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.

1.35x

Quality

85%

Does it follow best practices?

Impact

100%

1.35x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is linkerd-patterns in wshobson/agents

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, actionable patterns skill built around copy-paste-ready templates and commands with sensible validation checkpoints. Its main weaknesses are minor verbosity in the concept/intro sections and the absence of explicit error-recovery feedback loops.

Suggestions

Trim the ASCII architecture diagram and the 'When to Use This Skill' list (which duplicates the description) to tighten token efficiency.

Add explicit feedback loops for risky operations, e.g., 'if `linkerd check` fails, review errors and re-run before proceeding' and a canary-verification step after applying a TrafficSplit.

Dimension	Reasoning	Score
Conciseness	The body is largely lean, executable bash/YAML with little concept explanation, but includes minor padding such as the ASCII architecture diagram, the 'When to Use This Skill' list (which restates the description), and a marketing-style intro line.	4 / 5
Actionability	Templates 1-7 plus Monitoring and Debugging sections provide fully executable, copy-paste-ready commands and YAML covering the common Linkerd operations.	5 / 5
Workflow Clarity	Installation and multi-cluster templates are sequenced with validation checkpoints ('linkerd check --pre', 'linkerd check', 'linkerd multicluster check'), but explicit fix-and-revalidate feedback loops are not stated for failing checks or canary rollout verification.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized into clearly headed sections with external doc links signaled in Resources, and no bundle files exist to split; the inline template bulk is appropriate for a patterns skill, though some reference material (monitoring/debugging command catalog) could live in a separate file.	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 strong, well-formed description that clearly states capability and trigger conditions in third person. It is specific and distinctive; the only room for improvement is broader keyword coverage and listing a couple more concrete actions.

Suggestions

Add a few more natural trigger terms such as 'mTLS', 'canary deployments', or 'Kubernetes service mesh' to broaden keyword coverage.

Consider listing one or two additional concrete actions (e.g., service profiles, traffic splits) to close the coverage gaps relative to the body.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('setting up Linkerd, configuring traffic policies, or implementing zero-trust networking'), but omits capabilities the body covers such as canary traffic splits, service profiles, and multi-cluster, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both what ('Implement Linkerd service mesh patterns...') and when ('Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('Linkerd', 'service mesh', 'traffic policies', 'zero-trust networking') with good coverage, but lacks common synonyms like mTLS, canary, or 'Kubernetes service mesh'.	4 / 5
Distinctiveness Conflict Risk	Linkerd is a specific named product with a clear niche ('lightweight, security-focused service mesh') and distinct triggers, giving minimal conflict risk with other skills.	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: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-wshobson/cloud-infrastructure/skills/linkerd-patterns/SKILL.md
Commit: 6453c0b

Reviewed: about 9 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.