CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

maple-agent-tracing-openrouter

Trace OpenRouter calls with Maple: route OpenRouter Broadcast (OTLP) to Maple and edit the app's OpenRouter requests to send session_id and trace ids, so each conversation is one Maple Agent Session with model calls, tokens and real cost. Triggers on 'trace my openrouter calls', 'add Maple to openrouter', 'agent sessions for openrouter', 'OpenTelemetry for openrouter', 'openrouter broadcast to maple'.

77

Quality

97%

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

96%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 tightly written, highly actionable runbook: executable code for multiple clients, exact dashboard configuration, and a thorough verification checklist with error-recovery guidance. The only structural weakness is that the long inline 'Known behavior' catalog keeps a single file where a references/ split would improve progressive disclosure.

Suggestions

Move the 'Known behavior' attribute and edge-case catalog (span-tree shapes, gen_ai attribute list, truncation limits) into a references/broadcast-behavior.md file, keeping a 2-3 line pointer in Step 8 so verification can pull details on demand.

The version minimums inline in Step 2 ('openai npm (>= 7)', '>= 3', '>= 3.1') are fine as support requirements, but consider grouping them in one line per client so future version changes touch a single spot.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious facts Claude cannot know (e.g. 'a trace with two different ids is assigned to the lexically larger one, silently', 'keys are region-bound') and contains no padding or explanations of known concepts, matching the lean anchor 5 rather than the minor-trimming anchor 4.

5 / 5

Actionability

Copy-paste-ready TypeScript and Python snippets, exact ingest endpoints and headers, literal dashboard settings with URLs, and a concrete verification checklist fully cover the common client cases, matching anchor 5; anchor 4 would require missing key details, and none are evident.

5 / 5

Workflow Clarity

Steps 0-8 are clearly sequenced with detection branching in Step 0, explicit validation in Step 8, and recovery feedback ('If ~2x: Step 3 nesting or response-id match is missing'; a 401 means 'switch the endpoint to the other region'), matching the anchor-5 pattern of validation steps plus error-recovery loops.

5 / 5

Progressive Disclosure

Section structure is good and steps are easy to navigate, but this is a single ~170-line file with no bundle: the 'Known behavior' section is ~20 lines of inline attribute/edge-case reference material that would fit a one-level-deep references file. That matches anchor 4 (good structure, minor organization gaps) rather than anchor 5, which requires well-signaled separate-file references.

4 / 5

Total

19

/

20

Passed

Description

96%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 states concrete capabilities, an explicit outcome, and five natural trigger phrases. The only weakness is slight trigger overlap with generic OpenTelemetry setup intent and a sibling Maple tracing skill.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'route OpenRouter Broadcast (OTLP) to Maple', 'edit the app's OpenRouter requests to send session_id and trace ids' — with a concrete outcome ('each conversation is one Maple Agent Session with model calls, tokens and real cost'), matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

It explicitly answers both 'what' (route Broadcast to Maple and edit requests to send session_id/trace ids so each conversation is one Agent Session) and 'when' (an explicit trigger clause with concrete phrases), which is the anchor-5 pattern; anchor 4 would require the 'when' to be less explicit.

5 / 5

Trigger Term Quality

'Triggers on 'trace my openrouter calls', 'add Maple to openrouter', 'agent sessions for openrouter', 'OpenTelemetry for openrouter', 'openrouter broadcast to maple'' covers natural user phrasings plus synonyms (OpenTelemetry, agent sessions, broadcast), matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

The Maple+OpenRouter niche is clear with distinct, product-specific triggers, but 'OpenTelemetry for openrouter' could fire for users wanting a non-Maple OTel backend, and a closely related framework-tracing skill exists — minor overlap risk, matching anchor 4 rather than the minimal-conflict anchor 5.

4 / 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-openrouter/SKILL.md

Revision

f1305bd

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill