# genpark-agent-step-latency-percentile-tracker-skill

> genpark-agent-step-latency-percentile-tracker-skill — alpha-park-genpark-agent-step-latency-percentile-tracker-skill. Use this tool when you need to track and analyze latency percentiles in AI agent workflows, solving problems of performance optimization and bottleneck identification. It provides sliding-window latency accumulation and histogram quantiles as output, accepting step latency data as input. Ideal for use in monitoring and debugging AI agent workflows, particularly when optimizing performance and isolating bottlenecks.

Canonical page: https://skillsregistry.net/skills/alpha-park-genpark-agent-step-latency-percentile-tracker-skill  
JSON: https://api.skillsregistry.net/v1/skills/alpha-park-genpark-agent-step-latency-percentile-tracker-skill

## Description

GenPark AI Agent Skill - P50, P90, P99 sliding-window latency accumulator, bottleneck step isolation, and histogram quantiles.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Alpha-Park/genpark-agent-step-latency-percentile-tracker-skill)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "alpha-park-genpark-agent-step-latency-percentile-tracker-skill"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/alpha-park-genpark-agent-step-latency-percentile-tracker-skill` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/alpha-park-genpark-agent-step-latency-percentile-tracker-skill/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt