CtrlK
BlogDocsLog inGet started
Tessl Logo

coordinating-multi-space-devops-agent

Coordinate the AWS DevOps Agent across multiple AgentSpaces from one Claude Code session — route questions to the right space (prod vs staging vs knowledge), query several spaces in parallel and synthesize, or compare findings across accounts. Use whenever the user has more than one AgentSpace configured, mentions multiple AWS accounts, or asks something like "check both prod and staging", "compare across accounts", or "ask the knowledge space".

77

Quality

96%

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

92%

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

Highly actionable, concise routing guidance with clear sequenced workflows and explicit error/scope checkpoints. The main gap is progressive disclosure: the only external reference targets a walkthrough file that does not exist in the bundle.

Suggestions

Add the referenced examples/multi-space-walkthrough.md to an examples/ bundle (or remove the See also link) so the one-level-deep reference resolves to a real file.

If no bundle is intended, inline a brief worked example or drop the reference rather than pointing at a missing path.

DimensionReasoningScore

Conciseness

The body is lean and purposeful — decision table, named patterns A-D, concrete tool calls, and timeout/anti-pattern notes — with every section earning its place rather than explaining general concepts Claude already knows.

3 / 3

Actionability

Provides copy-paste-ready tool invocations with real names and parameters (e.g. aws_devops_agent__chat(message=..., agent_space_id=...)), a routing-table format, and templated message strings, fully executable rather than pseudocode.

3 / 3

Workflow Clarity

Discovery is a numbered sequence and each pattern has explicit checkpoints: verify scope before fanning out, surface a 90s timeout and skip, and ask the user once when routing is ambiguous rather than guessing.

3 / 3

Progressive Disclosure

Sections are well organized and the 'See also' reference is one level deep and clearly signaled, but it points to examples/multi-space-walkthrough.md which is not present in any bundle directory, so the externalized reference is a broken/dangling path.

2 / 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, surfaces natural trigger phrases, and explicitly covers both the what and when. No first/second-person voice issues.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'route questions to the right space', 'query several spaces in parallel and synthesize', 'compare findings across accounts' — matching the anchor for several specific concrete actions.

3 / 3

Completeness

Clearly states what it does (route, parallel query, synthesize, compare) and when to use it via an explicit 'Use whenever...' clause with concrete triggers, satisfying both what and when.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered: 'more than one AgentSpace configured', 'multiple AWS accounts', and quoted phrases like "check both prod and staging" and "ask the knowledge space" that a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The multi-AgentSpace routing niche is distinct from single-space skills and its triggers (multiple accounts, prod-vs-staging) are unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.