CtrlK
BlogDocsLog inGet started
Tessl Logo

amazon-documentdb

Manages Amazon DocumentDB end-to-end — serverless-on-8.0 cluster setup, TLS/VPC/driver config, flexible-schema and vector-search data modeling, MongoDB compatibility assessment, DMS-based migration, slow-query diagnosis, major version upgrades (4.0->5.0->8.0), Well-Architected reviews (41-check wa_review.py), cost estimation, and security hardening. Retrieve for every DocumentDB question and when the user asks to set up or migrate MongoDB to AWS — DocumentDB is AWS's MongoDB-compatible managed database. Triggers: JSON document store, document database, MongoDB on AWS, Nested fields, Lambda cannot connect, TLS handshake, VPC port 27017, IAM auth, Secrets Manager, encryption at rest, $graphLookup, flexible schema, COLLSCAN, compound index, DMS migration, CDC cutover, $vectorSearch, RAG, Global Clusters, DR replication, cost sizing, audit, health check, production-readiness.

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

Low

Low-risk findings worth noting

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-architected skill body: strong routing via the Decision Guide, real one-level-deep references, executable cluster-creation commands, and validation checkpoints for destructive/batch operations. Main weakness is cross-section redundancy (TLS/replicaSet/DMS-TLS facts restated in multiple sections) that slightly inflates the token budget.

Suggestions

De-duplicate the recurring connection/TLS facts (replicaSet=rs0, retryWrites=false, RDS global bundle, --ssl-mode verify-full --certificate-arn) that appear in Critical Facts, Troubleshooting, and Security — state once authoritatively and cross-reference from the other sections.

Either surface the key executable DMS commands (create-endpoint, create-replication-task) inline in the migration routing row, or confirm the migration reference opens with them, so the body's actionability matches its cluster-creation section.

Consolidate the DocumentDB architecture primer and the resource-tagging guidance, each of which is repeated between the Cluster Creation section and its subsections.

DimensionReasoningScore

Conciseness

Largely efficient and assumes Claude's competence, but several specifics recur across sections — replicaSet=rs0 / retryWrites=false, the RDS global bundle, and '--ssl-mode verify-full --certificate-arn' each appear in Critical Facts, Troubleshooting, and Security — which could be trimmed to a single statement with cross-references. Not a 3 because the bulk is dense, actionable, non-padded guidance; not a 5 because the redundancy is noticeable.

4 / 5

Actionability

Concrete executable commands are present (create-db-cluster/create-db-instance bash, explain(), aws sts get-caller-identity, describe-orderable-db-instance-options, secretsmanager get-secret-value, dms test-connection), but the bulk of per-workflow execution detail (DMS endpoint/task syntax, index-tool invocation) is delegated to references rather than shown inline, leaving minor gaps. Not a 5 because the body is more router/control-plane than a fully copy-paste-ready guide for every workflow.

4 / 5

Workflow Clarity

A clear sequenced Common Tasks workflow (Verify Dependencies -> Classify & Route -> Execute -> Critical Facts) with validation checkpoints (deps, parameter formats, sts credential check, destructive-action confirmation) and feedback loops (DMS test-connection polling, CloudWatch lag monitoring before cutover). Not a 5 because detailed per-workflow validation/rollback loops live in the references rather than the body, leaving minor gaps.

4 / 5

Progressive Disclosure

Clear overview with a Decision Guide table mapping user requests to well-signaled, one-level-deep references; all referenced paths (references/*.md, scripts/wa_review.py) exist and are appropriately split from the body, making navigation easy.

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.

An exemplary description: third-person, comprehensive in named capabilities, with an explicit when-to-retrieve clause and a broad natural-language trigger list. Every token earns its place; no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions with comprehensive coverage: 'serverless-on-8.0 cluster setup, TLS/VPC/driver config, flexible-schema and vector-search data modeling, MongoDB compatibility assessment, DMS-based migration, slow-query diagnosis, major version upgrades (4.0->5.0->8.0), Well-Architected reviews (41-check wa_review.py), cost estimation, and security hardening.'

5 / 5

Completeness

Explicitly answers both what (the enumerated capability list) and when ('Retrieve for every DocumentDB question and when the user asks to set up or migrate MongoDB to AWS') with concrete trigger phrases.

5 / 5

Trigger Term Quality

A dedicated 'Triggers:' list provides comprehensive natural-keyword coverage including synonyms, operators, and error phrases: 'JSON document store, document database, MongoDB on AWS, Lambda cannot connect, TLS handshake, VPC port 27017, $graphLookup, COLLSCAN, $vectorSearch, CDC cutover, RAG'.

5 / 5

Distinctiveness Conflict Risk

Clear DocumentDB-specific niche with distinct triggers ('DocumentDB is AWS's MongoDB-compatible managed database') and version/operator-specific terms, giving minimal overlap risk with sibling database skills.

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.