CtrlK
BlogDocsLog inGet started
Tessl Logo

nitinjain999/platform-skills

Production-grade platform engineering handbook — Kubernetes, Terraform, Flux CD, GitHub Actions, AWS, and more.

77

Quality

97%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

Quality

Content

100%

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

The body is an exemplar of lean, actionable platform guidance: terse rules, executable commands, sequenced validation workflows, and a clean one-level reference table whose entries all resolve to real files. Minor note: the body mentions an examples/fluxcd/ path that does not exist in the bundle, but this does not materially undermine the strong structure.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — rules and tool-selection tables are terse with no padding or explanation of concepts Claude already knows; every line is directive ('Prefer OIDC...', 'Do not skip layers').

3 / 3

Actionability

Provides concrete, executable commands and sequences — 'terraform fmt -check -recursive', 'conftest test', 'ss -tulnp', 'ping', 'nc -zv', 'curl -v', 'helm lint --strict', 'kubeconform -strict -summary' — copy-paste ready with specific flags.

3 / 3

Workflow Clarity

Multi-step processes are explicitly sequenced with validation checkpoints and ordering gates, e.g. the Terraform chain ('fmt → validate → conftest → tflint → security scan → plan') and the Linux/networking layered escalation, both with explicit 'do not skip' / blocking-gate language.

3 / 3

Progressive Disclosure

Clear overview body with a well-signaled one-level-deep reference table ('Pick the Right Reference Files' mapping each file to its scope); all listed reference files exist in references/, and the body routes to them rather than inlining detail.

3 / 3

Total

12

/

12

Passed

Description

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is highly specific and complete, with strong natural trigger terms and explicit what/when guidance. Its only weakness is breadth — covering so many tools raises conflict risk with more focused single-domain skills.

Suggestions

Narrow the trigger scope or add a qualifier that distinguishes this skill from individual single-tool skills (e.g., 'when the task spans multiple of these layers') to reduce conflict risk.

The tool list is long; consider moving the exhaustive enumeration into the body and keeping the description focused on the cross-cutting diagnosis workflow.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'structured diagnosis with blast radius, validation steps, and rollback plan' — and enumerates specific domains and tools (Cosign, SBOM, SLSA, OIDC, SHA pinning, DORA metrics), matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers what ('Provides structured diagnosis with blast radius, validation steps, and rollback plan for: ...') and when ('Use when troubleshooting, implementing, reviewing, or auditing platform infrastructure'), satisfying the explicit-trigger 'what AND when' anchor.

3 / 3

Trigger Term Quality

Covers natural user terms across the stack — 'troubleshooting, implementing, reviewing, or auditing platform infrastructure', 'Kubernetes', 'Flux CD', 'Argo CD', 'Terraform', 'GitHub Actions', 'PR review' — strong coverage of phrases users would actually say.

3 / 3

Distinctiveness Conflict Risk

The niche is distinct (platform infrastructure intersection) but the description spans a very broad toolset (Kubernetes, GitOps, CI/CD, AWS, Azure, observability, compliance), so it could overlap with narrower single-domain skills; it is 'somewhat specific but could still overlap'.

2 / 3

Total

11

/

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.

Reviewed

Table of Contents