happy-technologies-llc/happy-platform-skills/sidebar-summarization
Claude Code and agent skill by happy-technologies-llc/happy-platform-skills
- community
Checking that the SKILL.md file is still in the repository.
Generate sidebar summaries for customer service agents with case context, customer history, and recommended actions to accelerate case handling
Install
npx vskill@latest install happy-technologies-llc/happy-platform-skills/sidebar-summarizationSKILL.md
Sidebar Summarization
Overview
This skill generates concise sidebar summaries for customer service agents working in Agent Workspace. When an agent opens or is assigned a case, the sidebar summary provides instant context without requiring the agent to read through the entire case history. It covers:
- Generating a compact case overview with priority, status, and age
- Pulling customer history including past cases, interactions, and satisfaction scores
- Summarizing the consumer profile and account tier for entitlement context
- Identifying related or similar cases that may indicate a broader issue
- Recommending next-best actions based on case category and resolution patterns
- Highlighting SLA status and any escalation risks
When to use: When agents need rapid context upon accepting a case, during live chat or phone interactions, or when reviewing a queue of assigned cases.
Value proposition: Reduces average handle time by providing agents with pre-assembled case context, customer history, and actionable recommendations in a scannable sidebar format. Eliminates the need to manually navigate between multiple records to build context.
Prerequisites
- Plugins: Customer Service Management (
com.sn_customerservice) must be active - Roles:
sn_customerservice_agent,sn_customerservice_manager, orcsm_admin - Access: Read access to
sn_customerservice_case,interaction,csm_consumer,customer_account,customer_contact,sys_journal_field, andkb_knowledgetables - Knowledge: Familiarity with Agent Workspace sidebar components and CSM case lifecycle
Procedure
Step 1: Retrieve the Active Case Details
Fetch the case currently open in the agent's workspace.
Using MCP (Claude Code/Desktop):
Using REST API:
Step 2: Retrieve Consumer Profile
Fetch the consumer record to understand the customer's profile and history summary.
Using MCP:
Using REST API:
Step 3: Pull Customer Account Context
Retrieve account-level details for entitlement and priority context.
Using MCP:
Using REST API:
Step 4: Retrieve Customer Case History
Query recent cases for the same consumer or account to identify patterns.
Using MCP:
Using REST API:
Step 5: Retrieve Recent Interactions
Pull the latest interactions for the case and the consumer.
Using MCP:
For consumer-level interaction history:
Using REST API:
Step 6: Check for Related Knowledge Articles
Search for knowledge articles matching the case category and product.
Using MCP:
Using REST API:
Step 7: Retrieve Latest Work Notes
Pull the most recent work notes for quick context on current progress.
Using MCP:
Using REST API:
Step 8: Assemble the Sidebar Summary
Compile all gathered data into a compact sidebar format:
Tool Usage
MCP Tools Reference
| Tool | When to Use | |
|---|---|---|
SN-Natural-Language-Search | Natural language lookup for cases, consumers, or knowledge articles | |
SN-Query-Table | Structured queries across case, interaction, consumer, and KB tables | |
SN-Get-Record | Retrieve a single case or consumer record by sys_id |
REST API Reference
| Endpoint | Method | Purpose | |
|---|---|---|---|
/api/now/table/sn_customerservice_case | GET | Query case records | |
/api/now/table/interaction | GET | Retrieve case and consumer interactions | |
/api/now/table/csm_consumer | GET | Consumer profile details | |
/api/now/table/customer_account | GET | Account tier and entitlement info | |
/api/now/table/customer_contact | GET | Contact preferences and details | |
/api/now/table/sys_journal_field | GET | Work notes and comments | |
/api/now/table/kb_knowledge | GET | Knowledge article recommendations |
Best Practices
- Keep summaries concise: Sidebar space is limited; aim for scannable bullet points rather than paragraphs
- Prioritize actionable information: Lead with status, SLA risk, and recommended next steps
- Show customer sentiment: If sentiment analysis data is available, include the latest sentiment score
- Highlight repeat contacts: Flag if the customer has contacted support multiple times for the same issue
- Include entitlement context: Account tier affects SLA targets and available support channels
- Refresh on case update: Sidebar summaries should be regenerated when significant case changes occur
- Respect privacy: Only display customer PII appropriate for the agent's role and jurisdiction
- Calculate case age dynamically: Display age in human-readable format (hours, days) relative to current time
Troubleshooting
"Consumer record not found"
Cause: The case may not have a consumer linked, or the consumer was created as an anonymous contact. Solution: Fall back to the contact field on the case. Query customer_contact instead of csm_consumer using the contact sys_id.
"No case history available"
Cause: This may be the customer's first case, or historical cases are archived. Solution: Expand the search to account-level cases using account=[account_sys_id] instead of filtering by consumer.
"Knowledge articles not relevant"
Cause: The category-based search may return generic articles. Solution: Use SN-Natural-Language-Search with the case short_description for semantic matching. Combine category and product filters for more targeted results.
"SLA information missing"
Cause: SLA definitions may not be configured for the case type or priority. Solution: Query task_sla with task=[case_sys_id] to check if SLAs are attached. Consult CSM admin if SLAs are tracked externally.
"Interaction records return empty"
Cause: Interactions may be stored with a different parent reference or the channel integration may not create interaction records. Solution: Check if interactions use document instead of parent as the reference field. Also query sys_journal_field for comments that may capture interaction history.
Examples
Example 1: Live Chat Sidebar Context
Scenario: Agent accepts an incoming chat and needs instant context.
Step 1 - Get case from interaction:
Step 2 - Build sidebar from parent case:
Output:
Example 2: Queue Review Sidebar Summaries
Scenario: Agent reviewing their assigned case queue needs summaries for each case.
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/csm/sidebar-summarization/SKILL.md
Popularity
- Repository stars
- 29
- Repository forks
- 11
- 7-day trend score
- 17
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/happy-technologies-llc/happy-platform-skills/sidebar-summarization)