Triage Alert logo

Triage Alert

Community
dandye
triage-alert

Triage a security alert or case. Use when given an ALERT_ID or CASE_ID to assess if it's a real threat. Enriches IOCs, searches SIEM for context, and determines if the alert should be closed (false positive) or escalated for investigation.

Overview

Publisherdandye
Repositoryai-runbooks
Skill nametriage-alert
Stars
126
Forks
34
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by dandye on GitHub. Read the source before you install it.

Installation

Install the Triage Alert AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/dandye/ai-runbooks.git /tmp/ai-runbooks
mkdir -p .claude/skills
cp -r /tmp/ai-runbooks/skills/triage-alert .claude/skills/triage-alert
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Triage Alert in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Triage Alert on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Triage Alert is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Alert Triage Skill

Perform standardized initial assessment of security alerts to determine if they represent real threats requiring investigation or can be closed as false positives.

Inputs

You need one of these identifiers to begin:

  • ALERT_ID - The alert identifier
  • CASE_ID - The case identifier

Workflow

Step 1: Gather Initial Context

Retrieve full details about the alert/case:

Use secops-soar tools:
- get_case_full_details(case_id) - Get case metadata and context
- list_alerts_by_case(case_id) - List all alerts in the case
- list_events_by_alert(alert_id) - Get triggering events

Extract and note:

  • Alert type and severity
  • Key entities involved (IPs, domains, hashes, users, hostnames)
  • Triggering events and timestamps

Note: Duplicate detection should be handled by invoking /check-duplicates before this skill, or by using the /full-triage-alert workflow which orchestrates both skills in the correct sequence.

Step 2: Find Related Open Cases

Search for other open cases involving the same entities:

Use secops-soar.list_cases with:
- Search terms = key entities from Step 1
- Status filter = "Opened"

Note any related cases for correlation.

Step 3: Alert-Specific SIEM Search

Perform a targeted SIEM search based on the alert type:

Use secops-mcp.search_security_events with relevant query

By alert type:

  • Suspicious Login: Search login events (success/failure) for user/source IP around alert time
  • Malware Detection: Search process execution, file mods, network events for the hash/endpoint
  • Network Alert: Search network flows, DNS lookups for source/destination IPs/domains

Step 4: Enrich Key Entities

For each key entity (IP, domain, hash, URL), gather threat intelligence:

GTI Enrichment (use gti-mcp tools):

  • get_ip_address_report(ip) - IP reputation and context
  • get_domain_report(domain) - Domain reputation
  • get_file_report(hash) - File/hash analysis
  • get_url_report(url) - URL reputation

SIEM Enrichment (use secops-mcp tools):

  • lookup_entity(entity) - Entity summary from SIEM
  • get_ioc_matches(hours_back) - Check if IOC appears in threat feeds

Step 5: Make Assessment

Based on all gathered evidence, classify the alert:

ClassificationCriteriaAction
False Positive (FP)No malicious indicators, known benign activityClose
Benign True Positive (BTP)Real detection but authorized/expected activityClose
True Positive (TP)Confirmed malicious indicators or suspicious behaviorEscalate
SuspiciousInconclusive but warrants investigationEscalate

Step 6: Take Action

If FP or BTP:

  1. Document findings in case comments explaining the rationale
  2. Close the case/alert:
    • Use secops-soar.siemplify_close_case or siemplify_close_alert
    • Closure reason: NOT_MALICIOUS
    • Root cause: Use get_case_settings_root_causes to get valid options (e.g., "Legit action", "Normal behavior")

If TP or Suspicious:

  1. Optionally adjust priority with secops-soar.change_case_priority
  2. Document initial findings and assessment in case comments
  3. Escalate to Tier 2 or trigger appropriate investigation runbook:
    • Suspicious login → suspicious_login_triage
    • Malware → malware_triage
    • IOC-focused → deep_dive_ioc_analysis

Output Requirements

After completing triage, provide:

  1. Alert Status: Closed (with reason) or Escalated
  2. Classification: FP, BTP, TP, or Suspicious
  3. Evidence Summary: Key findings from enrichment and SIEM searches
  4. Rationale: Why this classification was chosen
  5. Next Steps: What happens next (closed, assigned to whom, which runbook triggered)

Quick Reference

SOAR Tools:

  • get_case_full_details, list_alerts_by_case, list_events_by_alert
  • post_case_comment, change_case_priority
  • siemplify_get_similar_cases, siemplify_close_case, siemplify_close_alert

SIEM Tools:

  • lookup_entity, get_ioc_matches, search_security_events

GTI Tools:

  • get_file_report, get_domain_report, get_ip_address_report, get_url_report

For detailed workflow diagrams, completion criteria, and evaluation rubric, see reference.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Triage Alert AI skill do?

Triage a security alert or case. Use when given an ALERT_ID or CASE_ID to assess if it's a real threat. Enriches IOCs, searches SIEM for context, and determines if the alert should be closed (false positive) or escalated for investigation.

Why use Triage Alert on TypingMind?

Because you install it once and use it with any model. Triage Alert is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Triage Alert in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dandye/ai-runbooks/tree/main/skills/triage-alert. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Triage Alert?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Triage Alert?

As many as you like. As long as a model supports skills, you can use Triage Alert with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Triage Alert AI skill free?

Yes. It is published on GitHub by dandye under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