CtrlK
BlogDocsLog inGet started
Tessl Logo

aws-serverless

Builds, deploys, manages, debugs, configures, and optimizes serverless applications on AWS using Lambda, API Gateway, Step Functions, EventBridge, and SAM/CDK. Covers cold starts, CORS debugging, event source mappings, troubleshooting, concurrency, SnapStart, Powertools, function URLs, EventBridge Scheduler, Lambda layers, and production readiness. Triggers on mentions of Lambda, API Gateway, Step Functions, SAM templates, CDK serverless stacks, DynamoDB stream triggers, SQS event sources, cold starts, timeouts, 502/504 errors, throttling, concurrency, CORS, Powertools, or any event-driven architecture on AWS, even without the word "serverless." Does not apply to EC2, ECS/Fargate containers, or Amplify hosting.

72

Quality

89%

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

78%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 well-engineered hub skill: the body routes to specialized skills and one-level-deep references with explicit MUST/MUST-NOT boundaries and concrete security baselines, avoiding concept explanations entirely. Its only weakness is advisory prose embedded in routing table cells that slightly inflates token cost without adding routing signal.

DimensionReasoningScore

Conciseness

The body is a dense router with no concept explanations Claude already knows, but several table cells embed paragraph-length advisory prose (e.g. "compare Step Functions pricing (Standard vs Express) against Lambda invocation cost at the expected volume before choosing") that could be trimmed or pushed to a reference. Matches the 4 anchor (efficient, minor over-explanation); not 3 because there is no padding, not 5 because a few routing cells editorialize.

4 / 5

Actionability

Concrete, directive guidance throughout: "you MUST surface the choice between AWS Step Functions and AWS Lambda Durable Functions before implementing", an explicit MUST-NOT scope boundary for the event-bus skill, and specific security actions (CloudTrail execution logging, CloudWatch alarms, least-privilege roles, Secrets Manager/ARN pointers, customer-managed KMS). Not 5 because some directives are soft ("confirm against current AWS documentation", the optional MCP-server pointer) rather than executable steps.

4 / 5

Workflow Clarity

A clear decision sequence is laid out: check specialized skills first, route on explicit trigger signals, then fall back to the general-reference routing table. No destructive or batch operations exist in this file, so no validation cap applies, but the body also lacks the explicit validation checkpoints and error-recovery loops of the 5 anchor — matching the 4 anchor (clear sequence, minor gaps).

4 / 5

Progressive Disclosure

Textbook overview structure: a "User need → Read" routing table whose 9 reference files and assets/powertools-handler.py all exist on disk, references exactly one level deep with only lateral sibling cross-links (no nested chains), plus a useful staleness note directing users to confirm version-sensitive values. Matches the 5 anchor (clear overview, well-signaled one-level-deep references, easy navigation).

5 / 5

Total

17

/

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.

Exemplary description: concrete third-person capability list, explicit trigger clause with natural terms and error codes, and a hard negative boundary against adjacent domains. Every phrase carries either a capability or a trigger; no fluff despite its length.

DimensionReasoningScore

Specificity

Six concrete third-person verbs ("Builds, deploys, manages, debugs, configures, and optimizes") plus named services and specific feature areas (SnapStart, function URLs, EventBridge Scheduler, Lambda layers) give comprehensive, non-generic coverage. Not 4: no coverage gaps; not below 5: every capability is concrete rather than abstract.

5 / 5

Completeness

Explicitly answers both questions: sentences 1-2 state what ("Builds, deploys, manages... serverless applications on AWS") and sentence 3 states when ("Triggers on mentions of...") with concrete trigger phrases. This is the 5 anchor verbatim; the missing-'Use when' cap does not apply because an equivalent explicit trigger clause is present.

5 / 5

Trigger Term Quality

"Triggers on mentions of Lambda, API Gateway, Step Functions, SAM templates, CDK serverless stacks, DynamoDB stream triggers, SQS event sources, cold starts, timeouts, 502/504 errors, throttling, concurrency, CORS, Powertools" covers natural terms users actually say, including raw error codes (502/504) and the guidance that it fires "even without the word 'serverless.'" Not 4: no common variation or synonym is obviously missing.

5 / 5

Distinctiveness Conflict Risk

Clear AWS-serverless niche with distinct triggers, reinforced by an explicit negative boundary: "Does not apply to EC2, ECS/Fargate containers, or Amplify hosting." Not 4: the exclusion boundary eliminates the main adjacent-skill overlap.

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
aws/agent-toolkit-for-aws
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.