CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

maple-agent-tracing-google-adk

Trace Google ADK (Agent Development Kit) agents with Maple, in Python (google-adk) and TypeScript (@google/adk): register an OTLP tracer provider, get the transcript and tool calls into the GenAI attributes Maple reads (env switches + a plugin in Python, a span processor in TypeScript), and keep one session per ADK session id. Triggers on 'trace my ADK agent', 'add Maple to Google ADK', 'add Maple to @google/adk', 'agent sessions for Google ADK', 'OpenTelemetry for google-adk'.

80

Quality

100%

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

100%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.

This is a model skill body: a lean, sequenced Steps 0–7 workflow with executable code at every decision point, explicit verification with error-recovery loops, and a clean split of the TypeScript variant into a well-signaled one-level-deep reference. It assumes Claude's competence and spends its tokens exclusively on Maple/ADK-specific knowledge.

DimensionReasoningScore

Conciseness

The body is dense, imperative bullets with zero explanation of concepts Claude already knows — no OTel or ADK tutorials, no padding — and every line is a Maple/ADK-specific fact, constraint, or instruction. Version pins ("google-adk>=2.10", "opentelemetry-sdk<=1.42.1") are functional dependency constraints rather than date-conditional API branches, so they earn their place; nothing matches anchor 4's "minor instances of over-explanation".

5 / 5

Actionability

Fully executable throughout: a copy-paste-ready telemetry.py with complete plugin and span-processor classes, exact env-var and install blocks, a second plugin for error-continuation, and a console-exporter verification snippet. Common variations are covered concretely (CLI vs Runner, existing provider, missing key, human-approval flows), which goes beyond anchor 4's "minor gaps".

5 / 5

Workflow Clarity

Steps 0–7 form a clear sequence from environment detection through verification, and Step 7 is an explicit checklist with feedback loops: 401 → try the other region, a local console exporter when exports fail, and concrete pass criteria when Maple access is unavailable. Anchor 5's "explicit validation steps; feedback loops for error recovery; checklists" is matched; this is not a destructive/batch skill so no cap applies.

5 / 5

Progressive Disclosure

The entire TypeScript variant is appropriately split into references/typescript.md (a real file, one level deep, with no nested references), and it is clearly signaled twice — up front with explicit scope ("follow [references/typescript.md] ... instead of Steps 0-7 below") and in the Reference notes. The remaining inline content is the core Python workflow under clean, navigable step headers, matching the top anchor rather than anchor 4's "minor organization gaps".

5 / 5

Total

20

/

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.

An exemplary description: it states concrete, mechanism-level capabilities for both language ecosystems and gives an explicit trigger clause with natural user phrasings and package-name synonyms. It is dense but not padded — every clause carries information — and it is unmistakably distinct from other tracing skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "register an OTLP tracer provider", "get the transcript and tool calls into the GenAI attributes Maple reads (env switches + a plugin in Python, a span processor in TypeScript)", "keep one session per ADK session id" — with comprehensive coverage of what the skill does in both languages. It goes beyond anchor 4 (minor gaps) because every capability named is concrete and mechanism-level.

5 / 5

Completeness

Explicitly answers both "what" (register an OTLP tracer provider, capture transcript and tool calls into the GenAI attributes Maple reads, one session per ADK session id) and "when" (a literal "Triggers on ..." clause with concrete phrases). This is the exact anchor-5 pattern; anchor 4 would require a less explicit 'when'.

5 / 5

Trigger Term Quality

Five natural trigger phrases ("trace my ADK agent", "add Maple to Google ADK", "agent sessions for Google ADK", "OpenTelemetry for google-adk") plus package-name synonyms (google-adk, @google/adk) and the spelled-out "Agent Development Kit", matching the comprehensive synonym-plus-identifier coverage of the top anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is tightly pinned to "Google ADK (Agent Development Kit) agents with Maple" with both ecosystem package names and ADK-named triggers, so it is clearly distinguishable from generic tracing or other frameworks' skills. Minimal conflict risk; anchor 4 would require noticeable overlap with a closely related skill.

5 / 5

Total

20

/

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-google-adk/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.