CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

maple-onboarding-style

General OpenTelemetry onboarding style for Maple: native APIs, the business-span pattern, inline keys, VCS resource attributes, per-framework notes, business signals, export verification, LLM calls, and smoke checks.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/maple-onboarding-style/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 a strong, lean style guide: highly actionable with complete code examples, exact attribute keys, and a verification section that includes real error-recovery loops. Its weaknesses are minor — some verbatim repetition between sections and a couple of long sections (LLM calls, framework notes) that could be offloaded to reference files.

DimensionReasoningScore

Conciseness

The body is dense, prescriptive Maple-specific policy with no padding on concepts Claude already knows — every rule ("Don't read OTEL_EXPORTER_OTLP_* env vars", "Do not shell out to git from the running process") is non-obvious. Minor trims exist: "provider setup, exporter construction, log bridging, and framework instrumentation" is repeated verbatim in "Verify export" and "Smoke checks", and the commit-SHA env-var enumeration (VERCEL_GIT_COMMIT_SHA, RAILWAY_GIT_COMMIT_SHA, GITHUB_SHA, SOURCE_COMMIT, GIT_COMMIT, HEROKU_SLUG_COMMIT) runs long, so it sits at anchor 4 rather than 5.

4 / 5

Actionability

Guidance is fully executable: the complete tracer.startActiveSpan try/catch/finally TypeScript example, the MapleBrowser.init(...) snippet with exact options, the exact curl sanity check ("curl -X POST <endpoint>/v1/traces -H \"authorization: Bearer MAPLE_TEST\" ... -d '{}' returns 200"), exact semantic-convention keys (vcs.repository.url.full, gen_ai.usage.cost, maple_ai.session.id), and exact package names cover the common cases copy-paste ready, matching anchor 5.

5 / 5

Workflow Clarity

As a topic-organized style guide it is not an end-to-end sequenced workflow, but the "Verify export" section is a numbered sequence with explicit checkpoints ("Don't ship if the app's own startup is now broken") and a genuine error-recovery feedback loop (401 → try the other region's ingest → prove the path with MAPLE_TEST → disclose in the hand-off). The overall ordering of sections (bootstrap → instrument → verify) stays implicit, which keeps it at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist, and per-framework detail is appropriately delegated to clearly signaled one-level-deep sibling skills ("see maple-nextjs-style", "see maple-effect-style") rather than inlined. However, the LLM-calls section (~44 lines) and the framework notes are long enough that they could be split into reference files, leaving minor organization gaps that fit anchor 4 rather than a clean anchor 5 split.

4 / 5

Total

17

/

20

Passed

Description

58%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 does a good job enumerating specific, comprehensive coverage topics for the Maple OTel onboarding domain, but it reads as a table of contents rather than a triggering description: it lacks any "Use when..." guidance, uses internal jargon users would not naturally say, and omits the most common synonyms (OTel, telemetry, tracing, instrumentation) users would type when they need this skill.

Suggestions

Add an explicit trigger clause, e.g. "Use when onboarding a Maple project to OpenTelemetry, instrumenting an app with OTel, or adding telemetry/tracing to a repo that reports to Maple."

Include the natural synonyms users actually say — "OTel", "telemetry", "tracing", "instrumentation" — alongside "OpenTelemetry" so the description matches how the need is voiced.

Rephrase a few topic nouns as actions (e.g. "wrap critical business operations in spans, set VCS resource attributes, verify OTLP export") to strengthen the concrete-action phrasing.

DimensionReasoningScore

Specificity

The description enumerates nine concrete coverage areas ("native APIs, the business-span pattern, inline keys, VCS resource attributes, per-framework notes, business signals, export verification, LLM calls, and smoke checks"), which exceeds anchor 3's 1-2 concrete actions, but every item is a noun phrase with no action verbs, so it falls short of anchor 5's "extract text, fill forms, merge documents" style of specific concrete actions.

4 / 5

Completeness

The "what" is clear ("General OpenTelemetry onboarding style for Maple" plus the enumerated topics), but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. The "when" is only weakly implied by the topic list.

3 / 5

Trigger Term Quality

"OpenTelemetry" and "LLM calls" are natural user terms, but the common variations a user would actually say for this need — "OTel", "telemetry", "tracing", "instrumentation" — are absent, and much of the list ("business-span pattern", "inline keys", "VCS resource attributes") is internal jargon users would not naturally say. This matches anchor 3 ("some relevant keywords but missing common variations or synonyms") better than anchor 4, which requires the core natural vocabulary to be present with only a few terms missing.

3 / 5

Distinctiveness Conflict Risk

"OpenTelemetry onboarding style for Maple" carves out a clear niche, but "per-framework notes" signals real overlap with closely related sibling skills (maple-nextjs-style, maple-effect-style) that cover adjacent framework instrumentation, fitting anchor 4's "mostly distinct; minor overlap risk with closely related skills" rather than anchor 5's minimal conflict risk.

4 / 5

Total

14

/

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-onboarding-style/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.