CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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, Durable Functions, durable execution, checkpoint-and-replay, and production readiness. Use when the user mentions 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, Durable Functions, durable execution, checkpoint-and-replay, or any event-driven architecture on AWS, even if they don't say "serverless." Do NOT use for EC2, ECS/Fargate containers, or Amplify hosting.

Quality

98%

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

100%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.

An exemplary hub-style SKILL.md: a lean body that assumes competence, routes each user need to a specific, verified reference file, and pushes all detail (and version-sensitive values) into a well-organized one-level-deep bundle. The only structural observation is mild redundancy between the Routing and Files tables, but they serve complementary purposes (when to read vs. what's inside) and cost only a few lines.

DimensionReasoningScore

Conciseness

The ~37-line body is pure routing and navigation: no explanation of what Lambda or serverless is, no filler, and every row earns its tokens. The staleness caveat ("confirm values against current AWS documentation") is two lines and handles time-sensitive content by directing verification rather than embedding version numbers.

5 / 5

Actionability

Every routing row names a real file and what it contains ("Read troubleshooting.md — starts with the 5 most common fixes"; "Use powertools-handler.py as a template" — a real, complete executable template), and the rows cover the common cases (build, debug, optimize, event sources, orchestration, concurrency, API Gateway, anti-patterns). Per the rubric's code-vs-instruction note, absence of inline code is not penalized when guidance is this actionable.

5 / 5

Workflow Clarity

This is a single-action routing skill and the single action (match user need → read the named reference) is unambiguous; the 'Spans multiple areas' row even handles the ambiguous case ('read the most specific reference first, then consult others'). No destructive or batch operations appear, so the validation cap does not apply, and the simple-skill exception yields 5.

5 / 5

Progressive Disclosure

Scored against the actual bundle: all 9 referenced .md files and the asset exist and match their described contents; references are exactly one level deep (spot-checks show reference files link only to external AWS docs, never to each other or to third-level files); the Routing and Files tables make navigation trivial.

5 / 5

Total

20

/

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.

A model description: third-person, concrete action verbs, an enumerated capability list, comprehensive natural trigger terms including error codes and symptoms, and both positive and negative boundary guidance. The only nit is density — the term lists are long and a few items (Powertools, durable execution, checkpoint-and-replay) repeat between the 'Covers' and 'Use when' clauses — but the repetition serves the what/when split and stays within exemplar style.

DimensionReasoningScore

Specificity

"Builds, deploys, manages, debugs, configures, and optimizes serverless applications" lists multiple concrete actions, and the "Covers" sentence enumerates specific capabilities (cold starts, CORS debugging, event source mappings, SnapStart, Powertools, function URLs) — comprehensive coverage matching the anchor-5 exemplar rather than the 'minor gaps' of anchor 4.

5 / 5

Completeness

Explicitly answers both questions: what it does (builds/deploys/debugs/optimizes serverless apps across named services) and when to use it via a concrete "Use when the user mentions..." trigger list, plus a negative boundary ("Do NOT use for EC2, ECS/Fargate containers, or Amplify hosting"). The missing-'Use when' cap does not apply.

5 / 5

Trigger Term Quality

The 'Use when' clause covers natural user phrasing comprehensively, including symptom terms users actually say ("cold starts, timeouts, 502/504 errors, throttling, concurrency, CORS") and synonyms ("SAM templates", "CDK serverless stacks", "DynamoDB stream triggers", "SQS event sources"), plus the catch-all "any event-driven architecture on AWS, even if they don't say 'serverless.'"

5 / 5

Distinctiveness Conflict Risk

A clear AWS-serverless niche anchored by named services (Lambda, API Gateway, Step Functions, EventBridge, SAM/CDK), with the explicit exclusion of EC2, ECS/Fargate, and Amplify minimizing overlap with adjacent AWS skills.

5 / 5

Total

20

/

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

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository

mreferre/aws-agent-toolkit-skills

Path

.kiro/skills/aws-serverless/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.