Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Knowledgebase Article Generator

    1

    Identifies recurring support issues and transforms resolved tickets into PII-scrubbed knowledge base articles.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Knowledgebase Article Generator

    Knowledgebase Article Generator

    Example session with this skill installed

    Analyze tickets.csv for clusters with at least 5 tickets and draft an internal article for the most frequent issue not found in the /kb directory.

    • Read your context and instructions
    • Compiled the knowledgebase article generator

    I analyzed 450 tickets and identified 8 recurring clusters. One high-impact cluster regarding "VPN Authentication Timeouts" is missing from your /kb directory. I have drafted an internal technician article based on 12 related tickets.

    KB Draft: Troubleshooting VPN Authentication Timeouts (Internal)

    Article ID: KB-DRAFT-001
    Source Tickets: INC-8821, INC-8845, INC-8902, INC-8915 [+8 others]
    Audience: Internal Technician
    Category: Networking / Remote Access

    Symptoms

    • Users report "GlobalProtect Connection Timed Out" after entering MFA credentials.
    • Issue occurs primarily on macOS Sonoma clients.
    • Intermittent connectivity loss when switching from Wi-Fi to Ethernet.

    Scope

    • Systems: Palo Alto GlobalProtect, Okta MFA, macOS Sonoma.
    • Impact: High. Affects remote employees using company-managed laptops.

    Resolution Steps

    1. Clear Local Cache: Navigate to /Library/Logs/PaloAltoNetworks/GlobalProtect/ and clear the local state files.
    2. Refresh Gateway: Force a manual gateway selection in the GlobalProtect settings menu.

    Verify MTU Settings: Ensure the MTU on the virtual adapter is set to 1400 (common fix for home ISP encapsulation issues).
    4. Keychain Check: Delete the 'GlobalProtect' entry in Keychain Access and re-authenticate.

    Escalation Path

    If symptoms persist after step 4, escalate to the Network Infrastructure team via Jira (NET-OPS queue) with the user's public IP and client logs attached.

    Next steps

    • Review the drafted resolution steps for accuracy against your current firewall policies.
    • Move the file from kb/drafts/ to your production kb/networking/ folder.
    • Run the draft command again for the "Printer Spooler Error" cluster (9 tickets).

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Service desks waste hours resolving the same issues because solutions live in ticket history rather than a searchable database. This skill identifies recurring problems and converts resolved ticket threads into structured knowledge base articles.

    What it does

    • Issue clustering groups tickets by subject and description to identify high-frequency problems.
    • Gap analysis compares identified clusters against your existing KB directory to prevent duplicate content.
    • Automatic drafting generates Markdown articles featuring symptoms, scope, and resolution steps.
    • PII scrubbing removes requester emails, phone numbers, IP addresses, and names from the final drafts.
    • Audience targeting creates either technician-focused internal documentation or simplified end-user guides.

    How it works

    1. Analyze your ticket CSV to surface clusters of similar issues ranked by volume.
    2. Filter against your current knowledge base to see which clusters lack documentation.
    3. Draft articles by merging resolution notes from multiple tickets into a single logical sequence.
    4. Review the output Markdown files for environment-specific details before publishing.

    Frameworks & tools

    This skill uses a Python-based CLI (kb_gen.py) and processes data in CSV format. It outputs standard GitHub-flavored Markdown compatible with Zendesk, ServiceNow, or static site generators.

    Why this beats prompting it yourself

    Generic prompts often fail to merge contradictory resolution notes from multiple agents or forget to scrub PII. This skill enforces a consistent structure across every article and ensures you only write documentation for issues that actually drive ticket volume.

    Use cases

    • Ticket deflection to build a self-service portal based on the most common user complaints.
    • Tech onboarding to create a technical runbook for new service desk agents.
    • KB auditing to find gaps in existing documentation using historical ticket data.

    Known limitations

    Requires a CSV with specific headers: id, subject, description, and resolution_notes. Accuracy depends on the quality of agent resolution notes in the source tickets.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Technical Documentation.

    Requires CSV headers: id, subject, description, resolution_notes. Accuracy depends on the quality of original agent notes. Review drafts for environment-specific data before publishing.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Permissions

    Terminal / Shell
    Listed1 month ago
    Updated27 days ago

    What's inside

    Frequently Asked Questions

    The skill requires a CSV file containing four specific headers: 'id', 'subject', 'description', and 'resolution_notes'. This allows the tool to accurately cluster recurring issues and synthesize multiple ticket resolutions into a single, cohesive article.

    The tool includes a robust PII scrubbing layer that automatically identifies and removes sensitive information such as requester names, phone numbers, email addresses, and IP addresses. This ensures your generated documentation is safe for public-facing portals or internal sharing without violating privacy policies.

    Unlike manual prompting, this skill performs 'Gap Analysis' by comparing ticket clusters against your existing documentation library. This ensures the AI only drafts new content for undocumented issues, preventing duplicates and focusing your efforts on actual knowledge gaps.

    The skill outputs standard GitHub-flavored Markdown files, which are natively supported by major platforms like Zendesk and ServiceNow. You can also easily upload these files to static site generators or internal wikis with minimal formatting changes.

    The generated articles are structured into logical sections including 'Symptoms', 'Scope', and 'Resolution Steps'. This professional formatting ensures that even if individual tickets contain messy notes, the final output is a clean, readable guide for either technicians or end-users.

    New in Technical Documentation