amazon-keyspaces

Provides authoritative compatibility checks, pricing estimates, connection troubleshooting, pre-warming guidance, and infrastructure mutations for Amazon Keyspaces (for Apache Cassandra). Covers LWT/batch operations, secondary indexes, materialized views, capacity modes, TTL, PITR, CDC, auto-scaling, multi-region keyspaces, UDTs, nodetool diagnostics parsing, SQL-to-Cassandra migration, and Cassandra-to-Keyspaces migration scenarios. Agents frequently produce incomplete or incorrect answers about Keyspaces feature support without this skill loaded.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

Highly actionable, well-sequenced content with strong progressive disclosure and a real, well-organized bundle. Its main weakness is verbosity from repeated JSON output shapes and worked examples that could be consolidated or pushed into reference files.

Suggestions

Show the full JSON output shape once (in the Script execution model section) and reference it from each mode instead of repeating it in Mode 1 and the worked example, to reduce token redundancy.

Move the large inline compatibility worked example and the verbose IAM permission lists into the relevant reference files (e.g., mode-2-cassandra-diagnostics.md, a dedicated IAM/auto-scaling reference), keeping the main body a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational and assumes competence (no padding explaining what Cassandra is), but it is ~400 lines with redundancy — the full JSON output shape is repeated in the Script execution model, Mode 1, and the worked example, and the correct/incorrect pattern section restates concepts — so it could be tightened.	2 / 3
Actionability	Provides fully executable AWS CLI and `npx ts-node` commands with resolved flags, exact JSON output shapes, IAM permission scopes, and worked examples; matches the 'copy-paste ready' anchor.	3 / 3
Workflow Clarity	The four-step mandatory response pattern sequences each mode, with explicit validation checkpoints (region validation against regions.json, dependency verification, compatibility parsing rules before emitting output) and confirmation gates before destructive operations, plus a troubleshooting section for error recovery.	3 / 3
Progressive Disclosure	Clear overview sections with well-signaled one-level-deep references ('Load [mode-1-manual-inputs.md](references/mode-1-manual-inputs.md) for ...'); all 10 referenced reference files, 4 scripts, and 3 asset data files exist and are easy to navigate.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, third-person, well-scoped description with strong trigger-term coverage and clear distinctiveness. Its main weakness is the absence of an explicit 'Use when...' clause, which caps completeness.

Suggestions

Append an explicit trigger clause such as 'Use when estimating Amazon Keyspaces costs, checking Cassandra-to-Keyspaces compatibility, migrating SQL schemas, or troubleshooting Keyspaces connections.' to raise completeness to 3.

Consider dropping the meta-justification sentence ('Agents frequently produce incomplete or incorrect answers...') since it does not aid trigger discovery and adds tokens.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('compatibility checks, pricing estimates, connection troubleshooting, pre-warming guidance, and infrastructure mutations') plus a broad enumeration of feature areas, matching the 'lists multiple specific concrete actions' anchor; third-person voice ('Provides') is correct.	3 / 3
Completeness	The 'what' is detailed, but there is no explicit 'Use when...' trigger clause; the closing sentence about agents producing incomplete answers is a justification, not explicit trigger guidance, so completeness is capped at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Covers natural terms a user would say — 'Amazon Keyspaces', 'Apache Cassandra', 'nodetool diagnostics', 'SQL-to-Cassandra migration', 'pricing estimates' — with good breadth; not the level-2 single-keyword case.	3 / 3
Distinctiveness Conflict Risk	Amazon Keyspaces is a narrow, well-defined niche with distinct triggers, making conflict with other skills unlikely; matches the 'clear niche' anchor.	3 / 3
	Total	11 / 12 Passed

Validation

81%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 6 missing, 6 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: aws/agent-toolkit-for-aws
Path: skills/specialized-skills/database-skills/amazon-keyspaces/SKILL.md
Commit: 222ce56

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.