CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

serverless-integrations

Use when adding, modifying, debugging, or reviewing dd-trace-js serverless platform integrations that create root invocation spans for AWS Lambda, Azure Functions, Google Cloud Functions, or similar runtimes. Triggers: serverless integration, function invocation root span, Lambda runtime, Azure Functions, GCP Functions, type = 'serverless', DD_LAMBDA_HANDLER, datadog-lambda-js, deployed serverless verification, manual serverless test.

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

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.

The body is a well-structured, token-efficient overview that gives concrete paths, APIs, and invariants while delegating depth to one-level-deep reference files; its only weakness is that the validation feedback loop lives in the referenced testing guide rather than inline in the workflow.

Suggestions

Add an explicit inline validate->fix->retry checkpoint in the Workflow (e.g. 'After implementing, run the deployed verification from testing-guide.md; if traces do not appear in Datadog, re-check context extraction and flush behavior before proceeding') to lift workflow_clarity to 5.

Consider a one-line note in the Workflow step 1 linking the Decision Gate rows to their reference sections, so classification maps directly to the right reference file.

DimensionReasoningScore

Conciseness

The body is lean — bullets, a compact decision table, and checklists — and never explains concepts Claude already knows (e.g. what a span or Lambda is); every line carries a concrete invariant, path, or guard.

5 / 5

Actionability

Guidance is concrete and executable for an internal-codebase skill: exact paths (packages/datadog-instrumentations/, packages/dd-trace/src/plugins/index.js), named helpers (web.patch, web.startServerEndlessSpanWithInferredProxy, web.finishAll), and specific flags (static kind = 'server', static type = 'serverless').

5 / 5

Workflow Clarity

A clear Decision Gate plus a 4-step numbered Workflow (classify -> study references -> implement -> test/verify) and an Implementation/Review Checklist give a strong sequence, but the validate->fix->retry feedback loop is delegated to references rather than stated inline, leaving a minor checkpoint gap.

4 / 5

Progressive Disclosure

SKILL.md is a true overview pointing to four well-signaled, one-level-deep references (architecture.md, reference-integrations.md, implementation-guide.md, testing-guide.md) — all verified to exist — with content appropriately split for easy navigation.

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.

The description is exemplary: third-person, concise, and explicit about both what the skill does and when to use it, with a rich trigger-term list and a clearly bounded niche that distinguishes it from related integration skills.

DimensionReasoningScore

Specificity

Names multiple concrete actions ('adding, modifying, debugging, or reviewing') tied to a specific outcome ('create root invocation spans for AWS Lambda, Azure Functions, Google Cloud Functions'), giving comprehensive coverage rather than vague abstraction.

5 / 5

Completeness

It opens with an explicit 'Use when adding, modifying, debugging, or reviewing...' clause (the when) and states what the skill does (serverless platform integrations creating root invocation spans), with concrete trigger phrases — both what and when are explicit.

5 / 5

Trigger Term Quality

An explicit 'Triggers:' list covers natural phrases (Lambda runtime, Azure Functions, GCP Functions, serverless integration) plus synonyms and technical identifiers (type = 'serverless', DD_LAMBDA_HANDLER, datadog-lambda-js), matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is sharply bounded to dd-trace-js serverless platform integrations with distinct identifiers (DD_LAMBDA_HANDLER, datadog-lambda-js, type = 'serverless'), giving minimal overlap risk with sibling skills like apm-integrations.

5 / 5

Total

20

/

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

DataDog/dd-trace-js

Path

.agents/skills/serverless-integrations/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.