Full Investigation logo

Full Investigation

Community
dandye
full-investigation

Complete Tier 2 investigation workflow. Orchestrates deep investigation of escalated cases: deep-dive-ioc, correlate-ioc, specialized triage (malware/login), pivot-on-ioc, and generate comprehensive report. Use for escalated cases requiring thorough analysis.

Overview

Publisherdandye
Repositoryai-runbooks
Skill namefull-investigation
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 Investigation 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-investigation .claude/skills/full-investigation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Full Investigation 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 Investigation 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 Investigation 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 Investigation Workflow

A composite skill that orchestrates comprehensive Tier 2/3 investigation of escalated security cases.

Inputs

  • CASE_ID - The escalated case to investigate (required)
  • PRIMARY_IOCS - Key IOCs identified during Tier 1 triage (optional)
  • ALERT_TYPE - Type of alert (malware, authentication, network, etc.)
  • ESCALATION_REASON - Why this was escalated from Tier 1

Orchestrated Workflow

┌─────────────────────────────────────────────────────────────────┐
│                   FULL INVESTIGATION                            │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  ESCALATED CASE                                                 │
│       │                                                         │
│       ▼                                                         │
│  ┌─────────────────────┐                                        │
│  │   /deep-dive-ioc    │  (for each primary IOC)                │
│  └──────────┬──────────┘                                        │
│             │                                                   │
│             ▼                                                   │
│  ┌─────────────────────┐                                        │
│  │   /correlate-ioc    │                                        │
│  └──────────┬──────────┘                                        │
│             │                                                   │
│     ┌───────┴───────────────────┐                               │
│     │     ALERT TYPE ROUTING    │                               │
│     └───────────────────────────┘                               │
│             │                                                   │
│   ┌─────────┼───────────┬─────────┐                             │
│   ▼         ▼           ▼         ▼                             │
│ MALWARE   AUTH      NETWORK    OTHER                            │
│   │         │           │         │                             │
│   ▼         ▼           ▼         ▼                             │
│ /triage   /triage      /pivot   Continue                        │
│ -malware  -suspicious  -on-ioc  with pivoting                   │
│   │       -login        │         │                             │
│   └─────────┴───────────┴─────────┘                             │
│             │                                                   │
│             ▼                                                   │
│  ┌─────────────────────┐                                        │
│  │   /pivot-on-ioc     │  (expand investigation)                │
│  └──────────┬──────────┘                                        │
│             │                                                   │
│     ┌───────┴───────┐                                           │
│     │   DECISION    │                                           │
│     └───────┬───────┘                                           │
│             │                                                   │
│   ┌─────────┼─────────┐                                         │
│   ▼         ▼         ▼                                         │
│ INCIDENT  RESOLVED  ESCALATE                                    │
│   │         │       TO IR                                       │
│   ▼         ▼         │                                         │
│ Create   /close       │                                         │
│ Incident  -case       │                                         │
│   │       -artifact   │                                         │
│   │         │         │                                         │
│   └─────────┴─────────┘                                         │
│             │                                                   │
│             ▼                                                   │
│  ┌─────────────────────┐                                        │
│  │  /generate-report   │                                        │
│  └──────────┬──────────┘                                        │
│             │                                                   │
│             ▼                                                   │
│            END                                                  │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Detailed Steps

Phase 1: Deep Analysis

Step 1.0: Extract Primary IOCs (if not provided)

If PRIMARY_IOCS is not provided as input, extract key entities from the case:

secops-soar.get_case_full_details(case_id=CASE_ID)

From the case details, extract IOCs:

  • IP addresses from alert entities
  • Domain names from network indicators
  • File hashes from endpoint alerts
  • URLs from web security alerts

Populate PRIMARY_IOCS with extracted IOCs.

Step 1.1: Deep Dive on Primary IOCs

For each IOC in PRIMARY_IOCS:

Invoke: /deep-dive-ioc IOC_VALUE=$ioc CASE_ID=$CASE_ID

Collect:

  • GTI_DEEP_FINDINGS - Full threat intelligence analysis
  • SIEM_DEEP_CONTEXT - Detailed SIEM context
  • RELATED_ENTITIES - Discovered related IOCs and entities
  • THREAT_ATTRIBUTION - Any threat actor/campaign links

Step 1.2: Aggregate Discovered IOCs

Combine all RELATED_ENTITIES collected from deep-dive steps into ALL_DISCOVERED_IOCS:

ALL_DISCOVERED_IOCS = PRIMARY_IOCS + all(RELATED_ENTITIES from each deep-dive)

This aggregated list is used for correlation in Phase 2.

