[["Alice"],["Bob"]]}`}, factory, stdout); err != nil {
+			t.Fatalf("err=%v", err)
+		}
+		if got := stdout.String(); !strings.Contains(got, `"record_id_list"`) || !strings.Contains(got, `"rec_1"`) || !strings.Contains(got, `"Alice"`) {
+			t.Fatalf("stdout=%s", got)
+		}
+	})
+
+	t.Run("batch update", func(t *testing.T) {
+		factory, stdout, reg := newExecuteFactory(t)
+		reg.Register(&httpmock.Stub{
+			Method: "POST",
+			URL:    "/open-apis/base/v3/bases/app_x/tables/tbl_x/records/batch_update",
+			Body: map[string]interface{}{
+				"code": 0,
+				"data": map[string]interface{}{
+					"has_more":       false,
+					"record_id_list": []interface{}{"rec_1"},
+					"update":         map[string]interface{}{"Status": "Done"},
+				},
+			},
+		})
+		if err := runShortcut(t, BaseRecordBatchUpdate, []string{"+record-batch-update", "--base-token", "app_x", "--table-id", "tbl_x", "--json", `{"record_id_list":["rec_1"],"patch":{"Status":"Done"}}`}, factory, stdout); err != nil {
+			t.Fatalf("err=%v", err)
+		}
+		if got := stdout.String(); !strings.Contains(got, `"record_id_list"`) || !strings.Contains(got, `"update"`) || !strings.Contains(got, `"Done"`) {
+			t.Fatalf("stdout=%s", got)
+		}
+	})
+
+	t.Run("batch update passthrough", func(t *testing.T) {
+		factory, stdout, reg := newExecuteFactory(t)
+		updateStub := &httpmock.Stub{
+			Method: "POST",
+			URL:    "/open-apis/base/v3/bases/app_x/tables/tbl_x/records/batch_update",
+			Body: map[string]interface{}{
+				"code": 0,
+				"data": map[string]interface{}{
+					"record_id_list": []interface{}{"rec_1"},
+				},
+			},
+		}
+		reg.Register(updateStub)
+		if err := runShortcut(t, BaseRecordBatchUpdate, []string{"+record-batch-update", "--base-token", "app_x", "--table-id", "tbl_x", "--json", `{"record_id_list":["rec_1"],"patch":{"Name":"Alice","Status":"Done"}}`}, factory, stdout); err != nil {
+			t.Fatalf("err=%v", err)
+		}
+		if got := stdout.String(); !strings.Contains(got, `"record_id_list"`) || !strings.Contains(got, `"rec_1"`) {
+			t.Fatalf("stdout=%s", got)
+		}
+		body := string(updateStub.CapturedBody)
+		if !strings.Contains(body, `"record_id_list":["rec_1"]`) || !strings.Contains(body, `"patch":{"Name":"Alice","Status":"Done"}`) {
+			t.Fatalf("request body=%s", body)
+		}
+	})
+
 	t.Run("delete", func(t *testing.T) {
 		factory, stdout, reg := newExecuteFactory(t)
 		reg.Register(&httpmock.Stub{
diff --git a/shortcuts/base/base_shortcuts_test.go b/shortcuts/base/base_shortcuts_test.go
index 8271f3cff..e3289e851 100644
--- a/shortcuts/base/base_shortcuts_test.go
+++ b/shortcuts/base/base_shortcuts_test.go
@@ -132,7 +132,7 @@ func TestShortcutsCatalog(t *testing.T) {
 		"+table-list", "+table-get", "+table-create", "+table-update", "+table-delete",
 		"+field-list", "+field-get", "+field-create", "+field-update", "+field-delete", "+field-search-options",
 		"+view-list", "+view-get", "+view-create", "+view-delete", "+view-get-filter", "+view-set-filter", "+view-get-visible-fields", "+view-set-visible-fields", "+view-get-group", "+view-set-group", "+view-get-sort", "+view-set-sort", "+view-get-timebar", "+view-set-timebar", "+view-get-card", "+view-set-card", "+view-rename",
-		"+record-list", "+record-search", "+record-get", "+record-upsert", "+record-upload-attachment", "+record-delete",
+		"+record-list", "+record-search", "+record-get", "+record-upsert", "+record-batch-create", "+record-batch-update", "+record-upload-attachment", "+record-delete",
 		"+record-history-list",
 		"+base-get", "+base-copy", "+base-create",
 		"+role-create", "+role-delete", "+role-update", "+role-list", "+role-get", "+advperm-enable", "+advperm-disable",
@@ -265,7 +265,6 @@ func TestBaseRecordValidate(t *testing.T) {
 		t.Fatalf("record upsert validate should be nil for API passthrough")
 	}
 }
-
 func TestBaseViewValidate(t *testing.T) {
 	ctx := context.Background()
 	if err := BaseViewCreate.Validate(ctx, newBaseTestRuntime(map[string]string{"base-token": "b", "table-id": "tbl_1", "json": `{"name":"Main"}`}, nil, nil)); err != nil {
diff --git a/shortcuts/base/record_batch_create.go b/shortcuts/base/record_batch_create.go
new file mode 100644
index 000000000..623a2caaf
--- /dev/null
+++ b/shortcuts/base/record_batch_create.go
@@ -0,0 +1,32 @@
+// Copyright (c) 2026 Lark Technologies Pte. Ltd.
