CtrlK
BlogDocsLog inGet started
Tessl Logo

slos-and-triggers

Decision heuristics for interpreting Honeycomb SLO compliance, budget burn rates, and trigger status — what the numbers mean and what action to take, including detecting misconfigured SLIs, deciding when to freeze deploys vs page on-call, and designing burn alert thresholds. Load this skill before calling get_slos or get_triggers. Trigger phrases: "check our SLOs", "are we meeting our SLOs", "which SLOs are healthy", "is the error budget OK", "are any alerts firing", "what's the burn rate", "set up an SLO", "create a trigger", "configure alerts", "set up burn alerts", "check trigger status", "starting on-call", "reliability picture", "should we freeze deploys", "is this SLO misconfigured", "are we within budget", "SLO is broken", "budget is negative", or any request about service level objectives, error budgets, burn rates, or alerting in Honeycomb.

100

1.42x
Quality

100%

Does it follow best practices?

Impact

100%

1.42x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

28%

SLO Setup for the Checkout Service

SLO design and alert configuration for latency SLO

Criteria
Without context
With context

SLI IF() format

100%

100%

Root span qualifier

100%

100%

Latency success condition

70%

100%

Conservative starting target

100%

100%

Near-exhaustion alert

50%

100%

Slow-burn alert

50%

100%

Fast burn rate alert

12%

100%

User confirmation step

58%

100%

SLO list URL pattern

100%

100%

Post-creation backfill caveat

66%

100%

100%

32%

On-Call Handover Reliability Review

SLO health interpretation and deployment decisions

Criteria
Without context
With context

Healthy threshold correct

100%

100%

Caution threshold correct

50%

100%

At-risk threshold correct

70%

100%

Breached status correct

75%

100%

Zero compliance diagnosis

35%

100%

Zero compliance action

40%

100%

Freeze recommendation present

100%

100%

Deployment thresholds referenced

62%

100%

Investigate breached service

70%

100%

Summary table present

100%

100%

100%

28%

Alerting Setup for a New Payment Processing Service

Trigger design with count-based queries and correct alert routing

Criteria
Without context
With context

Triggers recommended

100%

100%

Count-based latency trigger

0%

100%

Error trigger is count-based

100%

100%

Duration minimum 5 minutes

100%

100%

Frequency at most half duration

25%

100%

Descriptive trigger names

100%

100%

Descriptions include action guidance

100%

100%

PagerDuty for actionable alerts

100%

100%

User confirmation before creating

33%

100%

SLO vs trigger reasoning

100%

100%

Repository
honeycombio/agent-skill
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.