Review agent skill definitions (SKILL.md files) to enforce maximum token efficiency, eliminate conversational fluff, and ensure standardized formatting without losing functional fidelity.

Checks

1. Structure & Headers

Standardization: Require a top-level # Task section and # Checks (or # Workflow) section.
Header Conciseness: Flag overly verbose headers (e.g., ## Focus Areas & Deterministic Checks). Require terse headers.

2. Prose & Verbosity

Persona Elimination: Flag conversational AI persona setups (e.g., "You are an expert..."). Replace with imperative tasks.
Conversational Fluff: Flag transitional phrases, unnecessary adverbs, and filler words.
Imperative Voice: Require bullet points to start with strong, punchy verbs (Flag..., Require..., Ensure...).

3. Formatting

Density: Ensure rules are condensed into terse, single-sentence commands where possible.
Fidelity: Ensure no deterministic rules, checks, or domain knowledge are lost during token optimization.

Más de este repositorio

mismo repositorio

github-issue-resolver

gke-labs/kube-agents

Autonomously poll, triage, investigate, and resolve unaddressed open issues on our target GitHub repository strictly within authorized scope.

2026-07-1536

gke-compute-classes

gke-labs/kube-agents

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto Provisioning configuration or general GKE cluster creation.

2026-07-1436

kube-agents-observability

gke-labs/kube-agents

Audit, monitor, and debug the logging, tracing, metrics, and API/dashboard observability of the Platform Agent.

2026-07-1436

gke-manifest-generation

gke-labs/kube-agents

Standard Operating Procedure (SOP) for generating and updating secure, compliant, and cost-effective GKE manifests.

2026-07-1036

gke-workload-troubleshooting

gke-labs/kube-agents

Systematic Standard Operating Procedure (SOP) for diagnosing GKE workload failures, crash loops, resource OOMs, mounting errors, and connectivity timeouts.

2026-07-1036

review-security-k8s-pod

gke-labs/kube-agents

Reviews Kubernetes Pod security contexts for workload-level isolation and privilege escalation risks.

2026-06-1636

name	skill-review
description	Reviews agent skill definitions for token efficiency, clarity, and standardized formatting.

Task

Review agent skill definitions (SKILL.md files) to enforce maximum token efficiency, eliminate conversational fluff, and ensure standardized formatting without losing functional fidelity.

Checks

1. Structure & Headers

Standardization: Require a top-level # Task section and # Checks (or # Workflow) section.
Header Conciseness: Flag overly verbose headers (e.g., ## Focus Areas & Deterministic Checks). Require terse headers.

2. Prose & Verbosity

Persona Elimination: Flag conversational AI persona setups (e.g., "You are an expert..."). Replace with imperative tasks.
Conversational Fluff: Flag transitional phrases, unnecessary adverbs, and filler words.
Imperative Voice: Require bullet points to start with strong, punchy verbs (Flag..., Require..., Ensure...).

3. Formatting

Density: Ensure rules are condensed into terse, single-sentence commands where possible.
Fidelity: Ensure no deterministic rules, checks, or domain knowledge are lost during token optimization.