Phase 2: Correlation

Step 2.1: Correlate with Existing Cases

Invoke: /correlate-ioc IOC_LIST=$ALL_DISCOVERED_IOCS

Collect:

  • RELATED_CASES - Other cases with same IOCs
  • RELATED_ALERTS - Alerts involving same entities
  • PATTERN_ANALYSIS - Detected patterns across cases

Step 2.2: Find Related Open Cases

Invoke: /find-relevant-case with key entities

Document any linked investigations.

Phase 3: Specialized Analysis

Step 3.1: Route by Alert Type

Based on ALERT_TYPE, invoke specialized triage:

Alert TypeSkillFocus
Malware/triage-malwareFile analysis, behavior, persistence
Authentication/triage-suspicious-loginUser activity, login patterns
Network/pivot-on-iocNetwork IOC relationships
OtherContinue to pivotingGeneral IOC expansion

For Malware: Invoke: /triage-malware FILE_HASH=$hash CASE_ID=$CASE_ID

Collect:

  • Malware family identification
  • Behavioral analysis
  • Affected systems
  • Containment recommendations

For Authentication: Invoke: /triage-suspicious-login USER=$user CASE_ID=$CASE_ID

Collect:

  • Login anomaly analysis
  • User activity timeline
  • Compromised account indicators
  • Account status recommendations

Phase 4: Expansion

Step 4.1: Pivot on High-Confidence IOCs

For each high-confidence malicious IOC:

Invoke: /pivot-on-ioc IOC_VALUE=$ioc

Collect:

  • RELATED_INFRASTRUCTURE - Connected domains, IPs, files
  • CAMPAIGN_LINKS - Associated campaigns or actors
  • ADDITIONAL_IOCS - New IOCs to hunt for

Step 4.2: Validate Expanded IOCs

For significant new IOCs discovered:

  • Quick GTI lookup
  • SIEM presence check
  • Add to investigation scope if relevant

Phase 5: Assessment

Step 5.1: Determine Investigation Outcome

Assess all findings and classify:

OutcomeCriteriaAction
Incident ConfirmedActive compromise, ongoing threatEscalate to IR
Resolved - ContainedThreat neutralized, no ongoing riskDocument & Close
Resolved - False PositiveDeep analysis confirms benignDocument & Close
Requires IR EscalationContainment/eradication neededEscalate to IR

Step 5.2: Execute Disposition

If Incident Confirmed / Requires IR:

  1. Invoke: /document-in-case with full findings
  2. Output escalation recommendation:
    • Recommend specific IR skill:
      • Ransomware indicators → /respond-ransomware
      • Malware persistence → /respond-malware
      • Phishing origin → /respond-phishing
      • Account compromise → /respond-compromised-account
  3. Prepare handoff package for IR team

If Resolved:

  1. Invoke: /document-in-case with:
    • Investigation summary
    • All queries and findings
    • Resolution rationale
  2. If closing: Invoke: /close-case-artifact with appropriate reason

Phase 6: Documentation

Step 6.1: Generate Investigation Report

Invoke: /generate-report REPORT_TYPE=investigation

Include:

  • Executive summary
  • Investigation timeline
  • All IOCs analyzed (with verdicts)
  • SIEM queries used
  • GTI findings
  • Correlation results
  • Attack chain (if identified)
  • Recommendations
  • Lessons learned

Outputs

OutputDescription
INVESTIGATION_OUTCOMEIncident, Resolved, or Escalated
THREAT_ASSESSMENTSeverity, scope, and attribution
ALL_IOCSComplete list of analyzed IOCs with verdicts
ATTACK_CHAINReconstructed attack timeline (if applicable)
REPORT_PATHPath to investigation report
ESCALATION_DETAILSIf escalated, target and handoff package

Error Handling

  • If /deep-dive-ioc fails → Fall back to /enrich-ioc, continue
  • If GTI Enterprise features unavailable → Document limitation, use Standard features
  • If specialized triage fails → Document, continue with general analysis
  • If correlation timeout → Proceed with available data, note gap

Performance Targets

  • Total workflow time: < 2 hours
  • Deep dive per IOC: < 15 minutes
  • Correlation: < 10 minutes
  • Specialized triage: < 30 minutes
  • Report generation: < 15 minutes
  • Target accuracy: > 95% correct assessment

Frequently asked questions

What does the Full Investigation AI skill do?

Complete Tier 2 investigation workflow. Orchestrates deep investigation of escalated cases: deep-dive-ioc, correlate-ioc, specialized triage (malware/login), pivot-on-ioc, and generate comprehensive report. Use for escalated cases requiring thorough analysis.

Why use Full Investigation on TypingMind?

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

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

Which AI models can use Full Investigation?

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 Investigation?

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

Is the Full Investigation 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 👇