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

51%

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

56%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 body provides concrete, actionable routing guidance with a clear workflow and decision gates, but it is heavily padded with redundant tables and filler sections and does not split its long content across reference files.

Suggestions

Merge the duplicate Agent Selection Matrix and Domain Detection Rules tables into a single keyword-to-agent reference to remove redundancy.

Delete or move the Performance Considerations, User Education, Testing the System, and Debugging Agent Selection sections, which are filler that does not earn its tokens.

Extract the lookup tables and test cases into a reference file and link to it from SKILL.md so the overview stays lean.

Dimension	Reasoning	Score
Conciseness	The ~330-line body is noticeably verbose with redundant material (two overlapping keyword-to-agent tables) and filler sections (Performance Considerations, User Education, Testing the System, Debugging Agent Selection) that could be trimmed, fitting the 2 anchor.	2 / 5
Actionability	Concrete keyword-to-agent lookup tables, exact response-format templates, and explicit edge-case routing give mostly executable guidance; the pseudo-code is labeled as such but the actionable units are concrete, fitting the 4 anchor.	4 / 5
Workflow Clarity	The analyze-detect-assess-select-respond sequence is clear with decision gates ('ASK FIRST', clarifying questions, override capability); this is not a destructive/batch operation so the validation cap does not apply, fitting the 4 anchor.	4 / 5
Progressive Disclosure	Section headers provide some structure, but with no bundle files and a 330-line single document, tangential content (testing, debug, performance, education) is inlined and nothing is split into separate references, fitting the 3 anchor.	3 / 5
	Total	13 / 20 Passed

Description

46%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 occupies a distinct meta-routing niche, but it lacks natural trigger terms and an explicit 'Use when...' clause, leaving the 'when' only weakly implied.

Suggestions

Add an explicit 'Use when...' trigger clause with concrete user phrases (e.g., 'Use when routing a request to the right specialist agent, or when the user asks who should handle a task').

Replace generic terms like 'intelligent task routing' with natural keywords and synonyms users actually say ('pick the right agent', 'which specialist', 'route this task').

List a couple more distinct concrete actions to push specificity from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the routing domain with a couple of concrete actions ('analyzes user requests', 'selects the best specialist agent(s)'), but the actions overlap and coverage is not comprehensive, fitting the 3 anchor rather than 4.	3 / 5
Completeness	The 'what' is clear, but the 'when' is only weakly implied via 'without requiring explicit user mentions' with no 'Use when...' trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like 'user requests', 'task routing', and 'specialist agent(s)' are generic/technical with no natural phrases or synonyms a user would actually say, matching the 2 anchor (one or two generic keywords, missing natural phrases).	2 / 5
Distinctiveness Conflict Risk	It carves a clear meta-routing niche distinct from most task skills, with only minor overlap risk against orchestration skills, fitting the 4 anchor.	4 / 5
	Total	12 / 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
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: 549ba3d

Reviewed: 3 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.