Skip to content
Development
Skill

/cyber-detection-engineering

Designs and reviews detections from telemetry prerequisites, correlation logic, Sigma metadata, severity, status, and benign cases. Use for detection rules, Sigma review, analytic coverage, or tuning; not generic logging advice or live deployment.

From plugin
agent-skills-standard
570200 skills21 agents33 commands1 MCP
Install
$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill cyber-detection-engineering --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/cyber-detection-engineering

Context preview

The summary Claude sees to decide when to auto-load this skill.

Designs and reviews detections from telemetry prerequisites, correlation logic, Sigma metadata, severity, status, and benign cases. Use for detection rules, Sigma review, analytic coverage, or tuning; not generic logging advice or live deployment.

SKILL.md

cyber-detection-engineering.SKILL.md
name: cyber-detection-engineering
guardrail: true
description: Designs and reviews detections from telemetry prerequisites, correlation logic, Sigma metadata, severity, status, and benign cases. Use for detection rules, Sigma review, analytic coverage, or tuning; not generic logging advice or live deployment.
metadata:
  triggers:
    files: []
    keywords:
      - detection engineering
      - detection rule
      - Sigma rule
      - analytic coverage
      - telemetry prerequisite
      - false positive tuning

Cyber Detection Engineering

**Priority: P0 (CRITICAL)**

Do not claim analytic coverage without required telemetry and executable support.

Structure

Input: analytic question, behavior hypothesis, data source/fields, retention, clock quality, scope. Process: define predicates, entity keys, window, cardinality, ordered correlation, suppression, benign cases. Output: rule/spec, prerequisites, severity, lifecycle status, fixtures, limitations, evidence record.

Rules

  • A missing source, field, retention, clock, or collection path makes coverage `blocked` or `not-tested`.
  • Multi-step behavior requires ordered sequence correlation over related entities/events; never substitute Boolean OR across unrelated single events.
  • Sigma `level` expresses impact/priority (`informational`, `low`, `medium`, `high`, `critical`). Sigma `status` expresses lifecycle (`stable`, `test`, `experimental`, `deprecated`). A valid portable rule does not prove backend execution or telemetry.
  • Record expected matches, exclusions and benign/false-positive cases with rationale.
  • Include scope reference; skill/version/source; observation time; status; evidence references; limitations; owner. Reuse shared skill IDs.
  • Production queries or modifications require documented authorization and runtime-proven controls; offline fixtures only.

Anti-Patterns

  • Never write `severity: high` as Sigma metadata; use `level: high`.
  • Never equate `level` with `status`, rule validity with execution, or synthetic matches with efficacy.
  • Never hide missing telemetry by lowering priority or widening OR logic.

References (lazy, primary)

  • Sigma specification: https://sigmahq.io/sigma-specification/specification/sigma-rules-specification.html
  • MITRE ATT&CK detection strategies: https://attack.mitre.org/detectionstrategies/
  • Reuse `cyber-authorization`, `cyber-evidence`, `cyber-framework-mapping`.
Read more
Ships withagent-skills-standard

The portable SDLC standards layer for AI coding agents. Sync once, then work in your own runtime.

Get the whole plugin

Other skills on agent-skills-standard.