+// SPDX-License-Identifier: MIT
+
+package base
+
+import (
+	"context"
+
+	"github.com/larksuite/cli/shortcuts/common"
+)
+
+var BaseRecordBatchCreate = common.Shortcut{
+	Service:     "base",
+	Command:     "+record-batch-create",
+	Description: "Batch create records",
+	Risk:        "write",
+	Scopes:      []string{"base:record:create"},
+	AuthTypes:   authTypes(),
+	Flags: []common.Flag{
+		baseTokenFlag(true),
+		tableRefFlag(true),
+		{Name: "json", Desc: "batch create JSON object", Required: true},
+	},
+	Tips: []string{
+		`Example: --json '{"fields":["Title","Status"],"rows":[["Task A","Open"],["Task B","Done"]]}'`,
+		"Agent hint: use the lark-base skill's record-batch-create guide for usage and limits.",
+	},
+	DryRun: dryRunRecordBatchCreate,
+	Execute: func(ctx context.Context, runtime *common.RuntimeContext) error {
+		return executeRecordBatchCreate(runtime)
+	},
+}
diff --git a/shortcuts/base/record_batch_update.go b/shortcuts/base/record_batch_update.go
new file mode 100644
index 000000000..a06fb177e
--- /dev/null
+++ b/shortcuts/base/record_batch_update.go
@@ -0,0 +1,32 @@
+// Copyright (c) 2026 Lark Technologies Pte. Ltd.
+// SPDX-License-Identifier: MIT
+
+package base
+
+import (
+	"context"
+
+	"github.com/larksuite/cli/shortcuts/common"
+)
+
+var BaseRecordBatchUpdate = common.Shortcut{
+	Service:     "base",
+	Command:     "+record-batch-update",
+	Description: "Batch update records",
+	Risk:        "write",
+	Scopes:      []string{"base:record:update"},
+	AuthTypes:   authTypes(),
+	Flags: []common.Flag{
+		baseTokenFlag(true),
+		tableRefFlag(true),
+		{Name: "json", Desc: "batch update JSON object", Required: true},
+	},
+	Tips: []string{
+		`Example: --json '{"record_id_list":["recXXX"],"patch":{"Status":"Done"}}'`,
+		"Agent hint: use the lark-base skill's record-batch-update guide for usage and limits.",
+	},
+	DryRun: dryRunRecordBatchUpdate,
+	Execute: func(ctx context.Context, runtime *common.RuntimeContext) error {
+		return executeRecordBatchUpdate(runtime)
+	},
+}
diff --git a/shortcuts/base/record_ops.go b/shortcuts/base/record_ops.go
index 294751af5..f91ca5799 100644
--- a/shortcuts/base/record_ops.go
+++ b/shortcuts/base/record_ops.go
@@ -69,6 +69,26 @@ func dryRunRecordUpsert(_ context.Context, runtime *common.RuntimeContext) *comm
 		Set("table_id", baseTableID(runtime))
 }
 
+func dryRunRecordBatchCreate(_ context.Context, runtime *common.RuntimeContext) *common.DryRunAPI {
+	pc := newParseCtx(runtime)
+	body, _ := parseJSONObject(pc, runtime.Str("json"), "json")
+	return common.NewDryRunAPI().
