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.
no license ★ 73 updated 2026-11-15
npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a claude-codeWhat alert-tuning-and-false-positive-reduction 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.
What it helps with
- 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 for the agent
- 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.
How to install alert-tuning-and-false-positive-reduction
1Skills CLI (Vercel)
npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a claude-code2Manually: put the files in place
~/.claude/skills/alert-tuning-and-false-positive-reduction/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/alert-tuning-and-false-positive-reduction/
1Skills CLI (Vercel)
npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a codex2Manually: put the files in place
.agents/skills/alert-tuning-and-false-positive-reduction/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a cursor2Manually: put the files in place
.cursor/skills/alert-tuning-and-false-positive-reduction/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install W4L33Dx/Cyber-Monster blue-team/detection-and-monitoring/alert-tuning-and-false-positive-reduction2Manually: put the files in place
.github/skills/alert-tuning-and-false-positive-reduction/SKILL.md1Skills CLI (Vercel)
npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a gemini-cli2Platform CLI
gemini skills install https://github.com/W4L33Dx/Cyber-Monster --path blue-team/detection-and-monitoring/alert-tuning-and-false-positive-reductionManually: put the files in place
.devin/skills/alert-tuning-and-false-positive-reduction/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about alert-tuning-and-false-positive-reduction
How do I install alert-tuning-and-false-positive-reduction in Claude Code?
Run npx skills add W4L33Dx/Cyber-Monster --skill alert-tuning-and-false-positive-reduction -a claude-code. The skill file is at ~/.claude/skills/alert-tuning-and-false-positive-reduction/SKILL.md.
What does alert-tuning-and-false-positive-reduction do?
It helps measure false positives, group them by benign cause, and create narrow exclusions. It also checks that labelled true-positive detections still fire.
What data does alert-tuning-and-false-positive-reduction need?
It needs alerts linked to analyst dispositions for the review window. If fewer than 50 have written rationales, the outcome is “Inconclusive (Labelling Gap).”