CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aws-serverless-eda

AWS serverless and event-driven architecture expert based on Well-Architected Framework. Use when building serverless APIs, Lambda functions, REST APIs, microservices, or async workflows. Covers Lambda with TypeScript/Python, API Gateway (REST/HTTP), DynamoDB, Step Functions, EventBridge, SQS, SNS, and serverless patterns. Essential when user mentions serverless, Lambda, API Gateway, event-driven, async processing, queues, pub/sub, or wants to build scalable serverless applications with AWS best practices.

Quality

77%

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_all/aws-skills/skills/aws-serverless-eda/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 dense, code-rich reference with excellent concrete examples and a genuinely well-wired bundle of six on-disk reference files. The main costs are token bloat — duplicated MCP sections and pattern code that mirrors the reference files — and the absence of any sequenced workflow with validation checkpoints, leaving the body a catalog rather than a guided procedure.

Suggestions

Collapse the 'Integrated MCP Servers' and 'Using MCP Servers Effectively' sections into one, removing the near-duplicate capability lists and cutting roughly 80 lines.

Move the full inline pattern implementations (Event Router, Saga, Event Sourcing, API/Kinesis/webhook patterns) into the existing references/serverless-patterns.md and references/eda-patterns.md, keeping only short summaries or one signature example per pattern in SKILL.md.

Add a short sequenced workflow (e.g., verify service info via AWS Docs MCP → build/deploy via Serverless MCP → test via Lambda Tool MCP → validate the deployment) with explicit validation checkpoints so the MCP tooling guidance becomes an ordered procedure.

DimensionReasoningScore

Conciseness

The code examples are on-point, but there is noticeable padding: the MCP server capabilities are listed in full and then essentially repeated in "Using MCP Servers Effectively", and sections restate knowledge Claude already has ("Benefits of Step Functions: Visual workflow representation, Built-in error handling...", "Use environment variables for configuration"). It stays above a 2 because the bulk of the body is concrete pattern code rather than conceptual explanation, and much of the restated material is what a user would want at-a-glance.

3 / 5

Actionability

The body is dominated by concrete, near-executable TypeScript/CDK and Lambda handler examples covering idempotency, retries, DLQs, fan-out, sagas, and event sourcing — copy-paste quality with real API calls. Minor gaps: several snippets reference undefined symbols (dlq, processFunction, reserveFlightFunction) or contain "// ... configuration" placeholders, so they are mostly rather than fully executable.

4 / 5

Workflow Clarity

The skill is organized as a reference catalog (principles → patterns → best practices) with a "When to Use This Skill" bullet list, but it never lays out a sequenced build/deploy/test workflow with checkpoints. The MCP sections imply a rough order (verify docs → implement → deploy → test locally) yet no explicit validation steps exist, matching "sequence present but checkpoints missing or implicit" rather than the coherent ordered workflow of a 4.

3 / 5

Progressive Disclosure

All six referenced files (serverless-patterns.md, eda-patterns.md, security-best-practices.md, observability-best-practices.md, performance-optimization.md, deployment-best-practices.md) exist, are one level deep, and are clearly signaled with paths plus per-file scope summaries, plus curated external links. It falls short of 5 because the ~500 lines of inline pattern code substantially duplicate the subject matter of references/serverless-patterns.md and references/eda-patterns.md — content that should live in those files is inlined in the overview.

4 / 5

Total

14

/

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, well-structured description: third-person voice, explicit "Use when..." and "when user mentions..." trigger clauses, and a concrete enumeration of covered AWS services. Its only weaknesses are slightly generic action verbs ("building") and a few platform-agnostic trigger terms that create minor overlap risk with broader architecture skills.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — "building serverless APIs, Lambda functions, REST APIs, microservices, or async workflows" and "Covers Lambda with TypeScript/Python, API Gateway (REST/HTTP), DynamoDB, Step Functions, EventBridge, SQS, SNS" — with named services rather than generic claims. Not a 5 because the "what" leans on enumerating technologies while the actual actions stay at the level of "building" rather than more granular tasks (deploy, configure, orchestrate).

4 / 5

Completeness

Explicitly answers both: the "what" is stated ("AWS serverless and event-driven architecture expert... Covers Lambda with TypeScript/Python, API Gateway (REST/HTTP), DynamoDB, Step Functions, EventBridge, SQS, SNS, and serverless patterns") and the "when" is given twice with concrete trigger phrases ("Use when building serverless APIs..." and "Essential when user mentions serverless, Lambda, API Gateway, event-driven, async processing, queues, pub/sub..."). Both are present, explicit, and trigger-phrase-rich.

5 / 5

Trigger Term Quality

"Essential when user mentions serverless, Lambda, API Gateway, event-driven, async processing, queues, pub/sub" covers the natural phrases a user would say, plus "REST APIs", "microservices", and "async workflows". A few natural synonyms are missing (e.g., "Step Functions" appears only in the coverage list, no mention of "deploy", "webhooks", or "CloudWatch"), so it falls just short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

The AWS serverless/event-driven niche is clearly delimited by service-specific triggers (Lambda, API Gateway, EventBridge, Step Functions, DynamoDB). Minor overlap remains: "microservices", "REST APIs", "queues", and "pub/sub" are platform-agnostic terms that could also match a general architecture or non-AWS messaging skill, so it is mostly distinct rather than minimal-conflict.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (748 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

Microck/ordinary-claude-skills

Path

skills_all/aws-skills/skills/aws-serverless-eda/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.