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.

74

Quality

92%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, token-efficient overview that excels at progressive disclosure and routing. Its main gap is actionability within the body itself: concrete executable code and commands live in the referenced files rather than inline, so the SKILL.md is a dispatcher more than an instruction set.

Suggestions

Add at least one small in-body executable snippet (e.g., a minimal Lambda handler or a single SAM/CDK deploy command) so the overview is actionable without immediately opening a reference.

Surface one concrete validation/verification checkpoint inline (e.g., "after deploying, confirm the API Gateway stage returns 200") rather than deferring all feedback loops to the SOP skills.

Consider a one-line "Quick start" or canonical pattern reference at the top so first-time users get an immediately actionable entry point before the routing tables.

DimensionReasoningScore

Conciseness

Lean overview that assumes Claude's competence — it avoids restating basics and uses dense, scannable routing tables; the version-confirmation note earns its place because runtime values drift.

3 / 3

Actionability

The body routes to executable procedures and the powertools-handler.py asset rather than containing copy-paste code or commands itself; concrete guidance is present via task descriptions but not in-body executable snippets.

2 / 3

Workflow Clarity

Clear sequencing with explicit prioritization ("check these first", "Route to the matching skill before falling back to the references") and a structured routing table; the per-task SOP skills carry the validation feedback loops.

3 / 3

Progressive Disclosure

A clear overview with well-signaled, one-level-deep references — a routing table maps each user need to a specific file, all of which exist (9 reference .md files plus the powertools-handler.py asset), with easy navigation.

3 / 3

Total

11

/

12

Passed

Description

100%

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 highly specific, well-triggered description that names concrete actions, enumerates natural trigger terms including error codes, and disambiguates its scope with an explicit does-not-apply clause. It cleanly answers both what the skill does and when to use it.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "Builds, deploys, manages, debugs, configures, and optimizes" — plus named capabilities like cold starts, CORS, event source mappings, SnapStart, Powertools, and Lambda layers.

3 / 3

Completeness

Explicitly answers both what ("Builds, deploys, manages, debugs...") and when ("Triggers on mentions of...") with explicit trigger guidance; the "Does not apply to..." clause adds negative-scope clarity.

3 / 3

Trigger Term Quality

Strong coverage of natural terms users would say — "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" — including concrete error codes.

3 / 3

Distinctiveness Conflict Risk

A clear AWS-serverless niche with distinct triggers and an explicit exclusion list ("Does not apply to EC2, ECS/Fargate containers, or Amplify hosting"), making a wrong-skill trigger unlikely.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

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.