investigate-error-rates SKILL.md skillA

investigate-error-rates from prometheus/prometheus-mcp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add prometheus/prometheus-mcp/investigate-error-rates@git:20260721.4db318b

Pins git:20260721.4db318b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
prometheus/prometheus-mcp
Path
pkg/mcp/assets/skills/investigate-error-rates/SKILL.md
Versions recorded
1
Latest version
git:20260721.4db318b, committed Jul 21, 2026
Size
2,366 bytes
Repository stars
138
License
Apache-2.0

Investigate elevated error rates and failing requests. Use when errors or 5xx/gRPC failures spike, SLOs burn, or an error alert fires; quantifies error ratios with rate(), compares to baseline, and isolates affected jobs and instances.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Investigating High Error Response Rates

Figure out how bad the errors are, when they started, and where they are concentrated. Error metrics vary by system, so discover what actually exists before querying.

## Getting oriented

- Error signals are usually counters: HTTP status codes (http_requests_total{code=~"5.."}), gRPC codes (grpc_server_handled_total{grpc_code!="OK"}), or dedicated *_errors_total / *_failures_total metrics.
- Discover what this system exposes with series or label_values on __name__ using regex matchers, and confirm semantics with metric_metadata.
- list_alerts shows whether an error-related alert is already firing and carries useful labels to start from.
- The ALERTS{alertstate="firing"} series Prometheus generates is the queryable form of the same information: range_query it to see when alerts started firing and line their history up against the error timeline.

## Topics worth exploring

Treat these as starting points and follow what the data shows:

- Current error rate: counters need rate() before aggregating, e.g. with query:
  sum by (job) (rate(http_requests_total{code=~"5.."}[5m]))
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add prometheus/prometheus-mcp/investigate-error-rates@sha256:108a17d61842b553

The line at the top of this page pins the label git:20260721.4db318b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_hzeu4p7sf5yu6rif.svg)](https://markdownregistry.com/a/art_hzeu4p7sf5yu6rif)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 21, 2026.

versioncommittedcommitsizeaudit
git:20260721.4db318b latest2026-07-21 4db318b 2,366 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2366 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

prometheus/prometheus-mcp · 138 stars · license Apache-2.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hzeu4p7sf5yu6rif
GET https://markdownregistry.com/api/v1/resolve?ref=prometheus/prometheus-mcp/investigate-error-rates
GET https://markdownregistry.com/api/v1/blob/108a17d61842b553731929e38fd04965f600f8967b1fc49722cc65056436026a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from prometheus/prometheus-mcp

AGENTS.md AGENTS.md file
prometheus/prometheus-mcp · AGENTS.md
git:20261016.c4e1736 · audit A · 138 stars
CLAUDE.md CLAUDE.md file
prometheus/prometheus-mcp · CLAUDE.md
git:20260324.e032979 · audit B · 138 stars
check-system-health SKILL.md skill
prometheus/prometheus-mcp · pkg/mcp/assets/skills/check-system-health/SKILL.md · Health-check the Prometheus server and its targets. Use for status, uptime, or is-monitoring-OK questions; reviews…
git:20260721.4db318b · audit A · 138 stars
find-top-resource-consumers SKILL.md skill
prometheus/prometheus-mcp · pkg/mcp/assets/skills/find-top-resource-consumers/SKILL.md · Find the top CPU, memory, or disk consumers. Use for capacity reviews, noisy-neighbor hunts, and top-N questions about…
git:20260721.4db318b · audit A · 138 stars
optimize-high-cardinality SKILL.md skill
prometheus/prometheus-mcp · pkg/mcp/assets/skills/optimize-high-cardinality/SKILL.md · Find and reduce high-cardinality metrics and labels. Use when series counts or memory grow, queries slow down, or…
git:20260721.4db318b · audit A · 138 stars
review-prometheus-rules SKILL.md skill
prometheus/prometheus-mcp · pkg/mcp/assets/skills/review-prometheus-rules/SKILL.md · Audit and improve recording and alerting rules. Use when reviewing alert coverage or rule health, drafting new alerts…
git:20260721.4db318b · audit A · 138 stars
troubleshoot-missing-data SKILL.md skill
prometheus/prometheus-mcp · pkg/mcp/assets/skills/troubleshoot-missing-data/SKILL.md · Diagnose missing metrics, absent series, or scrape gaps. Use when queries unexpectedly return empty, a metric stopped…
git:20260721.4db318b · audit A · 138 stars
tune-prometheus-config SKILL.md skill
prometheus/prometheus-mcp · pkg/mcp/assets/skills/tune-prometheus-config/SKILL.md · Review and tune Prometheus configuration and performance. Use for scrape interval, retention, storage, relabeling…
git:20260721.4db318b · audit A · 138 stars

Every file in prometheus/prometheus-mcp

Browse by kind, by grade A, or by owner.