maple-onboard

Onboard a project to Maple by installing OpenTelemetry traces, logs, and metrics across every app and service in the repo. Triggers on requests like 'install Maple', 'set up Maple', 'add Maple telemetry', 'onboard this repo to Maple', 'instrument with OpenTelemetry for Maple'.

Quality

91%

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

88%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.

The body is an exceptionally actionable, well-sequenced orchestration guide with strong validation checkpoints for a repo-wide batch operation. Its main weaknesses are mild redundancy around the inline-key rationale and the fact that per-stack detail is inlined rather than fully delegated to the companion style skills it already points to.

Suggestions

State the inline-ingest-key rule once (Step 0) and have the bootstrap rules and Hard rules reference it in a few words instead of re-explaining the rationale, saving ~10 lines.

Trim the Step 2 'Framework rules' bullets that duplicate the companion style skills (e.g., Next.js and Expo detail) to package choices plus a pointer, keeping the inline detail for stacks where no companion exists.

Consolidate the repeated 'every app and service, do not skip' instruction into Step 1 only, where the enumeration procedure already enforces it.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-inferable Maple-specific facts (region table, key semantics, per-stack package choices) and avoids explaining known concepts, but the inline-key rationale repeats three times (Step 0, bootstrap rules, Hard rules) and the 'cover every service' point recurs, so minor trimming is possible.	4 / 5
Actionability	Exact packages per stack, a complete MapleBrowser.init snippet, a copy-paste curl smoke test with headers, the `claude mcp add` command, named MCP verification calls (`list_services`, `audit_setup`), and ready-made hand-off text cover the common execution cases.	5 / 5
Workflow Clarity	Steps 0-6 are clearly sequenced, and Step 4 is an explicit validation gate for this batch operation (run dev/build, confirm export with `OTEL_LOG_LEVEL=debug`, confirm landing via MCP) with a feedback loop (401 -> try other region -> `MAPLE_TEST` fallback -> report), plus 'Don't ship if the app's own startup is now broken.'	5 / 5
Progressive Disclosure	Companion style-skill references are clearly signaled and one level deep with a fallback URL, but no bundle files ship with this skill, and per-stack framework rules are inlined in the body that largely mirror those companions, leaving minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

95%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.

The description is excellent: third-person, concrete about what it does, and explicit about when to trigger it with five natural synonyms. It is a near-exemplar of the 'good' pattern, with only slightly limited action coverage keeping specificity at 4.

Dimension	Reasoning	Score
Specificity	"installing OpenTelemetry traces, logs, and metrics across every app and service in the repo" lists several concrete actions with a clear scope, but coverage stops short of the full set of capabilities (e.g., verification and hand-off), matching the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	It explicitly answers both what it does ("installing OpenTelemetry traces, logs, and metrics across every app and service in the repo") and when to use it ("Triggers on requests like ..."), with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Triggers on requests like 'install Maple', 'set up Maple', 'add Maple telemetry', 'onboard this repo to Maple', 'instrument with OpenTelemetry for Maple'" provides comprehensive natural-language coverage with synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The Maple/OpenTelemetry onboarding niche and product-specific trigger phrases ('install Maple', 'onboard this repo to Maple') are clearly distinct from any other skill, with minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MapleTechLabs/maple
Path: skills/maple-onboard/SKILL.md
Commit: 1a03fa7

Reviewed: 10 hours 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.