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

—

Does it follow best practices?

Impact

100%

1.35x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable catalog of Linkerd patterns with executable commands and complete manifests throughout. Its weaknesses are the absence of explicit error-recovery feedback loops in the installation workflows and a monolithic single-file structure with no progressive disclosure to separate reference files.

Suggestions

Add a brief feedback loop to the install template: after 'linkerd check', note what to inspect and fix if it fails (e.g., re-run 'linkerd check --proxy' and resolve reported failures before proceeding).

Move the larger per-resource manifests (ServiceProfile, TrafficSplit, Server/ServerAuthorization, HTTPRoute) into referenced files under references/ and keep SKILL.md as an overview with one-level-deep links.

Trim the ASCII architecture diagram and intro line, since the control-plane/data-plane split is already known to Claude.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable YAML/bash and reference tables, with no padded explanations of what a service mesh or mTLS is; the small conceptual bits (intro line, architecture diagram) are compact rather than verbose.	3 / 3
Actionability	Templates 1–7 plus Monitoring and Debugging sections are copy-paste-ready commands and complete manifests, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The install and multi-cluster templates include explicit validation checkpoints ('linkerd check --pre', 'linkerd check', 'linkerd multicluster check'), but no error-recovery feedback loops are described, and the skill is a pattern catalog rather than one guided multi-step workflow with recovery guidance.	2 / 3
Progressive Disclosure	Sections are clearly organized, but the skill is a single monolithic ~310-line file with no separate reference files or one-level-deep references; at this size, per-resource templates could be split out to keep SKILL.md a leaner overview.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description follows the high-quality pattern: a concrete capability statement plus an explicit 'Use when' trigger clause with specific, natural keywords. It clearly answers both what the skill does and when to invoke it, with a distinct Linkerd-specific niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'setting up Linkerd, configuring traffic policies, or implementing zero-trust networking' — matching the anchor for several specific actions rather than vague language.	3 / 3
Completeness	Clearly states what it does ('Implement Linkerd service mesh patterns...') and when to use it with an explicit 'Use when...' clause, satisfying both the what and the when.	3 / 3
Trigger Term Quality	Covers natural terms a user would say when needing this skill ('setting up Linkerd', 'configuring traffic policies', 'zero-trust networking', 'service mesh'), aligning with the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Targets a named, specific service mesh (Linkerd) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
Commit: abece4a

Reviewed: 4 days 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.