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

92%

Does it follow best practices?

Impact

87%

4.34x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured investigation workflow that chains concrete Honeycomb tool calls through a clear, verified sequence and appropriately offloads detail to three flat reference files. Minor trimming of the exception-compatibility paragraph and fuller query examples would push it to the top anchor.

Suggestions

Move the LogRecordProcessor / parent-span exception compatibility paragraph into trace-exploration.md, keeping only the 'discover the schema, query event.name=exception, sample a trace.trace_id' directive inline.

Add one complete copy-paste query example per pattern (e.g., a full HEATMAP(duration_ms) GROUP BY service.name query) so the common cases are executable without consulting the reference.

The 'Investigation Patterns' section repeats much of the Error Surge / Latency Spike steps already in Step 2–5; consider condensing it to a quick-reference table to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is efficient and explicitly defers tool parameters to the MCP docs rather than re-explaining them, but the LogRecordProcessor compatibility paragraph is dense enough it could be trimmed or moved to a reference.	4 / 5
Actionability	Concrete tool names (get_workspace_context, run_bubbleup, get_trace, create_board) and specific query fragments (P99(duration_ms), HEATMAP, count by service/route/category) are given throughout, though fragments are not full copy-paste queries.	4 / 5
Workflow Clarity	A clear six-step sequence (Orient → Characterize → BubbleUp → Drill → Verify → Record) with an explicit verification checkpoint in Step 5 (query with vs without the suspected cause) plus error-recovery guidance in 'When Results Are Empty or Unclear'.	5 / 5
Progressive Disclosure	The body is an overview that points to three real one-level-deep reference files (investigation-playbooks, bubbleup-guide, trace-exploration), each with a one-line description and no nested references, giving easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely states the capability and its sequencing, then supplies a rich set of natural trigger phrases. It cleanly answers both what and when with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain (investigating production issues in Honeycomb) and lists multiple concrete actions in sequence — 'context priming, broad query, BubbleUp, trace analysis, verification' — plus how to chain results, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (structured workflows and the sequence/chaining of tool calls) and when (a dedicated 'Trigger phrases:' clause with concrete examples), matching the top anchor.	5 / 5
Trigger Term Quality	Ten natural trigger phrases spanning synonyms and incident vocabulary ('debug latency spike', 'why is my API slow', 'errors are increasing', 'SLO burning', 'health check') that users would genuinely say.	5 / 5
Distinctiveness Conflict Risk	A clear Honeycomb-specific niche with named tools (BubbleUp) and production-investigation triggers, making overlap with unrelated skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: honeycombio/agent-skill
Path: honeycomb/skills/production-investigation/SKILL.md
Commit: 41214b7

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.