CtrlK
BlogDocsLog inGet started
Tessl Logo

resilience-program-design

Designs a resilience program: how to structure and standardize resilience policies across an organization, team, or portfolio (tiered policy model with availability/RTO/RPO targets and DR approach selection), and how often to run resilience activities (operational cadence). Applies when the user asks how to structure policies org-wide, what tiers/targets to set, which DR approach fits a tier, or how frequently to run assessments, FIS experiments, GameDays, or autoshift practice. Does not apply to creating or configuring a specific policy or resource for a single workload (use resilience-hub-getting-started), to step-by-step lifecycle execution (see aws-resilience-lifecycle), or to service-specific setup.

70

Quality

86%

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

72%

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

A tightly organized, actionable planning skill that names specific AWS primitives and cadences rather than hand-waving. Its main weaknesses are mild redundancy in the API-verification caveats and the absence of an explicit pre-recommendation validation checklist for the advisory flow.

Suggestions

Consolidate the three repeated 'verify the valid values/set via the API/docs' caveats into a single up-front note so the same instruction isn't restated in the SLO bullet, DR bullet, and illustrative example.

Add a short pre-recommendation checklist for the policy-structuring flow — e.g. '1) confirm SLO and DR-approach enum values against the API, 2) verify each tier's SLO/DR combo is non-contradictory (no max SLO with BACKUP_AND_RESTORE)' — to give the advisory workflow an explicit validation checkpoint.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no 'what is a resilience program' preamble) and is lean, but the 'verify the valid set via the API/docs' caveat is repeated three times (SLO bullet, DR bullet, and the illustrative example) and could be consolidated into one statement.

2 / 3

Actionability

Concrete, executable guidance throughout: a fixed minimum cadence (weekly/monthly/quarterly/event-driven), specific AWS condition keys ('aws:SourceArn'/'aws:SourceAccount', 'aws:SecureTransport'), SSE-KMS, and an IAM-roles-not-users mandate — actionable without code.

3 / 3

Workflow Clarity

The two-task structure (structuring policies, cadence) is clearly laid out with a 'Warn against contradictory policies' guardrail, but there is no explicit sequenced validation/checkpoint step for the advisory flow (e.g. a 'before recommending: confirm enum values, then check the SLO/DR combo is non-contradictory' checklist).

2 / 3

Progressive Disclosure

The body is under 50 lines, needs no external references, and is organized into well-signaled sections (Overview, Structuring policies, Cadence, Security Considerations), satisfying the simple-skill anchor for a top score with no bundles.

3 / 3

Total

10

/

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 high-quality, third-person description that states concrete capabilities, provides explicit activation triggers, and actively disambiguates itself from neighboring resilience skills via a 'Does not apply to' clause. It hits every anchor at the top level with no fluff or over-claims.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'structure and standardize resilience policies', 'tiered policy model with availability/RTO/RPO targets and DR approach selection', and 'operational cadence' — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (designs a resilience program: structuring policies + cadence) and when ('Applies when the user asks...'), and adds 'Does not apply to...' exclusion guidance.

3 / 3

Trigger Term Quality

Natural phrasing a user would actually say is well covered: 'how to structure policies org-wide', 'what tiers/targets to set', 'which DR approach fits a tier', 'how frequently to run assessments, FIS experiments, GameDays, or autoshift practice'.

3 / 3

Distinctiveness Conflict Risk

A clear niche (program-level resilience policy design) reinforced by explicit negative-scope routing to 'resilience-hub-getting-started', 'aws-resilience-lifecycle', and service-specific setup, making mis-activation unlikely.

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.