Reviews agent skill definitions for token efficiency, clarity, and standardized formatting.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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. Frontmatter
- **Discovery**: A harness loads `name` and `description` at session start and the body only once the description matches the request, so the description is what decides whether the skill is ever read. Require it to open with the action the user asks for and to name the thing acted on; flag one that describes the skill to a reader who already found it (`Discovers and removes provisioned kube-agents GCP/GKE infrastructure` never says "uninstall").
- **Loadability**: Require frontmatter a YAML parser accepts. Flag an unquoted `: ` in a description, and a value opening with `{`, `[`, `*` or `&`.
## 2. 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.
## 3. Prose & Verbosity
…
The line at the top of this page pins the label git:20260924.e118413, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_7x5t4ethszb4lzq5
GET https://markdownregistry.com/api/v1/resolve?ref=gke-labs/kube-agents/skill-review
GET https://markdownregistry.com/api/v1/blob/b277de477ac9de3c5ee7ddf2af11b8fae3ce514d3b494d17990672d8badc4800
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
gke-labs/kube-agents · .agents/skills/edit-mirrored-skill/SKILL.md · Edit, sync or start mirroring a `gke-*` skill in `agents/platform/skills/` that is copied from google/skills. Use when…
gke-labs/kube-agents · .agents/skills/install-kube-agents/SKILL.md · Install, set up, or deploy kube-agents (the Kubernetes Agentic Harness) and its Platform Agent onto a GKE cluster in a…
gke-labs/kube-agents · .agents/skills/review-address-feedback/SKILL.md · Address review feedback on an open pull request: triage and fix findings, reply in every thread, resolve the addressed…
gke-labs/kube-agents · .agents/skills/review-adversarial/SKILL.md · Reviews a change adversarially — establishes what it claims to do, hunts candidates from eleven angles, then re-derives…
gke-labs/kube-agents · .agents/skills/review-docs-drift/SKILL.md · Reviews a pull request for documentation drift — finds which docs the change should have updated, verifies doc claims…
gke-labs/kube-agents · .agents/skills/review-preflight/SKILL.md · Runs the review passes required before a pull request is opened — adversarial and docs-drift — each in a context that…
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-credentials/SKILL.md · Reviews AI agent Kubernetes configurations for credentials exposed to agents.
gke-labs/kube-agents · .agents/skills/review-security-k8s-agents-data-exfil/SKILL.md · Reviews Kubernetes configurations to prevent data exfiltration by AI agents.
techygarg/lattice · dev-skills/skill-review/SKILL.md · Deep behavioral audit of a Lattice skill — proposes 3 review personas relevant to the skill, runs independent scenario…
uipath/skills · .cursor/rules/skill-review.mdc · Strict skill audit/review framework — use when user asks to review, audit, grade, or compare skills, or when reviewing…
runxhq/runx · skills/skill-review/SKILL.md · Inspect, safely test, and assess one Runx skill package for capability, trust, and operator readiness. Use when…
hiroro-work/claude-plugins · .claude/skills/skill-review/SKILL.md · Review uncommitted skill changes against an internal checklist of skill-creator best practices and apply improvements…
coupler-io/skills · .agents/skills/skill-review/SKILL.md · Use this skill when reviewing a Coupler.io skill before merge, auditing an existing one, or checking a pack of skills…
stacklok/toolhive-catalog · .claude/skills/skill-review/SKILL.md · Review skill submissions and updates for compliance, security, and quality. Use when evaluating skill.json files…
ivy00johns/skill-madness · skills/meta/skill-review/SKILL.md · Audit and review skills for quality, consistency, and triggering accuracy — including skills that under-trigger or…
mindbox-cloud/agent-skills · plugins/skill-review/skills/skill-review/SKILL.md · Quick and accessible AI reviewer for Agent Skills — for non-specialists. Checks structure, workflow, references, and…
