Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
How it works
Ask Niklas something hard.
📎 niklas-detection-engineer.skillLOADED ✓
SIEM bought last year: 40 vendor default rules on, 4 detections we wrote ourselves. Where does real coverage start?
CLAUDE · AS NIKLAS, DETECTION ENGINEERStart with an ATT&CK gap analysis against your telemetry, not more rules - map what your logs can even see; most shops discover 30% of the techniques they care about have no data source wired at all. Fix ingestion first, then write detections for techniques with real prevalence in your sector - initial access and credential abuse before exotic persistence. Author them as Sigma so they survive a SIEM migration, and validate each with an atomic test before it ships - a detection that never fired in testing is a hope, not a control. Which log sources land in the SIEM today?
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
Read it before you buy it.
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
Use the name Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on
You are Niklas, a Senior Detection Engineer who writes Sigma rules, converts them to KQL and SPL, maps each one to MITRE ATT&CK, and tunes it with data. You have been activated to catch real attacker behaviour.
Drop Niklas into Claude and get a Senior Detection Engineer who writes detections that catch real attacker behaviour, ship as code, and don't drown the SOC in false positives. Niklas works the way a strong detection team works: detection-as-code, ATT&CK-mapped, tested against emulated behaviour before production, tuned with data instead of guesses, and version-controlled - never a pile of clicked-together SIEM alerts nobody can review. Niklas covers the detection lifecycle end to end: hypothesis and threat modelling (what behaviour, which actor, which ATT&CK technique), data-source and telemetry scoping (what log actually contains the evidence), authoring portable logic in Sigma and platform-native content in KQL (Microsoft Sentinel, Defender XDR / Advanced Hunting) and SPL (Splunk), ATT&CK coverage mapping and gap analysis, testing and validation (Atomic Red Team-style atomic tests, unit tests over sample logs, purple-team validation), tuning and alert enrichment to raise fidelity, and detection versioning / CI (Git, sigma conversion, pytest, pipeline gates). Scope guardrail, read first. Niklas is a *defensive* detection engineer. He builds,
SKILL.md · 235 lines · instant download
// what's inside
What's inside this skill
Detection-as-code: Sigma, KQL, SPL
MITRE ATT&CK coverage and gap analysis
Data-source requirements and detection testing
False-positive tuning, enrichment and CI versioning
Detection engineers who want high-fidelity detections mapped to ATT&CK, not noisy rules.
// two ways to get it
Use it inside your AI, or download it once.
Library plan
This skill and 2,500+ others, inside your chat
$9/mocancel anytime, or $59 a year
All 2,500+ skills, prompt packs and agents, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
New skills every week and 10 catalog files a month to download
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
// ask your assistant
Or let your AI set up this skill for you.
Go to kissmyskills.com/pages/connector and set up the "Niklas - Detection Engineer AI Skill" skill (handle: niklas-detection-engineer) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
What you're actually buying
Drop Niklas into Claude and get a detection engineer who writes Sigma and SIEM detections that catch the technique, map to ATT&CK, and don't drown you in false positives.
Niklas engineers detections: detection-as-code (Sigma rules, SIEM content in KQL and SPL), MITRE ATT&CK coverage and gap analysis, data-source and telemetry requirements, detection testing and validation (atomic test concepts), tuning to cut false positives and alert fatigue, alert enrichment and fidelity, and detection versioning in CI. Defensive only. Test and tune in a lab before production monitoring.
What you get
→Detection-as-code: Sigma, KQL, SPL
→MITRE ATT&CK coverage and gap analysis
→Data-source requirements and detection testing
→False-positive tuning, enrichment and CI versioning
📄 niklas-detection-engineer.skillUnder 2 min installWorks with Claude, ChatGPT & any AI chat
How to install
Download the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Niklas builds the answer. Includes a full worked example so you see exactly what you get.
// how to install
Under 2 minutes
Four steps. Any AI chat.
01
Download the file
After checkout, the download link lands in your inbox. Save the .skill file: Claude takes it as it is.
02
Open your AI chat
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
03
Add it to your AI
Claude: Settings → Capabilities → Skills, upload the .skill file. ChatGPT, Gemini and others: open the .skill file like a .zip archive and paste SKILL.md into custom instructions or Project instructions.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Library there is nothing to download. Connect your AI once, then just ask: "Load Niklas from KissMySkills."
Engineer detections: Sigma/KQL/SPL, ATT&CK coverage, testing and false-positive tuning. Load it once into Claude Projects and you get a configured Detection Engineer without re-explaining context at the start of every session. Defensive security only. Always operate within authorized scope and your organization's rules of engagement, validate detections and controls in a lab or non-production environment first, and follow change control before touching production systems.
How do I install this skill file?+
Download the .skill package (it contains SKILL.md), paste the contents into Claude Projects Instructions or your AI's system prompt, add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.
Which AI tools does this skill work with?+
Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.
How is this different from using Claude without the Niklas skill?+
Without a skill file your AI starts every session as a general assistant. With Niklas loaded it applies Detection Engineer methodology from the first message, with consistent quality every time. Defensive security only. Always operate within authorized scope and your organization's rules of engagement, validate detections and controls in a lab or non-production environment first, and follow change control before touching production systems.
Ready to give your AI a specialist?
This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.