+		POST("/open-apis/base/v3/bases/:base_token/tables/:table_id/records/batch_create").
+		Body(body).
+		Set("base_token", runtime.Str("base-token")).
+		Set("table_id", baseTableID(runtime))
+}
+
+func dryRunRecordBatchUpdate(_ context.Context, runtime *common.RuntimeContext) *common.DryRunAPI {
+	pc := newParseCtx(runtime)
+	body, _ := parseJSONObject(pc, runtime.Str("json"), "json")
+	return common.NewDryRunAPI().
+		POST("/open-apis/base/v3/bases/:base_token/tables/:table_id/records/batch_update").
+		Body(body).
+		Set("base_token", runtime.Str("base-token")).
+		Set("table_id", baseTableID(runtime))
+}
+
 func dryRunRecordDelete(_ context.Context, runtime *common.RuntimeContext) *common.DryRunAPI {
 	return common.NewDryRunAPI().
 		DELETE("/open-apis/base/v3/bases/:base_token/tables/:table_id/records/:record_id").
@@ -99,6 +119,7 @@ func validateRecordJSON(runtime *common.RuntimeContext) error {
 func recordListFields(runtime *common.RuntimeContext) []string {
 	return runtime.StrArray("field-id")
 }
+
 func executeRecordList(runtime *common.RuntimeContext) error {
 	offset := runtime.Int("offset")
 	if offset < 0 {
@@ -168,6 +189,36 @@ func executeRecordUpsert(runtime *common.RuntimeContext) error {
 	return nil
 }
 
+func executeRecordBatchCreate(runtime *common.RuntimeContext) error {
+	pc := newParseCtx(runtime)
+	body, err := parseJSONObject(pc, runtime.Str("json"), "json")
+	if err != nil {
+		return err
+	}
+	result, err := baseV3Raw(runtime, "POST", baseV3Path("bases", runtime.Str("base-token"), "tables", baseTableID(runtime), "records", "batch_create"), nil, body)
+	data, err := handleBaseAPIResult(result, err, "batch create records")
+	if err != nil {
+		return err
+	}
+	runtime.Out(data, nil)
+	return nil
+}
+
+func executeRecordBatchUpdate(runtime *common.RuntimeContext) error {
+	pc := newParseCtx(runtime)
+	body, err := parseJSONObject(pc, runtime.Str("json"), "json")
+	if err != nil {
+		return err
+	}
+	result, err := baseV3Raw(runtime, "POST", baseV3Path("bases", runtime.Str("base-token"), "tables", baseTableID(runtime), "records", "batch_update"), nil, body)
+	data, err := handleBaseAPIResult(result, err, "batch update records")
+	if err != nil {
+		return err
+	}
+	runtime.Out(data, nil)
+	return nil
+}
+
 func executeRecordDelete(runtime *common.RuntimeContext) error {
 	_, err := baseV3Call(runtime, "DELETE", baseV3Path("bases", runtime.Str("base-token"), "tables", baseTableID(runtime), "records", runtime.Str("record-id")), nil, nil)
 	if err != nil {
diff --git a/shortcuts/base/shortcuts.go b/shortcuts/base/shortcuts.go
index fec6df727..2068e280a 100644
--- a/shortcuts/base/shortcuts.go
+++ b/shortcuts/base/shortcuts.go
@@ -40,6 +40,8 @@ func Shortcuts() []common.Shortcut {
 		BaseRecordSearch,
 		BaseRecordGet,
 		BaseRecordUpsert,
+		BaseRecordBatchCreate,
+		BaseRecordBatchUpdate,
 		BaseRecordUploadAttachment,
 		BaseRecordDelete,
 		BaseRecordHistoryList,
diff --git a/skills/lark-base/SKILL.md b/skills/lark-base/SKILL.md
