CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

observability

Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.

65

Quality

82%

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

77%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.

Highly actionable content with excellent executable code, commands, and well-validated multi-step workflows (preflight, post-deploy error scan, performance audit). It is held back by a monolithic single-file structure with no references/ split and by duplicated logging and RootLayout examples that pad the token budget.

Suggestions

Move the Web Analytics drain payload schemas, the NDJSON streaming reader, and the Marketplace vendor integration sections into references/ files, keeping SKILL.md as a navigable overview.

Deduplicate the structured-logging baseline against the Runtime Logs example, and show the combined Analytics + SpeedInsights RootLayout once instead of three near-identical layout examples.

Tighten the Speed Insights metrics table and vendor sections to only Vercel-specific thresholds and setup steps Claude could not derive on its own.

DimensionReasoningScore

Conciseness

The body is mostly tight and code/table-driven, but contains real duplication: the "Structured Logging Baseline" block is restated almost verbatim under "Runtime Logs → Structured Logging", and the RootLayout example appears three times (Analytics setup, Speed Insights setup, and the combined full-stack setup). This goes beyond the "minor instances" of anchor 4, fitting anchor 3 ("mostly efficient... could be tightened").

3 / 5

Actionability

Fully executable throughout: copy-paste curl commands for the drains REST API (list/create/test/update/delete), complete TypeScript handlers, an NDJSON streaming reader with AbortController timeout, HMAC signature verification code, exact dashboard URLs, and findings-to-action tables. Matches the anchor-5 copy-paste-ready standard.

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced with validation checkpoints and feedback loops: deploy preflight checks drain configuration and errored drains before promotion, the post-deploy scan specifies "wait 60 seconds after READY state" then maps findings to actions, and a numbered 10-step performance audit exists — a direct match for anchor 5.

5 / 5

Progressive Disclosure

No bundle files exist; ~650 lines are inlined monolithically, including drain payload schemas, the full NDJSON parser implementation, and four vendor-integration sections that clearly belong in separate references files (anchor 2/3 territory). Good section headers and cross-skill pointers ("⤳ skill: vercel-api") keep it at anchor 3 rather than 2, but content that should be separate is inline.

3 / 5

Total

16

/

20

Passed

Description

83%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 description with an explicit Use-when clause, concrete trigger verbs, and comprehensive domain coverage. Its main weakness is that it lists feature nouns under the fluffy action phrase "expert guidance" rather than stating concrete actions, and it misses a few natural trigger phrasings and file/package signals.

Suggestions

Replace the vague action "expert guidance" with concrete verbs, e.g. "Configure Drains, set up Web Analytics and Speed Insights, add structured logging, and verify drain payload signatures".

Add natural user phrasings and file/package triggers such as "instrumentation.ts", "@vercel/analytics", "check the logs", and "why is my function slow" to trigger_term coverage.

DimensionReasoningScore

Specificity

Enumerates seven concrete domain areas ("Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards") with comprehensive coverage, but the action itself is the vague phrase "expert guidance" — the items are feature nouns, not concrete verbs as in the anchor-5 example.

4 / 5

Completeness

Explicitly answers both: a clear "what" (the enumerated Vercel observability stack) and a concrete "Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel" trigger clause — a direct match for the anchor-5 example.

5 / 5

Trigger Term Quality

Good natural keywords: "instrumenting", "debugging", "optimizing application performance", "monitoring", "logs", "analytics", "traces", "OpenTelemetry". A few natural phrasings users would say are missing (e.g. "check the logs", "slow", "error tracking") along with file/package signals like instrumentation.ts or @vercel/analytics, so it falls short of anchor 5's synonym-and-extension comprehensiveness.

4 / 5

Distinctiveness Conflict Risk

"Vercel" pins the platform and the triggers are observability-specific, but "debugging, or optimizing application performance" could overlap with generic debugging/performance skills if the trailing "on Vercel" qualifier is missed — anchor 4 ("mostly distinct; minor overlap risk with closely related skills").

4 / 5

Total

17

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (774 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

13

/

16

Passed

Repository

openai/plugins

Path

plugins/vercel/skills/observability/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.