skill-router

Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their goal.

Quality

72%

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 ./skills/skill-router/SKILL.md

Quality

Content

70%Scale 1-5

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

This is a well-structured conversational skill with a clear 4-step workflow and a comprehensive routing reference. Its main weakness is that the large routing reference table bloats the file and would benefit from being extracted into a separate bundle file. The content is mostly efficient but could trim some explanatory text that Claude doesn't need.

Suggestions

Extract the 'Skill Routing Reference' section into a separate file (e.g., ROUTING_REFERENCE.md) and reference it from the main SKILL.md to improve progressive disclosure and reduce token usage.

Tighten the funnel questions section — Claude doesn't need the full numbered option lists spelled out; a brief description of each question's intent with example options would suffice.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably structured but includes some unnecessary verbosity — the funnel questions are spelled out in full detail that Claude could infer, and the routing reference table, while useful, is quite long. The example interaction and constraints sections add value but could be tighter.	3 / 5
Actionability	The skill provides concrete guidance: exact question sequences, a structured recommendation format with copy-paste invoke syntax, and a detailed routing reference mapping goals to specific skills. However, it's an instruction-only skill (no code to execute), and the routing logic relies on Claude matching natural language to categories rather than providing a deterministic lookup mechanism.	4 / 5
Workflow Clarity	The 4-step workflow is clearly sequenced (acknowledge → interview → recommend → offer prompt), with explicit instructions on when to skip questions, a structured output format for recommendations, and a complete example interaction demonstrating the full flow. This is not a destructive/batch operation, so no validation checkpoints are needed.	5 / 5
Progressive Disclosure	The routing reference section is ~100 lines of category-to-skill mappings that would be better placed in a separate reference file, keeping the SKILL.md focused on the interview workflow. Everything is inlined in a single monolithic file with no bundle files to offload the reference content.	3 / 5
	Total	15 / 20 Passed

Description

75%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 effectively communicates a clear meta-skill purpose with explicit 'Use when' guidance and a distinct niche that won't conflict with other skills. Its main weaknesses are limited trigger term coverage (missing common user phrasings like 'what can you do' or 'help me choose') and moderate specificity about the interview/recommendation process.

Suggestions

Add more natural trigger terms users might say, such as 'what can you do,' 'help me choose,' 'which tool should I use,' 'list available skills,' or 'I don't know where to start'

Expand specificity by mentioning concrete actions like 'asks clarifying questions about the user's goal, matches requirements to available skills, and explains why each recommendation fits'

Dimension	Reasoning	Score
Specificity	Names the domain (skill selection/recommendation) and describes two concrete actions: interviewing the user with targeted questions and recommending skills. However, it lacks detail about what kinds of goals or scenarios it covers.	3 / 5
Completeness	Clearly answers both 'what' (interviews the user with targeted questions and recommends the best skill(s) from the installed library) and 'when' (when the user is unsure which skill to use or where to start), with an explicit 'Use when' clause containing concrete trigger conditions.	5 / 5
Trigger Term Quality	Includes some relevant trigger phrases like 'unsure which skill to use' and 'where to start,' but misses natural user phrases like 'help me choose,' 'what can you do,' 'list skills,' 'which tool,' or 'I don't know how to.' Coverage of synonyms and variations is limited.	3 / 5
Distinctiveness Conflict Risk	This is a meta-skill about skill selection itself, which is a very distinct niche. It's unlikely to conflict with any domain-specific skill since its purpose is explicitly about routing users to other skills.	5 / 5
	Total	16 / 20 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/skill-router/SKILL.md
Commit: 57c135b

Reviewed: 19 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.