index e4e76060b..0ed66538c 100644
--- a/skills/lark-base/SKILL.md
+++ b/skills/lark-base/SKILL.md
@@ -38,7 +38,7 @@ metadata:
 - 不要把 `+record-list / +record-search` 当聚合分析引擎
 - 不要没读 guide 就直接创建 formula / lookup 字段
 - 不要凭自然语言猜表名、字段名、公式表达式里的字段引用
-- 不要把系统字段、formula 字段、lookup 字段当成 `+record-upsert` 的写入目标
+- 不要把系统字段、formula 字段、lookup 字段当成 `+record-upsert / +record-batch-create / +record-batch-update` 的写入目标
 - 不要把“本地 Excel / CSV 导入成 Base”误判成 `+base-create`、`+table-create` 或 `+record-upsert`；这一步必须先走 `lark-cli drive +import --type bitable`
 - 不要在 Base 场景改走 `lark-cli api GET /open-apis/bitable/v1/...`
 - 不要因为 wiki 解析结果里的 `obj_type=bitable` 就去找 `bitable.*`；在本 CLI 里应继续使用 `lark-cli base +...`
@@ -46,10 +46,10 @@ metadata:
 ## Base 基本心智模型
 
 1. **Base 字段分三类**
-   - **存储字段**：真实存用户输入的数据，通常适合 `+record-upsert` 写入，例如文本、数字、日期、单选、多选、人员、关联。**附件字段例外**：对 agent 而言，文件上传必须走 `+record-upload-attachment`。
+   - **存储字段**：真实存用户输入的数据，通常适合 `+record-upsert / +record-batch-create / +record-batch-update` 写入，例如文本、数字、日期、单选、多选、人员、关联。**附件字段例外**：对 agent 而言，文件上传必须走 `+record-upload-attachment`。
    - **系统字段**：平台自动维护，只读，典型包括创建时间、最后更新时间、创建人、修改人、自动编号。
    - **计算字段**：通过表达式或跨表规则推导，只读，典型包括 **公式字段（formula）** 和 **查找引用字段（lookup）**。
-2. **写记录前先判断字段类别** — 只有存储字段可直接写；公式 / lookup / 创建时间 / 更新时间 / 创建人 / 修改人 / 自动编号都应视为只读输出字段，不能拿来做 `+record-upsert` 入参。
+2. **写记录前先判断字段类别** — 只有存储字段可直接写；公式 / lookup / 创建时间 / 更新时间 / 创建人 / 修改人 / 自动编号都应视为只读输出字段，不能拿来做 `+record-upsert / +record-batch-create / +record-batch-update` 入参。
 3. **Base 不只是存表数据，也能内建计算** — 用户提出“统计、比较、排名、文本拼接、日期差、跨表汇总、状态判断”等需求时，不能默认导出数据后手算；要先判断是否应通过 `+data-query` 或公式字段在 Base 内完成。
 
 ## 分析路径决策
@@ -109,7 +109,7 @@ metadata:
 
 ## 核心规则
 
-1. **只使用原子命令** — 使用 `+table-list / +table-get / +field-create / +record-upsert / +view-set-filter / +record-history-list / +base-get` 这类一命令一动作的写法，不使用旧聚合式 `+table / +field / +record / +view / +history / +workspace`
+1. **只使用原子命令** — 使用 `+table-list / +table-get / +field-create / +record-upsert / +record-batch-create / +record-batch-update / +view-set-filter / +record-history-list / +base-get` 这类一命令一动作的写法，不使用旧聚合式 `+table / +field / +record / +view / +history / +workspace`
 2. **写记录前先读字段结构** — 先调用 `+field-list` 获取字段结构，再读 [lark-base-shortcut-record-value.md](references/lark-base-shortcut-record-value.md) 确认各字段类型的写入值格式
 3. **写字段前先看字段属性规范** — 先读 [lark-base-shortcut-field-properties.md](references/lark-base-shortcut-field-properties.md) 确认 `+field-create/+field-update` 的 JSON 结构
 4. **筛选查询按场景执行** — 先读 [lark-base-view-set-filter.md](references/lark-base-view-set-filter.md)、[lark-base-record-list.md](references/lark-base-record-list.md)、[lark-base-record-search.md](references/lark-base-record-search.md)；默认优先 `+record-list`，仅当用户提供明确搜索关键词时使用 `+record-search`；视图筛选读取用 `+view-set-filter` + `+record-list`
@@ -143,6 +143,8 @@ metadata:
 | 关键词搜索记录 | `lark-cli base +record-search` | 透传搜索参数；用于关键词检索，不用于聚合分析 |
 | 列表 / 获取记录 | `lark-cli base +record-list` / `+record-get` | 原子命令，如果需要`聚合计算`，`分组统计` 推荐走 `+data-query` |
