CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ack-resources

AWS Controllers for Kubernetes (ACK) for Kubernetes-native AWS resource management. Use when managing AWS resources via kubectl, implementing GitOps for infrastructure, creating self-service developer platforms, integrating AWS services with EKS workloads, or adopting existing AWS resources into Kubernetes.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/ack-resources/SKILL.md

The canonical home for this skill is ack-resources in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

Highly actionable, well-sequenced content with real verification and troubleshooting feedback loops, backed by substantive one-level-deep references. Its weakness is conciseness: the file carries encyclopedic comparison/summary material and time-sensitive details that inflate tokens without adding guidance Claude cannot derive itself.

Suggestions

Trim the Overview 'Key Characteristics' bullets, the three 'ACK vs Alternatives' tables, and the closing Summary (which restates the intro) down to the single selective-adoption recommendation, moving full comparisons into a reference file.

Move the 16-row Supported Services table into a reference and keep only a count plus pointer; and confine version/time-sensitive details like '2025' and helm '--version=v0.1.7' to a clearly-labeled versioned section or the setup reference.

Add an explicit validation checkpoint after resource creation — e.g., wait for the ACK.ResourceSynced condition before cross-referencing the resource or consuming a FieldExport — to close the workflow gap between create and reference/export.

DimensionReasoningScore

Conciseness

The bulk is dense executable YAML/bash, but several sections add little beyond what Claude already knows: the Overview/Key Characteristics bullets, three 'ACK vs alternatives' comparison tables, a 16-row GA service table that duplicates the references, a closing Summary repeating the intro, and time-sensitive details ('Supported AWS Services (2025)', helm '--version=v0.1.7') placed outside any old-patterns/deprecation section. Mostly efficient but needs tightening — anchor 3, not 4, given the volume of removable material.

3 / 5

Actionability

Guidance is fully executable and copy-paste ready: complete eksctl/helm/aws/kubectl command sequences, full manifests for S3 Bucket, RDS DBInstance, SQS Queue, API Gateway references, FieldExport, AdoptedResource, ArgoCD/Flux, and CARM, plus exact annotations, status conditions, and troubleshooting commands. Specific examples cover the common cases — anchor 5.

5 / 5

Workflow Clarity

Clear routed sequence ('Understand Your Objective' branching to numbered sections), a 5-step install ending in an explicit verify step ('kubectl get pods', 'kubectl get crds'), status-check commands after resource creation, and a Troubleshooting section with error-recovery flows for pending, drift, and cross-account failures. The gap keeping it from anchor 5: no explicit checkpoint for waiting on ACK.ResourceSynced before cross-referencing or FieldExporting a newly created resource.

4 / 5

Progressive Disclosure

Three real, substantial references (controller-setup.md, resource-definitions.md, gitops-patterns.md) are clearly signaled both inline ('See reference:') and in the Next Steps section with content lists, and cross-links are one level deep (sibling files only). However, an ~870-line SKILL.md inlines material that belongs in references — the full 16-row service table, the three comparison tables, and the Common Patterns section — so structure is good but not the clean overview/content split of anchor 5.

4 / 5

Total

16

/

20

Passed

Description

75%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.

A strong description with a clear niche, natural trigger vocabulary, and an explicit, well-branched 'Use when' clause. Its main weakness is an abstract what-clause that relies on the trigger list to convey concrete capabilities.

DimensionReasoningScore

Specificity

Concrete actions are named ('managing AWS resources via kubectl', 'adopting existing AWS resources into Kubernetes', 'implementing GitOps for infrastructure'), but the core what-clause 'Kubernetes-native AWS resource management' is abstract and omits create/update/delete, CRD, and controller verbs. Matches anchor 4 (several specific actions, minor gaps) rather than 5 (comprehensive) or 3 (only 1-2 actions).

4 / 5

Completeness

Both what and when are present, with an explicit 'Use when...' clause enumerating five concrete triggers (kubectl management, GitOps, self-service platforms, EKS integration, adoption). Falls short of anchor 5 because the what-side ('Kubernetes-native AWS resource management') is a domain label rather than an explicit capability list as in the anchor-5 exemplar.

4 / 5

Trigger Term Quality

Natural trigger terms users would actually say are present: 'kubectl', 'EKS', 'GitOps', 'ACK', 'AWS resources', 'AWS Controllers for Kubernetes'. A few natural terms/synonyms are missing ('infrastructure as code', 'CRDs', 'Crossplane alternative', 'operator pattern'), which fits anchor 4 rather than the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The ACK/EKS/kubectl framing carves a clear niche with distinct triggers, but broader phrases like 'implementing GitOps for infrastructure' and 'creating self-service developer platforms' could also fire for Crossplane or generic platform-engineering skills. Mostly distinct with minor overlap risk — anchor 4, not the minimal-conflict anchor 5.

4 / 5

Total

16

/

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

skill_md_line_count

SKILL.md is long (873 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

.claude/skills/ack-resources/SKILL.md

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.