production-investigation

Structured workflows for investigating production issues in Honeycomb — the sequence of tool calls (context priming, broad query, BubbleUp, trace analysis, verification) and how to chain results between steps to reach root causes. Trigger phrases: "investigate production issue", "debug latency spike", "find root cause", "use BubbleUp", "analyze traces", "debug an outage", "why is my API slow", "errors are increasing", "health check", "SLO burning", or any request to investigate or debug production problems.

4.34x

Quality

100%

Does it follow best practices?

Impact

87%

4.34x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Evaluation results

83%

69%

Checkout API Latency Investigation

Latency spike investigation with BubbleUp and hypothesis verification

Criteria

Baseline

With context

Orient step executed

66%

100%

HEATMAP in initial query

get_service_map called

100%

BubbleUp not skipped

100%

BubbleUp 2D heatmap type

100%

BubbleUp time range specified

100%

BubbleUp value range specified

100%

BubbleUp filters applied before trace

100%

Verification WITH suspected cause

60%

100%

Control query WITHOUT suspected cause

40%

100%

create_board called

50%

Board includes query run PKs

25%

99%

59%

Checkout Failure Surge — Honeycomb Investigation

Error surge exception investigation workflow

Criteria

Baseline

With context

Context priming

100%

Schema discovery

100%

BubbleUp not skipped

100%

BubbleUp filter re-query

100%

Separate exception event query

100%

No span exception.message primary search

100%

get_trace with show_events=true

100%

Hypothesis verification query

55%

100%

create_board called

100%

Board content: root cause summary

100%

Board content: query PKs

28%

100%

Exception payload from event row

87%

79%

73%

Payment Service Performance Investigation

Deployment regression investigation with BubbleUp pagination

Criteria

Baseline

With context

Orient step

100%

Version comparison query

100%

BubbleUp with group selection

BubbleUp pagination or max_columns

100%

Multiple BubbleUp fields checked

100%

BubbleUp not skipped

100%

BubbleUp filters before trace

50%

Explicit view_mode in get_trace

100%

Hypothesis verified WITH filter

12%

100%

Control query WITHOUT filter

12%

87%

create_board called

37%

100%

Board includes query PKs

Repository: honeycombio/agent-skill
Commit: 189553c

Evaluated: 1 day ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Checkout Failure Surge — Honeycomb Investigation Checkout API Latency Investigation Payment Service Performance Investigation

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.