 | 创建 / 更新记录 | `lark-cli base +record-upsert` | `--table-id [--record-id] --json` |
+| 批量创建记录 | `lark-cli base +record-batch-create` | 适合大量创建写入（如 CSV/Excel 导入）；先按 record-value 规范整理为 `json.fields + json.rows` |
+| 批量更新指定记录 | `lark-cli base +record-batch-update` | `--table-id --json`（`json.record_id_list + json.patch`） |
 | 聚合分析 / 比较排序 / 求最值 / 筛选统计 | `lark-cli base +data-query` | 不要用 `+record-list / +record-search` 拉全量数据再手动计算，需使用 `+data-query` 走服务端计算 |
 | 配置 / 查询视图 | `lark-cli base +view-*` | `list/get/create/delete/get-*/set-*/rename` |
 | 查看记录历史 | `lark-cli base +record-history-list` | 按表和记录查询变更历史 |
@@ -169,6 +171,7 @@ metadata:
 - **记录读取字段筛选**：`+record-list` 支持重复传参 `--field-id` 做字段筛选
 - **`+record-list / +record-search` 选择规则**：优先使用 `+record-list`；仅当用户给出明确搜索关键词时，才使用 `+record-search`
 - **`+record-search` 使用规则**：仅通过 `--json` 传搜索请求体；`keyword/search_fields/offset/limit` 等字段合法性由 API 侧按 schema 校验
+- **`+record-batch-create` 适用边界**：优先用于大量创建写入（如 CSV/Excel 导入）。当输入是长表格或长文本时，先按 [lark-base-shortcut-record-value.md](references/lark-base-shortcut-record-value.md) 做字段映射和类型规范化，再组装 `fields + rows` 调用命令写入
 - **字段可写性先判断**：存储字段才可写；公式 / lookup / 系统字段默认只读，写记录时应跳过
 - **公式能力要主动想到**：用户说“算一下”“生成标签”“判断是否异常”“跨表汇总”“按日期差预警”时，要先判断是否应该建公式字段，而不是只返回手工分析方案
 - **lookup 不是默认首选**：lookup 只在用户明确要求或确实更适合固定查找模型时使用；常规计算、跨表聚合和条件判断优先 formula
@@ -277,9 +280,11 @@ https://{domain}/base/{base-token}?table={table-id}&view={view-id}
 
 ## 参考文档
 
-- [lark-base-shortcut-field-properties.md](references/lark-base-shortcut-field-properties.md) — `+field-create/+field-update` JSON 规范（推荐）
+- [lark-base-shortcut-field-properties.md](references/lark-base-shortcut-field-properties.md) — `+field-create/+field-update` 调用前必看，各类型 field JSON 规范
 - [role-config.md](references/role-config.md) — 角色权限配置详解
-- [lark-base-shortcut-record-value.md](references/lark-base-shortcut-record-value.md) — `+record-upsert` 值格式规范（推荐）
+- [lark-base-shortcut-record-value.md](references/lark-base-shortcut-record-value.md) — record 写入（`+record-upsert / +record-batch-create / +record-batch-update`）调用前必看，各类型 record JSON 规范
+- [lark-base-record-batch-create.md](references/lark-base-record-batch-create.md) — `+record-batch-create` 用法与 `--json` 结构
+- [lark-base-record-batch-update.md](references/lark-base-record-batch-update.md) — `+record-batch-update` 用法与 `--json` 结构
 - [formula-field-guide.md](references/formula-field-guide.md) — formula 字段写法、函数约束、CurrentValue 规则、跨表计算模式（强烈推荐）
 - [lookup-field-guide.md](references/lookup-field-guide.md) — lookup 字段配置规则、where/aggregate 约束、与 formula 的取舍
 - [lark-base-view-set-filter.md](references/lark-base-view-set-filter.md) — 视图筛选配置
@@ -307,7 +312,7 @@ https://{domain}/base/{base-token}?table={table-id}&view={view-id}
 |----------|------|
 | [`table commands`](references/lark-base-table.md) | `+table-list / +table-get / +table-create / +table-update / +table-delete` |
 | [`field commands`](references/lark-base-field.md) | `+field-list / +field-get / +field-create / +field-update / +field-delete / +field-search-options` |
