Task
SkillAI & modelsReviews agent skill definitions for token efficiency, clarity, and standardized formatting.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Task skill
What this skill tells your AI
The instructions your AI receives, as published by gke-labs/kube-agents in .agents/skills/skill-review/SKILL.md and read by ahel’s review.
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
# Tasksection 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.
Signals
- GitHub stars
- 54
- Forks
- 36
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
skill-review-gke-labs- Source
- github.com/gke-labs/kube-agents