Full Alert Triage logo

Full Alert Triage

Community
dandye
full-alert-triage

Complete Tier 1 triage workflow. Orchestrates the full alert triage process: check-duplicates, triage-alert, enrich-ioc for each entity, and either close (FP/BTP) or escalate (TP/Suspicious). Use for end-to-end alert processing.

Overview

Publisherdandye
Repositoryai-runbooks
Skill namefull-alert-triage
Stars
126
Forks
34
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Full Alert Triage 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/_workflows/full-alert-triage .claude/skills/full-alert-triage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Full Alert Triage 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 Full Alert Triage 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 Full Alert Triage 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.

Full Alert Triage Workflow

A composite skill that orchestrates the complete Tier 1 alert triage process from initial receipt to disposition (close or escalate).

Inputs

  • CASE_ID or ALERT_ID - The alert/case to triage (required)

Orchestrated Workflow

┌─────────────────────────────────────────────────────────────────┐
│                    FULL ALERT TRIAGE                            │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  START                                                          │
│    │                                                            │
│    ▼                                                            │
│  ┌─────────────────────┐                                        │
│  │  /check-duplicates  │                                        │
│  └──────────┬──────────┘                                        │
│             │                                                   │
│     ┌───────┴───────┐                                           │
│     ▼               ▼                                           │
│  DUPLICATE       NOT DUPLICATE                                  │
│     │               │                                           │
│     ▼               ▼                                           │
│  Close &      ┌─────────────────────┐                           │
│  Document     │   /triage-alert     │                           │
│     │         └───────────┬─────────┘                           │
│     │                     │                                     │
│     │         ┌───────────┴─────────┐                           │
│     │         │  For each entity:   │                           │
│     │         │    /enrich-ioc      │                           │
│     │         └───────────┬─────────┘                           │
│     │                     │                                     │
│     │         ┌───────────┴─────────┐                           │
│     │         │     DECISION        │                           │
│     │         └───────────┬─────────┘                           │
│     │                     │                                     │
│     │     ┌───────────────┼────────────────┐                    │
│     │     ▼               ▼                ▼                    │
│     │   FP/BTP         TP/Suspicious    Inconclusive            │
│     │     │                  │                  │               │
│     │     ▼                  ▼                  ▼               │
│     │  /document-in-case    /document-in-case /document-in-case │
│     │  /close-case-artifact  ESCALATE         Request more info │
│     │     │                  │                  │               │
│     └─────┴──────────────────┴──────────────────┘               │
│                    │                                            │
│                    ▼                                            │
│               /generate-report                                  │
│                    │                                            │
│                    ▼                                            │
│                  END                                            │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Detailed Steps

Phase 1: Pre-Check

Step 1.1: Check for Duplicates

Invoke: /check-duplicates CASE_ID=$CASE_ID

  • If duplicate confirmed:
    • Invoke: /document-in-case with "Closing as duplicate of [Similar Case ID]"
    • Invoke: /close-case-artifact with reason NOT_MALICIOUS
    • END WORKFLOW
  • If not duplicate: Continue to Phase 2

Phase 2: Initial Triage

Step 2.1: Perform Alert Triage

Invoke: /triage-alert CASE_ID=$CASE_ID

Extract from results:

  • CLASSIFICATION - FP, BTP, TP, or Suspicious
  • KEY_ENTITIES - List of IOCs (IPs, domains, hashes, URLs)
  • ALERT_TYPE - Type of alert (malware, authentication, network, etc.)
  • PRIORITY - Suggested priority level

Phase 3: Enrichment

Step 3.1: Enrich Each Entity

For each entity in KEY_ENTITIES:

Invoke: /enrich-ioc IOC_VALUE=$entity

Collect:

  • GTI_FINDINGS - Threat intelligence results
  • SIEM_CONTEXT - SIEM entity summary
  • IOC_MATCH_STATUS - Whether IOC appears in threat feeds

Update CLASSIFICATION if enrichment reveals new information.

Phase 4: Decision & Action

Step 4.1: Make Final Classification

Based on triage and enrichment, confirm classification:

ClassificationCriteriaAction
False Positive (FP)No malicious indicators, known benignClose
Benign True Positive (BTP)Real but authorized/expectedClose
True Positive (TP)Confirmed maliciousEscalate
SuspiciousInconclusive, warrants investigationEscalate

Step 4.2: Execute Disposition

If FP or BTP:

  1. Invoke: /document-in-case with:
    • Classification and rationale
    • Evidence summary from enrichment
    • Closure justification
  2. Invoke: /close-case-artifact with:
    • Reason: NOT_MALICIOUS
    • Root cause: Appropriate option (e.g., "Legit action", "Normal behavior")

If TP or Suspicious:

  1. Invoke: /document-in-case with:
    • Classification and rationale
    • Evidence summary
    • Recommended next steps
  2. Output escalation recommendation:
    • Escalate to Tier 2
    • Suggest appropriate follow-up skill based on alert type:
      • Malware → /triage-malware
      • Authentication → /triage-suspicious-login
      • IOC-focused → /deep-dive-ioc

Phase 5: Report

Step 5.1: Generate Triage Report

Invoke: /generate-report REPORT_TYPE=triage

Include:

  • Case/Alert ID
  • Classification with rationale
  • Key entities and enrichment results
  • SIEM queries executed
  • Disposition taken
  • Next steps (if escalated)

Outputs

OutputDescription
FINAL_CLASSIFICATIONFP, BTP, TP, or Suspicious
DISPOSITIONClosed or Escalated
EVIDENCE_SUMMARYKey findings from triage and enrichment
REPORT_PATHPath to generated triage report
ESCALATION_TARGETIf escalated, recommended next skill/tier

Error Handling

  • If /check-duplicates fails → Log warning, continue with triage
  • If /enrich-ioc fails for an entity → Log warning, continue with other entities
  • If /close-case-artifact fails → Log error, manual closure required
  • If any MCP tool unavailable → Document limitation, proceed with available data

Performance Targets

  • Total workflow time: < 15 minutes
  • Duplicate detection: < 1 minute
  • Per-entity enrichment: < 2 minutes
  • Target accuracy: > 90% correct classification

Frequently asked questions

What does the Full Alert Triage AI skill do?

Complete Tier 1 triage workflow. Orchestrates the full alert triage process: check-duplicates, triage-alert, enrich-ioc for each entity, and either close (FP/BTP) or escalate (TP/Suspicious). Use for end-to-end alert processing.

Why use Full Alert Triage on TypingMind?

Because you install it once and use it with any model. Full Alert Triage 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 Full Alert Triage in TypingMind?

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

Which AI models can use Full Alert Triage?

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 Full Alert Triage?

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

Is the Full Alert Triage 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 👇