intelligent-routing

Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.

Quality

22%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/intelligent-routing/SKILL.md

Quality

Discovery

17%

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

This description suffers from technical jargon that users wouldn't naturally use and lacks explicit trigger guidance for when to apply the skill. While it attempts to describe the capability, the abstract language ('intelligent task routing', 'specialist agents') doesn't provide concrete actions or natural keywords that would help Claude reliably select this skill.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user has a complex request that could benefit from multiple specialized capabilities or when no specific tool is mentioned.'

Replace technical jargon with natural user language - instead of 'specialist agent(s)', describe what users would actually say like 'help me with...', 'I need to...', or specific task types.

List concrete examples of the types of tasks or requests this skill handles to improve specificity and help distinguish it from other orchestration-type skills.

Dimension	Reasoning	Score
Specificity	Names the domain (agent selection, task routing) and describes actions (analyzes requests, selects agents), but lacks concrete specifics about what types of tasks, which agents, or what 'intelligent routing' actually entails.	2 / 3
Completeness	Describes what it does (analyzes and routes to agents) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Uses technical jargon like 'agent selection', 'task routing', and 'specialist agent(s)' that users would not naturally say. Missing natural trigger terms users might actually use when needing this functionality.	1 / 3
Distinctiveness Conflict Risk	The concept of 'agent selection' is somewhat specific, but 'task routing' and 'analyzes user requests' are generic enough to potentially overlap with orchestration, delegation, or general task management skills.	2 / 3
	Total	6 / 12 Passed

Implementation

27%

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

This skill suffers from severe verbosity, repeating the same routing concepts across multiple formats (tables, flowcharts, code, examples) without adding new information. While the agent selection matrices provide useful reference material, the document lacks executable implementation details and could be condensed significantly. The monolithic structure makes it difficult to navigate and maintain.

Suggestions

Reduce content by 60%+ by eliminating redundant explanations - keep one agent selection table and remove duplicate presentations in flowcharts and pseudo-code

Split into multiple files: main SKILL.md with core routing logic, separate AGENTS.md for agent definitions, and DEBUG.md for testing/debugging

Replace pseudo-code with concrete, actionable instructions for how Claude should analyze requests (e.g., specific keyword matching rules rather than abstract 'classifyRequest' functions)

Add explicit validation steps: what to do when agent selection produces poor results, how to detect misrouting, and recovery procedures

Dimension	Reasoning	Score
Conciseness	Extremely verbose with excessive repetition. The same concepts (agent selection, routing) are explained multiple times in different formats (tables, flowcharts, pseudo-code, examples). Contains unnecessary meta-commentary like 'Testing the System' and 'User Education' sections that add little value. Could be reduced by 60-70%.	1 / 3
Actionability	Provides concrete agent selection matrices and keyword mappings which are actionable. However, the pseudo-code is not executable, the mermaid diagram is illustrative rather than functional, and the actual implementation details for how Claude should perform this routing are abstract rather than concrete instructions.	2 / 3
Workflow Clarity	The workflow is presented (analyze → detect domains → assess complexity → select agent) but lacks explicit validation checkpoints. No feedback loops for when agent selection fails or produces poor results. The 'Edge Cases' section helps but doesn't provide recovery steps.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content is inline despite being over 200 lines. The document could benefit from splitting agent definitions, test cases, and debug instructions into separate files. References to 'GEMINI.md' exist but the relationship is unclear.	1 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: lchenrique/politron-ide
Commit: 7114206

Reviewed: 29 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.