# alert-tuning-and-false-positive-reduction

alert-tuning-and-false-positive-reduction is a Claude Code skill for reducing false positives in detections. It helps investigate rules that generate too many alerts.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 73 repo stars
- Author: W4L33Dx
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/W4L33Dx/Cyber-Monster/tree/HEAD/blue-team/detection-and-monitoring/alert-tuning-and-false-positive-reduction/SKILL.md
- Updated: 2026-11-15
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/alert-tuning-and-false-positive-reduction

## What it does

The skill groups analyst dispositions by recurring benign causes, then helps shape a narrow exclusion around a known host, account, or other entity. It checks the proposed change against labelled true-positive fixtures so the exclusion does not suppress those detections.

The analysis needs alerts linked to analyst dispositions. With fewer than 50 written rationales in the review window, the result is “Inconclusive (Labelling Gap)” rather than a filter. Missing telemetry for an exclusion field leads to “INCONCLUSIVE (Telemetry Gap).” The skill also separates noise caused by a rule’s selection logic from alerts produced by a known benign population.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/alert-tuning-and-false-positive-reduction/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/alert-tuning-and-false-positive-reduction/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/alert-tuning-and-false-positive-reduction/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/alert-tuning-and-false-positive-reduction/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install W4L33Dx/Cyber-Monster blue-team/detection-and-monitoring/alert-tuning-and-false-positive-reduction
```

2. **Manually: put the files in place**
- File: `.github/skills/alert-tuning-and-false-positive-reduction/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/W4L33Dx/Cyber-Monster --path blue-team/detection-and-monitoring/alert-tuning-and-false-positive-reduction
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/alert-tuning-and-false-positive-reduction/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/W4L33Dx/Cyber-Monster/tree/HEAD/blue-team/detection-and-monitoring/alert-tuning-and-false-positive-reduction/SKILL.md

## When to use it
- group false positives by analyst rationale
- choose between revising rule logic and excluding a benign entity
- test whether an exclusion suppresses labelled true positives
- identify when alert tuning lacks enough labelled cases

## Example prompts
- Group this detection's false positives by the analysts' stated reasons.
- Decide whether to revise the rule selection or add a narrow exclusion.
- Test this rule change against labelled true-positive fixtures.

## Similar
- [false-positive-playbook](https://affpapa.org/en/nevibecode/skills/false-positive-playbook.md) — skill · ★ 71 repo stars
- [detection-engineer](https://affpapa.org/en/nevibecode/agents/detection-engineer.md) — subagent · ★ 2482 repo stars
- [regression-alert](https://affpapa.org/en/nevibecode/skills/regression-alert.md) — skill · ★ 1198 repo stars
- [sentry-create-alert](https://affpapa.org/en/nevibecode/skills/sentry-create-alert.md) — skill · 4400 installs
- [alert-investigation](https://affpapa.org/en/nevibecode/skills/alert-investigation.md) — skill · 700 installs
- [huawei-cloud-ecs-alert](https://affpapa.org/en/nevibecode/skills/huawei-cloud-ecs-alert.md) — skill · 236 installs

From the same set: [w4l33dx/cyber-monster](https://affpapa.org/en/nevibecode/by/w4l33dx/cyber-monster.md) — 61 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
