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

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/intelligent-routing/SKILL.md

Quality

Content

50%

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

The body is well-organized and provides a clear, actionable routing model, but it is held at mid-level by redundancy between its two routing tables, illustrative rather than executable pseudo-code, and a monolithic structure with no progressive disclosure to supporting files.

Suggestions

Collapse the Agent Selection Matrix and Domain Detection Rules tables into one authoritative mapping to remove redundancy and tighten conciseness.

Replace the non-executable analyzeRequest pseudo-code with a concrete, copy-paste-ready decision checklist or a minimal real routing snippet to raise actionability.

Move the Testing the System, Debugging Agent Selection, and User Education sections into a separate reference file linked one level deep from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-sectioned, but the Agent Selection Matrix and Domain Detection Rules tables substantially duplicate each other, the JS analyzeRequest pseudo-code is illustrative rather than necessary, and the Summary restates earlier points, so it could be tightened considerably.	2 / 3
Actionability	The keyword-to-agent tables and complexity-tier actions are concrete and specific, but execution depends on named agents that are not defined here, and the routing logic is given as non-executable pseudo-code rather than copy-paste-ready invocation guidance.	2 / 3
Workflow Clarity	The analyze-to-select-to-respond sequence is clearly laid out with ASK-FIRST and clarifying-question gates for vague or contradictory requests, but validation checkpoints are implicit and there is no step verifying the routing decision itself.	2 / 3
Progressive Disclosure	The ~330-line body is a single monolithic file with good section headers but no one-level-deep references to split out material (testing, debugging, the duplicate tables), and at well over 50 lines it does not qualify for the simple-skill exemption.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 clear and written in correct third-person voice, but it settles at mid-level across all dimensions: it states what the skill does without an explicit 'Use when' trigger clause and without rich natural-language trigger terms. It is competent but not exemplary.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when routing user requests to specialist agents, handling multi-domain tasks, or when no agent is explicitly mentioned') to lift completeness to 3.

Surface natural user-language trigger terms (e.g., 'agent', 'specialist', 'who should handle this', 'multi-domain', 'unclear which expert') instead of jargon like 'intelligent task routing'.

List a couple more concrete actions (e.g., 'classifies request complexity, detects domains, and selects single or multi-agent routing') to raise specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Automatic agent selection and intelligent task routing') and a couple of concrete actions ('Analyzes user requests and automatically selects the best specialist agent(s)'), but does not enumerate multiple distinct concrete operations, matching the score-2 anchor rather than the multi-action score-3 example.	2 / 3
Completeness	It clearly states what the skill does, but offers no explicit 'Use when...' trigger clause; per the guidelines a missing explicit trigger caps completeness at 2, and the 'when' is only implied by 'without requiring explicit user mentions'.	2 / 3
Trigger Term Quality	Terms like 'agent selection', 'task routing', and 'specialist agent' are recognizable but lean technical and miss common user-language variations; a user is unlikely to say 'intelligent task routing' when they need this skill.	2 / 3
Distinctiveness Conflict Risk	The automatic-routing niche is fairly specific, but it could still overlap with general orchestrator/multi-agent skills, so it does not reach the distinct-trigger score-3 level.	2 / 3
	Total	8 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/intelligent-routing/SKILL.md
Commit: 04514f0

Reviewed: about 13 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.