agentcore-investigation

Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

71%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.

Highly actionable, executable query guidance with a clear phased workflow and good error handling. The main weaknesses are query duplication across log-group layouts and broken/missing MCP reference files that undermine navigation.

Suggestions

Create the referenced mcp/ files (mcp-setup.md, .mcp.json) or remove the dangling "ALWAYS load" references, since two of three referenced paths do not exist.

Collapse the structured vs combined-log-group query duplication by stating the glob-parse substitution once and showing only the deltas, rather than repeating all six queries in full twice.

Add an explicit validate→fix→retry loop (e.g., for 0-result queries: widen time range, then retry, then escalate to alternate ID fields) as a checkpoint rather than only an error-handling table.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept over-explanation, but each of the 6 query types is fully written out twice (structured + combined-log-group versions), which is more than minor duplication that could be tightened via a single substitution rule.	3 / 5
Actionability	Every phase provides copy-paste-ready, executable CloudWatch Logs Insights queries with explicit field lists and limits, covering all six common investigation cases with placeholders clearly marked.	5 / 5
Workflow Clarity	Phases 0–4 are clearly sequenced with an error-handling table and size-limit guidance, and Phase 3 includes a count/filter/log checkpoint; not a 5 because explicit validate→fix→retry feedback loops are only implicit despite the error-handling table covering recovery.	4 / 5
Progressive Disclosure	References are signaled with When/Contains labels, but the body references mcp/mcp-setup.md and mcp/.mcp.json ("ALWAYS load") whose mcp/ directory does not exist, and the large inlined query blocks could live in a separate reference file.	3 / 5
	Total	15 / 20 Passed

Description

92%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 pairs concrete capabilities with explicit use-when triggers for a well-scoped niche. It is comprehensive and distinct, with only minor room for broader natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "resolve session/trace IDs, query OTEL spans, filter noise, build timelines" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (resolve IDs, query OTEL spans, filter noise, build timelines) and when ("Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency" provides good natural keyword coverage, but is somewhat technical and lacks common synonyms; not a 5 because a few natural phrasings users might say are missing.	4 / 5
Distinctiveness Conflict Risk	"Bedrock AgentCore runtime sessions via CloudWatch Logs Insights" carves a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: awslabs/mcp
Path: src/cloudwatch-mcp-server/skills/agentcore-investigation/SKILL.md
Commit: 5609db9

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.