CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

maple-agent-tracing

Trace an AI agent or LLM app with Maple so each conversation shows up as one Agent Session with its transcript, model calls, tool calls, tokens, cost and failures. Detects the agent framework (Vercel AI SDK, eve, OpenAI Agents SDK, Mastra, LangChain/LangGraph, Claude Agent SDK, Pydantic AI, LlamaIndex, CrewAI, Google ADK, Strands, smolagents, Agno, DSPy, Haystack, Microsoft Agent Framework, Spring AI, LiteLLM, OpenRouter, raw provider SDKs) and installs the matching per-framework skill. Triggers on 'trace my agent', 'add agent observability', 'LLM tracing with Maple', 'set up Maple agent sessions', 'OpenTelemetry for my AI agent'.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 tight, highly actionable router skill: executable install commands, exact dependency signatures, and clear routing precedence. The only gap is that validation of a successful install/hand-off is delegated to the sub-skills rather than checked explicitly.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — a one-line scope statement, a dense dependency-to-skill table where every row is load-bearing, and a short 'Order matters' paragraph carrying routing logic; the eve-row elaboration is necessary disambiguation, not the trimmable over-explanation of the 4 anchor.

5 / 5

Actionability

Fully executable guidance: a copy-paste install command ('npx skills add MapleTechLabs/maple/skills --skill <skill> -y') with a concrete fallback URL, exact manifest filenames to scan, and exact package names per routing row.

5 / 5

Workflow Clarity

Steps 1–3 are clearly sequenced with a Step 3 hand-off checklist, but validation is delegated to the installed sub-skill ('After the per-framework skill's own checks pass') rather than explicitly verified here; not 5 because the top anchor demands explicit validation and feedback loops, not 3 because the sequence and hand-off conditions are unambiguous and the operation is non-destructive.

4 / 5

Progressive Disclosure

A single-purpose router under ~54 lines with no bundle files (no references/, scripts/, or assets/ exist); the inline routing table is decision-time content that belongs in the body and sections are well organized, so the simple-skill exception applies.

5 / 5

Total

19

/

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: concrete third-person capabilities, explicit trigger phrases, both what-and-when answered, and a distinct Maple-branded niche. No fluff or over-claims are present.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Trace an AI agent or LLM app with Maple so each conversation shows up as one Agent Session with its transcript, model calls, tool calls, tokens, cost and failures' and 'Detects the agent framework ... and installs the matching per-framework skill' — in third-person voice, with comprehensive coverage matching the top anchor.

5 / 5

Completeness

Both 'what' (traces agents into Agent Sessions with transcript, calls, tokens, cost, failures; detects framework; installs matching skill) and 'when' (explicit 'Triggers on ...' phrases) are clearly and explicitly stated, matching the top anchor exactly.

5 / 5

Trigger Term Quality

It provides five natural user phrasings ('trace my agent', 'add agent observability', 'LLM tracing with Maple', 'set up Maple agent sessions', 'OpenTelemetry for my AI agent') plus a full list of framework names users would naturally mention, matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

It occupies a clear Maple-specific niche with triggers uniquely tied to Maple agent tracing, so conflict with other skills is minimal; nothing pushes it toward the 4 anchor's 'minor overlap risk'.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

MapleTechLabs/maple

Path

skills/maple-agent-tracing/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.