CtrlK
BlogDocsLog inGet started
Tessl Logo

recovery-controller-setup

Configures AWS Application Recovery Controller (ARC) for operational resilience: routing controls with safety rules for cross-Region failover, and zonal shift / zonal autoshift for AZ-impairment recovery. Applies when setting up failover routing, configuring safety rules, enabling zonal shift, or configuring zonal autoshift with practice runs. Also applies when shifting traffic out of a specific Availability Zone (AZ) for an ALB/NLB or other resource. For a broader "an AZ is impaired, what is my response across services" question, see aws-resilience-lifecycle. Does not apply to Resilience Hub setup or FIS experiments.

67

Quality

81%

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

71%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-structured index-style skill: clean overview, real one-level-deep references, effective boundary enforcement, and no wasted tokens on known concepts. Its main weakness is that the body is a pure router — every executable command and step sequence is deferred to references/arc-procedures.md, leaving the body itself without concrete inline guidance.

Suggestions

Inline a minimal quick-start (e.g., the 2-3 core CLI commands for creating a routing control, adding a safety rule, and flipping a control state) so the body is actionable before the reference is opened.

Add a short outline of the 6-step procedure (verify dependencies → create controls → safety rules → test failover → optional zonal shift → recommended zonal autoshift) in the body so the sequence and validation checkpoint are visible at a glance.

Tighten the CRITICAL CONSTRAINT section — the scope exclusion and the redirect template are each stated twice; one statement plus the template would cut ~8 lines without losing enforcement clarity.

DimensionReasoningScore

Conciseness

Efficient and assumes competence — no explanations of concepts Claude already knows, and the MCP-vs-local guardrail is operationally necessary, not padding. Not 5 because the CRITICAL CONSTRAINT section states the scope rule and the redirect template twice each ("Readiness checks... are NOT in scope... You MUST NOT..." then the same as an if-then with a quoted template).

4 / 5

Actionability

The body's guidance is direction, not instruction: "To set up ARC routing controls and zonal shift, follow the procedure exactly. See references/arc-procedures.md" — all concrete CLI commands live one level deep in the reference file, and the body contains no inline code, commands, or step summaries. Not 2 because the delegation is specific and unambiguous (exact file paths, exact redirect wording, exact troubleshooting topics).

3 / 5

Workflow Clarity

The multi-step procedure is sequenced with a "Test Failover" checkpoint and a Troubleshooting section in references/arc-procedures.md, and the body's delegation to it is unambiguous; routing-control failover validation is present, so the destructive-operation cap does not apply. Not 5 because the body itself enumerates no steps or checkpoints — the reader must open the reference to learn the sequence exists.

4 / 5

Progressive Disclosure

The body is a concise overview with clearly signaled, one-level-deep references that both exist in the bundle: "See [references/arc-procedures.md](references/arc-procedures.md)" (with its Troubleshooting section) and "See [references/security-considerations.md](references/security-considerations.md) for least-privilege IAM action scoping...". No content that belongs in a reference is inlined, and navigation is easy. Scored against the actual bundle structure per the rubric's bundle guideline.

5 / 5

Total

16

/

20

Passed

Description

92%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.

Excellent description: third-person voice, concrete capabilities, explicit 'Applies when...' triggers, and explicit boundary routing to adjacent skills. The only weakness is minor — a few natural synonym phrasings (e.g., 'Route 53 ARC', 'drain traffic from an AZ') are not covered.

DimensionReasoningScore

Specificity

Names the domain ("AWS Application Recovery Controller (ARC)") and multiple concrete capabilities — "routing controls with safety rules for cross-Region failover", "zonal shift / zonal autoshift", "practice runs" — covering both capability families comprehensively. Not below 4 because coverage of the skill's stated scope has no gaps; not below 5 because there are no minor missing actions within that scope.

5 / 5

Completeness

Explicitly answers both: what — "Configures AWS Application Recovery Controller (ARC)... routing controls with safety rules... zonal shift / zonal autoshift"; when — "Applies when setting up failover routing, configuring safety rules, enabling zonal shift... Also applies when shifting traffic out of a specific Availability Zone". Clear trigger phrases plus explicit non-goals ("Does not apply to Resilience Hub setup or FIS experiments").

5 / 5

Trigger Term Quality

Strong natural phrasing users would actually say: "setting up failover routing", "configuring safety rules", "enabling zonal shift", "shifting traffic out of a specific Availability Zone (AZ) for an ALB/NLB". Falls short of 5 because a few natural synonyms are absent (e.g., "Route 53 ARC", "drain an AZ"), though domain coverage is otherwise good.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers and explicit disambiguation from neighbors: "For a broader 'an AZ is impaired, what is my response across services' question, see aws-resilience-lifecycle" and "Does not apply to Resilience Hub setup or FIS experiments". Not 4 because it doesn't just minimize overlap — it actively names and routes away the adjacent skills.

5 / 5

Total

19

/

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.

Validation — 15 / 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.