CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

maple-agent-tracing-spring-ai

Trace Spring AI agents with Maple: wires Spring Boot's OpenTelemetry starter to Maple, samples every turn, and adds one configuration class so each ChatClient conversation is one Maple Agent Session with transcript, tool calls (failures marked), sub-agent lanes and tokens. Triggers on 'trace my spring ai agent', 'add Maple to spring ai', 'agent sessions for spring ai', 'OpenTelemetry for spring ai'.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

An exceptionally actionable, well-sequenced skill with verified gotchas and a real verification loop, held back only by mild internal duplication and a monolithic single-file structure with no progressive disclosure. Splitting the version-specific and verification material into reference files would bring it to top marks.

Suggestions

Move the Spring AI 1.1 / Boot 3.5 branch (Step 2d) and the OTel-agent branch (Step 2c) into a reference file (e.g. references/versions.md) signaled from the main body, keeping SKILL.md focused on the current Boot 4 / Spring AI 2.0 path.

Move the 100-line MapleAiObservationConfig class into references/MapleAiObservationConfig.java and instruct Claude to copy it from there, reducing the inline body substantially.

Trim the Goal/Mechanism opening (it duplicates the description) and the Step 5 re-explanation of Step 3's ToolExecutionExceptionProcessor.

DimensionReasoningScore

Conciseness

The body is dense with verified, non-obvious operational facts ("Default is `0.1`: 90% of turns silently missing", "Boot does not append it", "a bare `${MAPLE_INGEST_KEY}` fails startup when unset") and never explains concepts Claude already knows, but the Goal/Mechanism opening restates the description and Step 5 partially re-explains Step 3's processor — minor over-explanation that could be trimmed.

4 / 5

Actionability

Fully executable throughout: complete properties blocks, a copy-verbatim configuration class, a ready-to-paste `main` method, a sub-agent example, and verification via named MCP commands (`list_agent_sessions` with `search=<conversation id>`) plus a LoggingSpanExporter fallback — covering the common cases (OTel agent attached, Spring AI 1.1, Kotlin).

5 / 5

Workflow Clarity

Steps 0–7 are clearly sequenced from detection through verification, ending in an explicit checklist with error-recovery guidance (401 → try the other region; missing key → export disabled, never crash) and a no-Maple-access verification path — a full feedback loop.

5 / 5

Progressive Disclosure

No bundle files exist and the entire skill is one ~300-line file: the 100-line config class, the version-specific branches (2c OTel agent, 2d Spring AI 1.1), and the 16-item verification checklist are all inlined. In-file section structure is clear, but material that belongs in one-level-deep reference files is not split out.

3 / 5

Total

17

/

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 description: concrete third-person capabilities, explicit trigger phrases, and a clearly delimited Maple + Spring AI niche. The only gap is that natural synonym variations (monitor/observability/instrument) are absent from the trigger list.

Suggestions

Add one or two synonym triggers such as 'monitor my spring ai agent' or 'spring ai observability' to broaden natural-phrase coverage without adding vagueness.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "wires Spring Boot's OpenTelemetry starter to Maple, samples every turn, and adds one configuration class" with specific outcomes ("transcript, tool calls (failures marked), sub-agent lanes and tokens") — in third person, comprehensive coverage of what the skill produces.

5 / 5

Completeness

Both questions are answered explicitly: a detailed "what" (wiring, sampling, config class, session shape) and an explicit "when" via "Triggers on 'trace my spring ai agent', ..." with concrete trigger phrases — the exact anchor-5 pattern.

5 / 5

Trigger Term Quality

Four explicit natural phrases are provided ("trace my spring ai agent", "add Maple to spring ai", "agent sessions for spring ai", "OpenTelemetry for spring ai") that users would plausibly say, but common synonyms like "monitor", "observability", or "instrument my agent" are missing.

4 / 5

Distinctiveness Conflict Risk

It names both tools (Maple + Spring AI) and their integration point, occupying a clear niche with distinct triggers that would not fire for generic tracing skills or other frameworks.

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

MapleTechLabs/maple

Path

skills/maple-agent-tracing-spring-ai/SKILL.md

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.