Tessl • The management layer for AI agent skills

SkillPublic

eks-irsa

IAM Roles for Service Accounts (IRSA) for EKS pod-level AWS permissions. Use when configuring pod IAM access, setting up AWS service integrations, implementing least-privilege security, troubleshooting OIDC trust relationships, or deploying AWS controllers.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

67%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 highly actionable, comprehensive IRSA guide with excellent executable examples, clear verification steps, and a well-structured reference layer. Its main weakness is verbosity: padding (benefits lists, keyword lines, repeated metadata, redundant SDK examples) and inlined detail that belongs in the reference files inflate the token cost without adding capability.

Suggestions

Remove the 'Key Benefits' (Security/Compliance/Operational) section, the 'Keywords' line, and the duplicated Status/Version metadata at the top and bottom of the file — none of it adds capability Claude does not already have.

Collapse the three per-language SDK examples into a single line ('AWS SDKs v3/v2 and boto3 detect IRSA credentials automatically; no configuration needed') and keep at most one short code example.

Move the seven controller pattern HCL blocks and the blue/green upgrade section into references/role-creation.md and references/oidc-setup.md, keeping only the module name and relevant attach flag inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose across several padded sections: the 'Key Benefits' (Security/Compliance/Operational) bullets, a 'Keywords' line, status/version metadata repeated three times ('Production-ready (2025 best practices)', 'Last Updated: November 2025'), and three per-language SDK examples that each restate 'AWS SDK automatically detects IRSA credentials'. Time-sensitive version/date information appears inline rather than in a deprecated/old-patterns section.	2 / 5
Actionability	Fully executable throughout: complete Terraform for the quick start and seven controller patterns, eksctl commands, verification commands with expected output ('Should show: AWS_WEB_IDENTITY_TOKEN_FILE=...'), a concrete issue/cause/fix troubleshooting table, and copy-paste IAM policy JSON. Only trivial gaps exist (the Go example omits the fmt import).	5 / 5
Workflow Clarity	The sequence (enable IRSA -> create role -> annotate ServiceAccount -> use in pod) is clear and the 'Verify IRSA Setup' section provides explicit validation with expected outputs, backed by a troubleshooting table for error recovery. Not a 5 because the steps, validation, and recovery guidance are scattered across sections rather than consolidated into one workflow with an explicit 'if verification fails' loop.	4 / 5
Progressive Disclosure	Three real, one-level-deep reference files are clearly signaled in 'Detailed Documentation' with per-file content summaries, and all three exist in references/. Not a 5 because roughly 200 lines of controller pattern HCL, blue/green upgrade, and per-language SDK examples are inlined in a 550-line SKILL.md when the reference files exist to hold that detail.	4 / 5
	Total	15 / 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.

A well-constructed description that clearly states what the skill covers and when to use it, with concrete action verbs, strong natural trigger terms, and a distinct niche. It closely follows the structure of the rubric's good examples with no fluff or over-claiming.

Dimension	Reasoning	Score
Specificity	The trigger clause enumerates multiple concrete actions — 'configuring pod IAM access', 'setting up AWS service integrations', 'implementing least-privilege security', 'troubleshooting OIDC trust relationships', 'deploying AWS controllers' — comprehensively covering the skill's scope. Not a 4 because coverage is comprehensive rather than having minor gaps.	5 / 5
Completeness	Explicitly answers both: the 'what' ('IAM Roles for Service Accounts (IRSA) for EKS pod-level AWS permissions') and a concrete 'Use when...' clause with five trigger phrases, matching the anchor-5 pattern. Not a 4 because the 'when' is fully explicit with concrete triggers, not merely present.	5 / 5
Trigger Term Quality	Good natural keyword coverage: 'IRSA', 'pod IAM access', 'least-privilege security', 'OIDC trust relationships', 'EKS'. Not a 5 because common variations such as 'service account annotation', 'EKS add-ons', or 'pod identity' are missing.	4 / 5
Distinctiveness Conflict Risk	Firmly pinned to the EKS/IRSA niche — a user mentioning these triggers is unambiguously asking for this skill, not a general IAM or Terraform skill. 'AWS service integrations' is slightly broad but anchored by the IRSA/EKS framing. Not a 4 because no closely related skill would realistically capture these triggers.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (556 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/eks-irsa/SKILL.md
Revision: 93ed392

Reviewed: 11 days ago

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.

eks-irsa

Table of Contents

Is this your skill?