CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

98

1.55x
Quality

100%

Does it follow best practices?

Impact

93%

1.55x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

This is an excellent skill that provides a clear, actionable investigation workflow with proper sequencing, validation checkpoints, and interpretation guidance. It efficiently balances being a concise overview while providing enough detail to be immediately useful, with well-organized references for deeper content. The anti-pattern guardrails in 'Stay on the Path' and the troubleshooting section for empty results add significant practical value.

DimensionReasoningScore

Conciseness

The content is lean and efficient throughout. It assumes Claude knows how to use MCP tools and doesn't explain basic concepts. Every section earns its place — the 'Stay on the Path' section might seem verbose but provides genuinely useful anti-patterns specific to incident investigation that Claude wouldn't inherently know.

3 / 3

Actionability

Each step specifies exact tool calls (get_workspace_context, run_bubbleup, get_trace, create_board), concrete query patterns (P99(duration_ms), HEATMAP, COUNT with filters), and specific field names to look for. The BubbleUp interpretation guide and trace waterfall checklist provide precise, actionable guidance rather than vague descriptions.

3 / 3

Workflow Clarity

The 6-step workflow is clearly sequenced with explicit validation in Step 5 (query with/without suspected cause as control). The troubleshooting section handles empty results. The 'Stay on the Path' section acts as a guardrail against skipping verification steps. The investigation patterns section provides clear abbreviated workflows for common scenarios.

3 / 3

Progressive Disclosure

The SKILL.md provides a complete overview with well-signaled one-level-deep references to three specific reference files (investigation-playbooks.md, bubbleup-guide.md, trace-exploration.md) with clear descriptions of what each contains. Cross-references to related skills (observability-fundamentals, query-patterns, slos-and-triggers) are clearly signaled and purposeful.

3 / 3

Total

12

/

12

Passed

Description

100%

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

This is a strong skill description that clearly communicates both the specific workflow steps involved (context priming, broad query, BubbleUp, trace analysis, verification) and when to use the skill through an extensive list of natural trigger phrases. The description is well-scoped to Honeycomb-specific production debugging, making it highly distinctive. It uses appropriate third-person voice and avoids vague language.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: context priming, broad query, BubbleUp, trace analysis, verification, and describes chaining results between steps to reach root causes. These are concrete, actionable steps in a workflow.

3 / 3

Completeness

Clearly answers both 'what' (structured workflows for investigating production issues with specific tool call sequences) and 'when' (explicit trigger phrases section listing numerous scenarios). The 'Trigger phrases:' clause serves as an explicit 'Use when' equivalent.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would actually say: 'debug latency spike', 'find root cause', 'why is my API slow', 'errors are increasing', 'SLO burning', 'debug an outage', 'health check'. These cover a wide range of natural phrasings.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive — specifically scoped to Honeycomb production investigation workflows with named Honeycomb-specific features (BubbleUp, trace analysis). The combination of the Honeycomb platform and the specific debugging workflow makes it very unlikely to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
honeycombio/agent-skill
Reviewed

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.