linkerd-patterns

Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.

1.15x

Quality

85%

Does it follow best practices?

Impact

96%

1.15x

Average score across 6 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%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 high-quality, action-oriented reference skill with comprehensive executable templates and clear sectioning. Its main gaps are minor: a little introductory fluff and inline template blocks that could be progressively disclosed into separate reference files.

Suggestions

Trim the marketing-style intro line ('the lightweight, security-first service mesh for Kubernetes') since it restates the description, and consider whether the ASCII architecture diagram earns its tokens.

Add brief inline feedback loops after validation steps (e.g., 'if linkerd check fails, inspect errors and re-run before proceeding') rather than relying on the Best Practices section.

Consider moving the larger YAML templates (ServiceProfile, ServerAuthorization, HTTPRoute) into a references/ file with one-line pointers, keeping SKILL.md as a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and code-driven with no lengthy concept explanations, but the marketing-style intro ('the lightweight, security-first service mesh for Kubernetes') and the ASCII architecture diagram add minor padding that could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready bash and YAML templates spanning installation, injection, ServiceProfiles, TrafficSplit, authorization policy, HTTPRoute, multi-cluster, monitoring, and debugging, covering the common cases comprehensively.	5 / 5
Workflow Clarity	Installation and multi-cluster templates present clear sequenced steps with explicit validation checkpoints ('linkerd check --pre', 'linkerd check'), but error-recovery feedback loops (what to fix when a check fails) are only hinted at via best practices rather than stated inline.	4 / 5
Progressive Disclosure	Content is organized into clear, well-labeled sections (When to Use, Core Concepts, Templates, Monitoring, Debugging, Best Practices) with no bundle files to navigate, but the large inline YAML templates could justify splitting into reference files for a single-file skill of this length.	4 / 5
	Total	17 / 20 Passed

Description

87%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-crafted description that explicitly states both capability and trigger conditions with concrete, product-specific language. It is concise without padding and distinguishes the skill clearly.

Dimension	Reasoning	Score
Specificity	Names the Linkerd domain and several concrete actions ('setting up Linkerd, configuring traffic policies, or implementing zero-trust networking'), but omits capabilities the body covers like retries, traffic splits, and multi-cluster, so it stops short of comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' (implement Linkerd service mesh patterns) and 'when' via a 'Use when...' clause with concrete trigger phrases, matching the anchor for clear what-and-when coverage.	5 / 5
Trigger Term Quality	Includes strong natural terms users would say ('Linkerd', 'service mesh', 'traffic policies', 'zero-trust networking'), but misses common variations such as 'mTLS', 'canary', 'traffic splits', and 'Kubernetes'.	4 / 5
Distinctiveness Conflict Risk	The Linkerd-specific niche with distinct product-level triggers ('Linkerd', 'zero-trust networking with minimal overhead') makes it clearly distinguishable from generic or Istio-based mesh skills with minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wshobson/agents
Path: plugins/cloud-infrastructure/skills/linkerd-patterns/SKILL.md
Commit: d6837ae

Reviewed: about 12 hours ago

Table of Contents

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.