routing

Multi-agent routing, channel bindings, and tool policies

Quality

32%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./src/skills/bundled/routing/SKILL.md

Quality

Content

57%

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

The skill excels at actionability with concrete, executable TypeScript examples and clear chat commands. However, it suffers from being a monolithic reference document that would benefit greatly from splitting into an overview SKILL.md with references to detailed API docs. It also lacks validation/error-handling steps in its workflows.

Suggestions

Split the content into an overview SKILL.md with quick-start examples and separate reference files (e.g., API_REFERENCE.md, CHAT_COMMANDS.md, ROUTING_RULES.md) with clear cross-links.

Add validation/error-handling steps: what happens when routing fails, when an agent ID doesn't exist, or when a tool policy update conflicts?

Remove the Built-in Agents table since it duplicates the agent definitions already shown in the createRoutingService code example.

Trim the Best Practices section—items like 'use fast models for trading' and 'restrict tools appropriately' are self-evident from the agent configuration examples.

Dimension	Reasoning	Score
Conciseness	The content is fairly well-structured but includes some unnecessary verbosity—the 'Best Practices' section states obvious things, and the extensive inline API examples could be trimmed or referenced externally. The built-in agents table duplicates information already shown in the createRoutingService example.	2 / 3
Actionability	The skill provides fully executable TypeScript code examples for every operation—creating routing services, routing messages, managing bindings, setting tool policies, and adding custom agents. Chat commands are also concrete and copy-paste ready.	3 / 3
Workflow Clarity	The routing rules section explains the decision sequence (binding → pattern → keyword → fallback), but there are no validation checkpoints or error handling steps. For operations like updating tool policies or adding agents, there's no guidance on verifying success or recovering from errors.	2 / 3
Progressive Disclosure	This is a monolithic wall of content—over 200 lines of API reference, chat commands, routing rules, tool categories, and best practices all inline in a single file. The description says 'Complete API Reference' but there's no separation into overview vs. detailed reference files, and no cross-references to external documents.	1 / 3
	Total	8 / 12 Passed

Description

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 is essentially a list of three technical noun phrases with no verbs, no concrete actions, and no trigger guidance. It fails to communicate what the skill does or when it should be selected. A user or Claude would struggle to know when to invoke this skill over others.

Suggestions

Add concrete action verbs describing what the skill does, e.g., 'Configures routing rules between multiple agents, defines channel bindings for message delivery, and enforces tool access policies.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to set up agent routing, configure which tools agents can access, or bind communication channels between agents.'

Replace or supplement jargon with plain-language synonyms that users would naturally use, such as 'agent communication', 'tool permissions', or 'message routing'.

Dimension	Reasoning	Score
Specificity	The description lists abstract concepts ('multi-agent routing', 'channel bindings', 'tool policies') without describing any concrete actions. There are no verbs indicating what the skill actually does.	1 / 3
Completeness	The description fails to answer both 'what does this do' (no actions described) and 'when should Claude use it' (no 'Use when...' clause or equivalent trigger guidance).	1 / 3
Trigger Term Quality	The terms used are highly technical jargon ('channel bindings', 'tool policies') that users would rarely naturally say. A user needing this skill would likely describe their problem differently.	1 / 3
Distinctiveness Conflict Risk	The terms are niche enough that they wouldn't broadly conflict with many other skills, but the lack of specificity about what it actually does makes it hard to confidently distinguish from other agent/routing-related skills.	2 / 3
	Total	5 / 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: alsk1992/CloddsBot
Commit: e71a5f6

Reviewed: 2 months 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.