slo-implementation Skill (wshobson) for Claude: What It Does and How to Install It

Makes Claude define SLIs and SLOs, work out error budgets, and write Prometheus rules and burn-rate alerts for them.

Installs: 10.7K; on skills.sh
Stars: 42.1K; on GitHub
Files: 1; besides SKILL.md
Updated: Oct 2026; last repo commit

This skill is a reliability guide for Claude, from wshobson's agents collection. It covers the SLA, SLO and SLI hierarchy, availability, latency and durability SLIs, SLO targets, error budgets and burn-rate alerting.

The main file has Prometheus recording and alerting rules and a Grafana dashboard layout. references/details.md adds multi-window alerts, a weekly, monthly and quarterly review process, and ten best practices. It loads when you set reliability targets or measure service performance.

Good for

SREs setting reliability targets for a service
Platform teams building error budget alerts in Prometheus
Engineering leads who want an error budget policy

Install slo-implementation

Claude Code

Copy this prompt.

Install the slo-implementation skill in Claude Code. Run this command:

/plugin marketplace add wshobson/agents
/plugin install observability-monitoring@claude-code-workflows

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin routes install the whole observability-monitoring plugin: 4 agents, 2 commands and 4 skills (counted from the plugin folder in the repo tree, which has no hooks or MCP config files). The skills-only routes install just this skill, with no agents or commands. The skill has no setup of its own; the examples assume Prometheus and Grafana.

Built from the package data we hold. Not yet tested by us. Source.

What's in the skill

When it loads

Define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting. Use when establishing reliability targets, implementing SRE practices, or measuring service performance.

Sections in SKILL.md

Purpose
When to Use
SLI/SLO/SLA Hierarchy
Defining SLIs
Common SLI Types
Setting SLO Targets
Availability SLO Examples
Choose Appropriate SLOs
Error Budget Calculation
Error Budget Formula
Error Budget Policy
SLO Implementation
Prometheus Recording Rules
SLO Alerting Rules
SLO Dashboard
Additional patterns and templates

Key facts

Author: wshobson (repo owner); the plugin.json author is Seth Hobson
License: MIT (repo and plugin.json)
Installs on skills.sh: 10,664 (Nov 2, 2026)
GitHub stars: 42,081 for the whole wshobson/agents repo (Nov 2, 2026)
Last repo commit: Oct 30, 2026
What it includes: 2 files including SKILL.md: references/details.md (no scripts)
Needs: Examples use Prometheus rules and Grafana. SKILL.md names prometheus-configuration and grafana-dashboards as related skills
Part of: The observability-monitoring plugin (version 1.2.4) in wshobson/agents. Counted from the plugin folder: 4 agents, 2 commands and 4 skills
Works in: Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot and Pi, per the repo README. Skills-only installers ask which tool you use

What it includes

SLA is the customer contract, SLO the internal target, SLI the measurement
A short diagram that frames the rest of the skill.
Read · SLI/SLO/SLA hierarchy
Availability, latency and durability SLIs with PromQL
Each is a ratio of good events to total events. The availability and latency examples use a 28 day window.
Write · Defining SLIs
Downtime table for 99%, 99.9%, 99.95% and 99.99%, plus five factors to weigh
Factors: user expectations, business requirements, current performance, cost of reliability and competitor benchmarks.
Read · Setting SLO targets
Error Budget = 1 - SLO Target, with a four-step budget policy
The policy goes from normal velocity at 100% remaining to a feature freeze at 0%.
Write · Error budgets
Recording rules for SLI, compliance, budget remaining and burn rate
YAML rule groups you can adapt.
Write · Prometheus rules
Fast burn (14.4x, 1 hour), slow burn (6x, 6 hours) and budget exhausted
The details file adds a multi-window combination to cut false positives.
Write · Burn-rate alerts
A Grafana layout and example queries
Panels for compliance, budget remaining, SLI trend and burn rate.
Write · SLO dashboard
Weekly, monthly and quarterly reviews plus ten best practices
In references/details.md.
Read · Review process and practices

From the official docs

Permissions

Low risk

It writes monitoring rules and alert thresholds that you then apply to your own systems.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

The plugin route installs more than this skill
The observability-monitoring plugin has 4 agents, 2 commands and 4 skills. We found no hooks or MCP config files in its folder. The skills-only routes install just this skill. github.com
Alert rules need tuning before they go live
The burn-rate thresholds in SKILL.md are examples. Test rules against your own traffic before paging anyone. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only mode is documented in SKILL.md. Use version control for files it writes.
Talks to	Whatever your own Prometheus and Grafana setup calls
Sign-in and keys	SKILL.md and details.md do not mention any account or key.
Scopes	Claude can write Prometheus rule files and dashboard queries in your project when you ask The plugin route also installs agents and commands that are not part of this skill

Questions

What does the slo-implementation skill do?

It makes Claude help you define SLIs and SLOs, calculate error budgets and write alerting rules. The examples use Prometheus and Grafana.

How do I install slo-implementation?

Use the install box at the top of this page. It lists the plugin route and two skills-only commands, plus a Claude app upload. The skills-only commands skip the plugin's agents and commands.

Do I need Prometheus?

The rules and queries in SKILL.md are written for Prometheus. SKILL.md also names prometheus-configuration and grafana-dashboards as related skills for metric collection and visualization.

Should I install the whole observability-monitoring plugin?

Only if you want the rest. The plugin folder holds 4 agents, 2 commands and 4 skills, and the repo tree shows no hooks or MCP config files in it. The other skills there are distributed-tracing, grafana-dashboards and prometheus-configuration.

Is it safe to install?

It is a guide with one reference file and no scripts. When you ask for rules, Claude writes YAML and PromQL you then review and apply to your own monitoring. Check alert thresholds against your service before you deploy them.

Information

updated Nov 2, 2026

Repository: wshobson/agents
Folder: plugins/observability-monitoring/skills/slo-implementation

wshobson/agents skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

slo-implementation SKILL.md · github.com
wshobson/agents README · github.com
observability-monitoring plugin.json · github.com
wshobson/agents marketplace.json · github.com
slo-implementation details.md · github.com