CtrlK
BlogDocsLog inGet started
Tessl Logo

rds-oss

Advises on Amazon RDS open-source engines (MySQL, MariaDB, PostgreSQL) for instance creation, upgrade planning, commitment pricing, proxy evaluation, and Blue/Green deployments. Handles any RDS MySQL, MariaDB, or PostgreSQL question, including create a production-ready RDS MySQL instance, provision an RDS PostgreSQL database, run the RDS upgrade advisor for my RDS MySQL instance, what are my upgrade options, upgrade RDS MariaDB from 10.6 to the latest version, should I buy reserved instances or a savings plan for db.r7g.2xlarge RDS MySQL, change a VARCHAR to INT column on RDS MySQL 8.0 with Blue/Green, and does RDS Proxy help when PgBouncer already runs in transaction mode. Covers instance creation with production best practices, describe-db-instances and describe-db-engine-versions upgrade-target workflow, live prechecks via SSM or direct connection, RI versus DSP commitment pricing, RDS Proxy versus PgBouncer, and Blue/Green lifecycle with binlog replay compatibility.

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 highly actionable, well-structured advisory skill body with executable CLI commands, clear routing, numbered workflows, checklists, and a clean one-level reference structure. The main weakness is conciseness — repeated safety refrains and an inline Critical Facts section that mirrors the reference workflows add length that could be tightened without losing value.

Suggestions

Deduplicate the 'advisory-only / never execute without explicit confirmation' refrain — it appears in the Overview, Common Tasks constraints, Critical Facts (pricing fact 7), and Security Considerations; state it once authoritatively and back-reference it from the other locations.

Tighten 'Critical Facts to Always Surface' into terse forcing-function bullets that link to the relevant reference for full detail, instead of restating the upgrade/MariaDB/pricing/Blue-Green/Proxy fact lists inline where they duplicate the workflow references.

Trim the obvious rationale in Production Instance Creation's 13 best-practice bullets (e.g., 'It's cheaper and faster than gp2 with no minimum IOPS purchase') while retaining the exact flag guidance, to reduce length without losing actionability.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no basic-concept explanations) and is dense with RDS-specific facts, but it restates the 'advisory-only / never execute without confirmation' refrain in the Overview, Common Tasks, Critical Facts, and Security sections, and the long inline 'Critical Facts to Always Surface' duplicates content already in the reference workflows. Fits 'mostly efficient but could be tightened' rather than 'every token earns its place'.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands — the complete `aws rds create-db-instance` block with all production flags, `describe-db-engine-versions --query ...`, and the exact script invocation `rds_commitment_pricing_analyzer.py --instance-type db.r7g.2xlarge --engine mysql --num-instances 2`, plus specific parameters such as `require_secure_transport=ON` and `binlog_format=ROW`. Matches the score-3 anchor; not score 2 (no pseudocode or missing key details).

3 / 3

Workflow Clarity

Clear routing via the Decision Guide table and a numbered Common Tasks sequence (Verify Dependencies → Classify and Route → Execute), with workflows exposing `## Tasks` steps, pre/post checklists, and explicit confirmation gates for destructive ops ('MUST pause and ask the user for explicit confirmation before presenting the switchover-blue-green-deployment command'). Validation and feedback loops are present, so the destructive-ops cap does not apply.

3 / 3

Progressive Disclosure

SKILL.md is an overview that points via a Decision Guide table to one-level-deep references (upgrade-workflow.md, commitment-pricing-workflow.md, proxy-advisor-workflow.md, bluegreen-advisor-workflow.md, verify-dependencies.md); all referenced files exist and the engine-specific sub-references they delegate to are leaf content with no further indirection. Well-signaled navigation and an appropriate content split match the score-3 anchor.

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 strong, third-person description that names concrete capabilities, embeds natural trigger phrasings across all five skill areas, and scopes clearly to RDS open-source engines. It is somewhat verbose — the trailing 'Covers...' clause and eight inline example queries could be tightened — but every dimensional anchor is met at the top level, so no dimension is docked.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'instance creation, upgrade planning, commitment pricing, proxy evaluation, and Blue/Green deployments' — plus specific tooling such as 'describe-db-instances and describe-db-engine-versions' and 'live prechecks via SSM or direct connection'. Matches the score-3 anchor (multiple specific concrete actions), not score 2 (which would name the domain but only some actions).

3 / 3

Completeness

States the what ('Advises on Amazon RDS open-source engines ... for [five areas]') and supplies equivalent explicit trigger guidance via 'Handles any RDS MySQL, MariaDB, or PostgreSQL question, including [eight example triggers]'. Satisfies the score-3 anchor for both what and when; the 'Use when' cap does not apply because explicit triggers are present, so it is not score 2.

3 / 3

Trigger Term Quality

Embeds verbatim user-style queries such as 'run the RDS upgrade advisor for my RDS MySQL instance', 'should I buy reserved instances or a savings plan for db.r7g.2xlarge RDS MySQL', and 'does RDS Proxy help when PgBouncer already runs in transaction mode' — strong natural-term coverage across all five areas. Meets the score-3 anchor, not score 2 (which expects missing common variations).

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to 'Amazon RDS open-source engines (MySQL, MariaDB, PostgreSQL)' with RDS-specific triggers (RI vs DSP, Blue/Green, RDS Proxy vs PgBouncer), giving a clear niche unlikely to conflict with generic database or Aurora skills. Meets the score-3 anchor; not score 2 (which would still overlap with similar skills).

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.