approval-summarization
Summarize approval requests with context including what is being requested, who is requesting, business justification, and similar past approvals
Happy Technologies LLC · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add Happy-Technologies-LLC/happy-platform-skills --skill approval-summarization技能说明
name: approval-summarization version: 1.0.1 description: Summarize approval requests with context including what is being requested, who is requesting, business justification, and similar past approvals author: Happy Technologies LLC tags: [catalog, approval, summarization, employee-experience, approver, request, context, decision-support] platforms: [claude-code, claude-desktop, chatgpt, cursor, any] tools: mcp: - SN-Query-Table - SN-Get-Record - SN-Natural-Language-Search - SN-Execute-Background-Script - SN-Add-Work-Notes rest: - /api/now/table/sc_request - /api/now/table/sc_req_item - /api/now/table/sysapproval_approver - /api/now/table/sc_cat_item - /api/now/table/item_option_new - /api/now/table/sc_item_option_mtom - /api/now/table/sys_user native: - Bash complexity: intermediate estimated_time: 10-25 minutes
Approval Summarization
Overview
This skill generates comprehensive approval summaries that give approvers the context they need to make informed decisions. It covers:
- Retrieving approval requests from
sysapproval_approverwith full request and item context - Enriching approvals with requester profile data from
sys_userincluding role, department, and manager - Extracting variable values (form responses) from
sc_req_itemto show exactly what was requested - Analyzing historical approval patterns from
sc_requestfor similar requests - Generating structured approval summaries with recommendation signals
- Identifying cost, risk, and compliance considerations for each approval
When to use: When approvers need a quick, comprehensive summary of pending approvals, when building approval digest notifications, or when creating approval dashboards with contextual data.
Value proposition: Reduces approval decision time by presenting all relevant context in a single view, decreases approval bottlenecks, and improves decision quality by surfacing historical precedent and risk factors.
Prerequisites
- Roles:
approver_user,itil, oradmin - Access: Read access to
sysapproval_approver,sc_request,sc_req_item,sc_cat_item,item_option_new, andsys_user - Knowledge: Understanding of organizational approval policies and delegation rules
Procedure
Step 1: Retrieve Pending Approvals
Query for all approvals awaiting action by a specific approver or group.
Using MCP (Claude Code/Desktop):
Tool: SN-Query-Table
Parameters:
table_name: sysapproval_approver
query: approver=[approver_sys_id]^state=requested
fields: sys_id,sysapproval,sysapproval.number,sysapproval.short_description,sysapproval.sys_class_name,state,approver,group,sys_created_on,due_date,expected_start,comments
limit: 25
order_by: sys_created_on
Using REST API:
GET /api/now/table/sysapproval_approver?sysparm_query=approver=[approver_sys_id]^state=requested&sysparm_fields=sys_id,sysapproval,sysapproval.number,sysapproval.short_description,sysapproval.sys_class_name,state,approver,group,sys_created_on,due_date,comments&sysparm_limit=25&sysparm_display_value=true
Get group approvals:
Tool: SN-Query-Table
Parameters:
table_name: sysapproval_approver
query: group=[group_sys_id]^state=requested
fields: sys_id,sysapproval.number,sysapproval.short_description,state,group,sys_created_on,due_date
limit: 25
Step 2: Retrieve Request and Requested Item Details
For each approval, pull the full request and item context.
Get the requested item details:
Tool: SN-Query-Table
Parameters:
table_name: sc_req_item
query: request=[request_sys_id]
fields: sys_id,number,cat_item,cat_item.name,cat_item.short_description,cat_item.price,quantity,requested_for,requested_for.name,requested_for.department,requested_for.manager,opened_by,opened_by.name,stage,state,price,description
limit: 10
Using REST API:
GET /api/now/table/sc_req_item?sysparm_query=request=[request_sys_id]&sysparm_fields=sys_id,number,cat_item,cat_item.name,cat_item.short_description,cat_item.price,quantity,requested_for,requested_for.name,requested_for.department,requested_for.manager,opened_by,opened_by.name,stage,state,price,description&sysparm_limit=10&sysparm_display_value=true
Step 3: Extract Variable Values (Form Responses)
Retrieve the specific answers the requester provided on the catalog item form.
Using MCP:
Tool: SN-Query-Table
Parameters:
table_name: sc_item_option_mtom
query: request_item=[ritm_sys_id]
fields: sc_item_option.item_option_new.question_text,sc_item_option.value,sc_item_option.item_option_new.name,sc_item_option.item_option_new.type
limit: 30
Using background script for clean variable extraction:
Tool: SN-Execute-Background-Script
Parameters:
description: Extract catalog variable values for RITM
script: |
var ritmId = '[ritm_sys_id]';
var ritm = new GlideRecord('sc_req_item');
ritm.get(ritmId);
var variables = [];
var opts = new GlideRecord('sc_item_option_mtom');
opts.addQuery('request_item', ritmId);
opts.query();
while (opts.next()) {
var option = opts.sc_item_option;
var varDef = option.item_option_new;
if (varDef) {
variables.push({
question: varDef.question_text.toString(),
answer: option.value.getDisplayValue(),
variable_name: varDef.name.toString(),
mandatory: varDef.mandatory.toString() === 'true'
});
}
}
var result = {
ritm_number: ritm.number.toString(),
item_name: ritm.cat_item.getDisplayValue(),
requested_for: ritm.requested_for.getDisplayValue(),
department: ritm.requested_for.department.getDisplayValue(),
variables: variables
};
gs.info(JSON.stringify(result, null, 2));
Step 4: Retrieve Requester Context
Gather relevant information about the person making the request.
Using MCP:
Tool: SN-Query-Table
Par
阅读完整来源 ↗