plugin-router

Analyze broad, mixed, or unclear Plugin Factory follow-up requests and select the correct plugin lane. Use when plugin intent lacks a clear lane owner.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

The body is a well-structured, concise overview that practices progressive disclosure by offloading detail to real, verified bundle files. Its weakness is actionability and workflow clarity: the actual routing procedure is not present inline, leaving Claude to load references/workflow.md before it can execute lane selection.

Suggestions

Inline a minimal lane-selection decision table or pseudocode so Claude can route common cases without first loading references/workflow.md.

Add an explicit numbered workflow sequence with a validation checkpoint (route → validate intent → emit handoff) rather than stating the sequence only implicitly.

Show one fully-worked routing handoff example output so the expected handoff object shape is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean, organized into tight sections (Philosophy, When to Use, Inputs, Outputs, Workflow, Boundaries) with no padding or explanation of concepts Claude already knows; every line carries routing-relevant instruction.	3 / 3
Actionability	It gives a concrete output schema (schema_version, selected_lane, next_skill, etc.) and a runnable validation command, but the core routing logic is deferred entirely to references/workflow.md rather than providing executable lane-selection rules inline.	2 / 3
Workflow Clarity	Sequencing is implicit ('Route first, execute second') and validation is deferred to a script with 'Fail fast: stop at first failed gate', but there is no explicit inline multi-step sequence with checkpoints; routing steps live in the referenced workflow.md.	2 / 3
Progressive Disclosure	A clear overview points to one-level-deep, well-signaled references — [references/workflow.md], the design contract, and the factory gate — and the four local bundle files (workflow.md, contract.yaml, evals.yaml, task-profile.json) all exist as referenced, with content appropriately split out of the main file.	3 / 3
	Total	10 / 12 Passed

Description

85%

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 specific, complete with explicit trigger guidance, and clearly distinct in its niche. Its main weakness is trigger-term naturalness — the phrasing leans on internal jargon ('lane owner') rather than language a user would naturally say.

Suggestions

Add more natural user-facing trigger phrasing alongside the jargon (e.g., 'Use when a plugin request is unclear or mixes multiple goals').

Include common term variations users might say such as 'plugin', 'follow-up', or 'route this plugin request' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyze...follow-up requests and select the correct plugin lane' — naming the domain (Plugin Factory follow-ups) and the routing action explicitly rather than vague abstraction.	3 / 3
Completeness	Answers both what ('Analyze...requests and select the correct plugin lane') and when ('Use when plugin intent lacks a clear lane owner') with an explicit 'Use when...' trigger clause, matching the 3-anchor example.	3 / 3
Trigger Term Quality	Includes relevant terms like 'Plugin Factory follow-up requests' and 'plugin intent lacks a clear lane owner', but lacks common natural user phrasings users would actually say (e.g., 'plugin', 'follow-up'); jargon-heavy ('lane owner') reduces coverage.	2 / 3
Distinctiveness Conflict Risk	Niche is clearly bounded to 'Plugin Factory follow-up' routing with explicit scope guard ('select the correct plugin lane'), making it unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: jscraik/Agent-Skills
Commit: 5a6027f

Reviewed: 5 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.