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

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./Plugins/plugin-factory/skills/team_automation/plugin-router/SKILL.md

Quality

Content

71%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.

The content is well-structured with strong progressive disclosure and mostly actionable guidance, delegating the detailed routing protocol cleanly to one-level-deep references. The main weakness is redundancy of the non-execution boundary across several sections.

Suggestions

Consolidate the repeated non-execution boundary into a single Execution Boundaries section and reference it from Constraints/Anti-Patterns to reduce token redundancy.

Inline a minimal copy-paste handoff object template in the body so the output shape is actionable without opening workflow.md.

Surface the numbered routing procedure (classify -> choose mode -> select lane -> emit handoff and stop) directly in the body, keeping workflow.md for the detailed route map.

Dimension	Reasoning	Score
Conciseness	The body is lean with no over-explanation of known concepts, but the non-execution boundary is restated in Execution Boundaries, Constraints, and Anti-Patterns, and the canonical-front-door caveat recurs in the intro and When to Use sections, so it could be tightened beyond a minor-trim level.	3 / 5
Actionability	Concrete guidance is present (output handoff fields, input-to-lane examples, an executable validation command), with only a minor gap because the full copy-paste handoff template lives in workflow.md rather than inline in the body.	4 / 5
Workflow Clarity	A clear sequenced procedure with a clarify-once feedback loop and a fail-fast stop checkpoint exists (in workflow.md), but the body delegates the sequence to a reference rather than sequencing it inline, leaving a minor gap below the explicit-checklist level of 5.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references (a 'Read when' navigation guide plus a References list), the referenced bundle files (workflow.md, contract.yaml, evals.yaml, task-profile.json) all exist, and detailed material is appropriately split out rather than nested.	5 / 5
	Total	16 / 20 Passed

Description

62%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.

The description clearly states what the skill does and when to use it with a concrete trigger, but its trigger phrasing is somewhat internal/jargon-heavy and it does not distinguish itself from the sibling plugin-factory-router. Strong on completeness, moderate on natural trigger terms.

Suggestions

Add more natural user-facing trigger phrases (e.g., 'Use when a user asks for plugin help without naming creator, builder, or installer') to improve trigger_term_quality.

List a couple more concrete routing actions (e.g., classify intent, emit a handoff object) to lift specificity from 1-2 actions to several.

Disambiguate from plugin-factory-router in the description (e.g., 'Use after canonical plugin-factory routing when a follow-up still lacks a clear lane owner') to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain ('Plugin Factory follow-up requests') and two concrete actions ('Analyze ... requests and select the correct plugin lane'), matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' level above.	3 / 5
Completeness	Both 'what' (analyze and select the correct lane) and an explicit 'when' ('Use when plugin intent lacks a clear lane owner') are present, but the when clause is a single trigger that could be more explicit and specific, so it is not a clean 5.	4 / 5
Trigger Term Quality	Relevant keywords exist ('plugin', 'Plugin Factory', 'plugin intent') but the phrasing leans internal/jargon ('lane owner') and misses the natural terms a user would actually say, so it sits at 'some relevant keywords but missing common variations' rather than the fuller coverage of 4.	3 / 5
Distinctiveness Conflict Risk	The routing niche is clear and domain-scoped, but the description does not disambiguate from the closely related canonical 'plugin-factory-router', leaving minor overlap risk rather than minimal conflict.	4 / 5
	Total	14 / 20 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
Path: Plugins/plugin-factory/skills/team_automation/plugin-router/SKILL.md
Commit: 2f91362

Reviewed: 1 day 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.