-| [`record commands`](references/lark-base-record.md) | `+record-search / +record-list / +record-get / +record-upsert / +record-upload-attachment / +record-delete` |
+| [`record commands`](references/lark-base-record.md) | `+record-search / +record-list / +record-get / +record-upsert / +record-batch-create / +record-batch-update / +record-upload-attachment / +record-delete` |
 | [`view commands`](references/lark-base-view.md) | `+view-list / +view-get / +view-create / +view-delete / +view-get-* / +view-set-* / +view-rename` |
 | [`data-query commands`](references/lark-base-data-query.md) | `+data-query` |
 | [`history commands`](references/lark-base-history.md) | `+record-history-list` |
diff --git a/skills/lark-base/references/lark-base-record-batch-create.md b/skills/lark-base/references/lark-base-record-batch-create.md
new file mode 100644
index 000000000..803883c25
--- /dev/null
+++ b/skills/lark-base/references/lark-base-record-batch-create.md
@@ -0,0 +1,76 @@
+# base +record-batch-create
+
+> **前置条件：** 先阅读 [`../lark-shared/SKILL.md`](../../lark-shared/SKILL.md) 了解认证、全局参数和安全规则。
+
+批量创建记录。
+
+## 适用场景（重点）
+
+- 适合大量创建写入场景，例如导入 CSV / Excel、外部系统一次性写入新数据。
+- 当输入是长表格或长文本数据时，先按 [lark-base-shortcut-record-value.md](lark-base-shortcut-record-value.md) 做字段映射和类型规范化，再组装 `fields + rows` 调用本命令写入。
+
+## 推荐命令
+
+```bash
+lark-cli base +record-batch-create \
+  --base-token XXXXXX \
+  --table-id tblXXX \
+  --json '{"fields":["标题","状态"],"rows":[["任务 A","Open"],["任务 B","Done"]]}'
+```
+
+```bash
+lark-cli base +record-batch-create \
+  --base-token XXXXXX \
+  --table-id tblXXX \
+  --json @batch-create.json
+```
+
+## 参数
+
+| 参数 | 必填 | 说明 |
+|------|------|------|
+| `--base-token <token>` | 是 | Base Token |
+| `--table-id <id_or_name>` | 是 | 表 ID 或表名 |
+| `--json <body>` | 是 | 批量创建请求体，必须是 JSON 对象。支持直接传 JSON 字符串，或 `@<file_path>` 从文件读取 |
+
+## API 入参详情
+
+**HTTP 方法和路径：**
+
+```http
+POST /open-apis/base/v3/bases/:base_token/tables/:table_id/records/batch_create
+```
+
+## `--json` 结构
+
+对象形态：`{"fields":[...],"rows":[...]}`。
+
+| 字段 | 类型 | 必填 | 说明 |
+|------|------|------|------|
+| `fields` | `string[]` | 是 | 字段 ID 或字段名数组 |
+| `rows` | `any[][]` | 是 | 二维数组，每一行按 `fields` 同序给值；单次最多 200 行 |
+
+## 返回重点
+
+`data` 为多行二维数组，与 `+record-list` 返回的多行数据结构一致（按 `fields` 列顺序对齐）。
+
+| 字段 | 类型 | 说明 |
+|------|------|------|
+| `fields` | `string[]` | 返回的字段名数组 |
+| `field_id_list` | `string[]` | 返回的字段 ID 数组 |
+| `record_id_list` | `string[]` | 新创建记录 ID 列表 |
+| `data` | `any[][]` | 与 `fields` 对齐的多行数据 |
+| `ignored_fields` | `array` | 可选，表示被忽略的字段信息 |
+
+## 坑点
+
+- ⚠️ `--json` 必须是对象。
+- ⚠️ 写 `rows` 前必须先阅读 [lark-base-shortcut-record-value.md](lark-base-shortcut-record-value.md)，按字段类型填值，禁止按自然语言猜测 value 结构。
+- ⚠️ `fields` 与 `rows` 列顺序必须一一对应。
+- ⚠️ 空单元格可以显式用 `null` 填充。
+- ⚠️ 单次最多 200 行，超出需分批写入。
+
+## 参考
+
+- [lark-base-record.md](lark-base-record.md) — record 索引页
+- [lark-base-shortcut-record-value.md](lark-base-shortcut-record-value.md) — 记录值格式规范
