CtrlK
BlogDocsLog inGet started
Tessl Logo

aws-lambda-durable-functions

Builds resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions. Covers the critical replay model, step operations, wait/callback patterns, error handling with saga pattern, testing with LocalDurableTestRunner. Triggers on phrases like lambda durable functions, durable execution, workflow orchestration, state machines, retry/checkpoint patterns, long-running stateful Lambda functions, saga pattern, human-in-the-loop callbacks, reliable serverless applications, context.step, context.wait, context.invoke, context.runInChildContext, withDurableExecution, DurableContext, UnrecoverableInvocationError, durable-execution-sdk, qualified ARN invocation, and durable handler replay.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 well-organized, actionable, and uses progressive disclosure effectively with a clear reference-routing table and real bundle files. Its main weakness is workflow clarity, where validation/feedback loops for replay-model violations are implicit rather than explicit, plus minor redundancy and truncated critical rules.

Suggestions

Add an explicit validate->fix->retry feedback loop for replay-model violations (e.g., after checking non-deterministic code outside steps, instruct to move it into a step and re-verify) to raise workflow_clarity above 3.

Complete Critical Rules #5 and #6 into full sentences so each rule is an executable instruction rather than a fragment (e.g., '#5 Closure mutations are lost on replay - return values from steps instead of mutating outer variables').

Deduplicate the replay-model violations between Critical Rules and the Validation Guidelines section, or explicitly cross-reference one from the other to remove redundancy.

DimensionReasoningScore

Conciseness

Mostly efficient with tight Critical Rules, quick reference, IAM, and validation checklists that assume competence; minor redundancy where Critical Rules #4-#6 are restated in the Validation Guidelines section.

4 / 5

Actionability

Provides executable TypeScript/Python handler examples, real `aws lambda invoke --function-name my-function:1` commands, and specific IAM actions; minor gaps include the truncated Critical Rules #5 and #6 which read as fragments rather than complete instructions.

4 / 5

Workflow Clarity

The "When to Load Reference Files" mapping and Validation checklists give a usable sequence, but the writing/reviewing workflow lacks explicit validation checkpoints and feedback loops (e.g., detect replay violation -> fix -> re-validate) for destructive/batch durable operations.

3 / 5

Progressive Disclosure

SKILL.md is a clear overview with a well-signaled "When to Load Reference Files" routing table mapping user intent to one-level-deep reference files, all of which exist; navigation is easy and content is appropriately split.

5 / 5

Total

16

/

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 comprehensive and well-structured, explicitly stating capabilities and providing an extensive trigger-phrase list that drives activation. It avoids vagueness and over-claiming.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities ("automatic state persistence, retry logic, and orchestration", "replay model, step operations, wait/callback patterns, error handling with saga pattern, testing with LocalDurableTestRunner") covering the domain comprehensively.

5 / 5

Completeness

Explicitly answers "what" (builds resilient long-running multi-step applications with state persistence, retry, orchestration) and "when" ("Triggers on phrases like...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

The "Triggers on phrases like" clause provides comprehensive natural terms including synonyms and technical symbols ("lambda durable functions", "durable execution", "workflow orchestration", "state machines", "saga pattern", "context.step", "withDurableExecution", "durable-execution-sdk").

5 / 5

Distinctiveness Conflict Risk

A clear niche (AWS Lambda durable functions) with highly specific triggers and named SDK symbols, making overlap with other skills minimal.

5 / 5

Total

20

/

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.

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.