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

—

Does it follow best practices?

Impact

96%

1.15x

Average score across 6 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.

The content is highly actionable and concise, with executable commands and complete manifests throughout. Its weaknesses are workflow clarity (verification steps lack explicit fix-and-retry feedback loops) and progressive disclosure (a long monolithic file with no external reference structure).

Suggestions

Add explicit error-recovery feedback loops after validation steps, e.g., after `linkerd check` add 'If checks fail, review output, resolve the listed issues, then re-run `linkerd check` before proceeding'.

Split the seven templates into one-level-deep reference files (e.g., references/installation.md, references/service-profiles.md, references/traffic-split.md) with a concise overview in SKILL.md pointing to them, improving progressive disclosure.

Add a brief sequencing/decision note for when to use each template (e.g., a 'Choosing a template' line under Templates) so the multi-step workflows are clearer for first-time users.

Dimension	Reasoning	Score
Conciseness	The body is lean and command/template-driven with no preamble explaining what a service mesh or Kubernetes is; it assumes Claude's competence and every section (templates, commands, do's/don'ts) earns its place, matching the score-3 anchor.	3 / 3
Actionability	It provides fully executable `linkerd` CLI commands and complete, copy-paste-ready YAML manifests for installation, injection, ServiceProfiles, TrafficSplit, Server/ServerAuthorization, HTTPRoute, and multi-cluster setup, matching the score-3 anchor.	3 / 3
Workflow Clarity	The installation and multi-cluster templates include sequenced steps with verification commands (`linkerd check --pre`, `linkerd check`, `linkerd multicluster check`), but there is no explicit error-recovery feedback loop ('if check fails, fix and re-run'), which per the rubric guidelines caps workflow clarity at 2 for operations involving cluster-level changes.	2 / 3
Progressive Disclosure	The skill is a single ~300-line monolithic SKILL.md with no external reference files (no references/, scripts/, or assets/ bundles exist) and no one-level-deep navigation, so content that could be split (e.g., the seven templates) is all inline, matching the score-2 anchor rather than a well-signaled multi-file structure.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 is strong: it clearly states what the skill does and when to use it with natural trigger terms and a distinct, tool-specific niche. The only mild weakness is the slightly abstract lead verb ('Implement ... patterns') which keeps specificity at 2 rather than 3.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Linkerd service mesh patterns') and several actions ('setting up Linkerd, configuring traffic policies, implementing zero-trust networking'), but the lead verb 'Implement ... patterns' is somewhat abstract rather than a comprehensive list of concrete actions, matching the score-2 anchor rather than the multi-action score-3 example.	2 / 3
Completeness	It explicitly answers both 'what' ('Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments') and 'when' ('Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking'), matching the score-3 anchor with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Natural terms a user would actually say appear here — 'Linkerd', 'service mesh', 'traffic policies', 'zero-trust networking' — giving good coverage of the domain's common phrasings, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	Linkerd is a specific named tool with distinct triggers ('Linkerd', 'zero-trust networking', 'minimal overhead'), making it clearly niche and unlikely to trigger for non-Linkerd skills, matching the score-3 anchor.	3 / 3
	Total	11 / 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: wshobson/agents
Commit: 5cc2549

Reviewed: about 2 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.