diff --git a/skills/lark-base/references/lark-base-record-batch-update.md b/skills/lark-base/references/lark-base-record-batch-update.md
new file mode 100644
index 000000000..7014e2dfa
--- /dev/null
+++ b/skills/lark-base/references/lark-base-record-batch-update.md
@@ -0,0 +1,71 @@
+# base +record-batch-update (batch update)
+
+> **前置条件：** 先阅读 [`../lark-shared/SKILL.md`](../../lark-shared/SKILL.md) 了解认证、全局参数和安全规则。
+
+批量更新记录（将同一份 `patch` 批量应用到一批 `record_id_list`）。
+
+## 推荐命令
+
+```bash
+lark-cli base +record-batch-update \
+  --base-token XXXXXX \
+  --table-id tblXXX \
+  --json '{"record_id_list":["recXXX"],"patch":{"field_id_or_name":"value"}}'
+```
+
+```bash
+lark-cli base +record-batch-update \
+  --base-token XXXXXX \
+  --table-id tblXXX \
+  --json @batch-update.json
+```
+
+## 参数
+
+| 参数 | 必填 | 说明 |
+|------|------|------|
+| `--base-token <token>` | 是 | Base Token |
+| `--table-id <id_or_name>` | 是 | 表 ID 或表名 |
+| `--json <body>` | 是 | 批量更新请求体，必须是 JSON 对象。支持直接传 JSON 字符串，或 `@<file_path>` 从文件读取 |
+
+## 生成 `patch` 前必看
+
+- 先阅读 [lark-base-shortcut-record-value.md](lark-base-shortcut-record-value.md)，按字段类型构造 `patch` 的 value，避免类型不匹配。
+
+## API 入参详情
+
+**HTTP 方法和路径：**
+
+```http
+POST /open-apis/base/v3/bases/:base_token/tables/:table_id/records/batch_update
+```
+
+## `--json` 结构
+
+对象形态：`{"record_id_list":[...],"patch":{...}}`。
+
+| 字段 | 类型 | 必填 | 说明 |
+|------|------|------|------|
+| `record_id_list` | `string[]` | 是 | 要更新的记录 ID 列表（单次最多 200 条） |
+| `patch` | `object` | 是 | 同一份字段更新对象，会应用到 `record_id_list` 内所有记录 |
+
+## 返回重点
+
+返回结构如下（其中 `update` 可与 `+record-list` 的单行字段对象结构对齐）：
+
+| 字段 | 类型 | 说明 |
+|------|------|------|
+| `record_id_list` | `string[]` | 本次更新到的记录 ID 列表 |
+| `update` | `object` | 本次应用的字段更新结果；可能为空对象 |
+| `ignored_fields` | `{id,name,reason}[]` | 可选，被忽略字段信息 |
+
+## 坑点
+
+- ⚠️ `--json` 必须是对象。
+- ⚠️ 该接口是“同值批量更新”：同一请求内所有 `record_id_list` 都会应用同一份 `patch`。
+- ⚠️ `record_id_list` 最大 200 条，超过会被接口校验拒绝。
+- ⚠️ 命令不会自动做字段/行映射转换，传什么就发什么。
+
+## 参考
+
+- [lark-base-record.md](lark-base-record.md) — record 索引页
diff --git a/skills/lark-base/references/lark-base-record.md b/skills/lark-base/references/lark-base-record.md
index 0546ac7a4..3d82352b6 100644
--- a/skills/lark-base/references/lark-base-record.md
+++ b/skills/lark-base/references/lark-base-record.md
@@ -12,6 +12,8 @@ record 相关命令索引。
 | [lark-base-record-list.md](lark-base-record-list.md) | `+record-list` | 分页列记录 |
 | [lark-base-record-get.md](lark-base-record-get.md) | `+record-get` | 获取单条记录 |
 | [lark-base-record-upsert.md](lark-base-record-upsert.md) | `+record-upsert` | 创建或更新记录 |
+| [lark-base-record-batch-create.md](lark-base-record-batch-create.md) | `+record-batch-create` | 按 `fields/rows` 批量创建记录 |
+| [lark-base-record-batch-update.md](lark-base-record-batch-update.md) | `+record-batch-update` | 批量更新记录 |
 | [lark-base-record-upload-attachment.md](lark-base-record-upload-attachment.md) | `+record-upload-attachment` | 上传本地文件到附件字段并更新记录 |
 | [lark-base-record-delete.md](lark-base-record-delete.md) | `+record-delete` | 删除记录 |