Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
charon-fan avatar

Skill Router

  • 801 installs
  • 65 repo stars
  • Updated June 21, 2026
  • charon-fan/agent-playbook

skill-router is an agent skill that analyzes plain-English requests and recommends the best matching skill from an installed catalog for developers who cannot manually search dozens of skills.

About

skill-router is an intelligent routing layer from charon-fan/agent-playbook for Claude Code skills. It pipelines user requests through intent analysis, semantic skill matching, and optional interactive clarification before recommending the most appropriate skill. Installation symlinks the skill into ~/.claude/skills/skill-router. Developers reach for skill-router when they describe a task in natural language—fix my tests, deploy to Vercel, write docs—and want the agent to pick the right playbook instead of guessing or loading the wrong skill. It is catalog-aware infrastructure, not a domain implementation skill itself.

  • Performs intent analysis, semantic matching, and interactive clarification
  • Routes requests to the most appropriate skill with clear reasoning
  • Handles both direct matches and ambiguous user requests
  • Interactive clarification with targeted follow-up questions
  • Reduces time spent hunting for the correct agent skill

Skill Router by the numbers

  • 801 all-time installs (skills.sh)
  • +13 installs in the week ending Jul 28, 2026 (Skillselion tracking)
  • Ranked #1,306 of 16,659 AI & Agent Building skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/charon-fan/agent-playbook --skill skill-router

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs801
repo stars65
Security audit3 / 3 scanners passed
Last updatedJune 21, 2026
Repositorycharon-fan/agent-playbook

How do you find the right agent skill for a task?

Instantly surface the right skill from the catalog when they describe a task in plain English.

Who is it for?

Developers with large Claude Code skill catalogs who describe tasks in natural language instead of skill slugs.

Skip if: Single-skill projects or workflows where the target skill is already known and explicitly named.

When should I use this skill?

The user describes a task in plain English without naming a specific skill, or asks which skill handles a workflow.

What you get

A ranked skill recommendation with intent classification and optional clarification prompts before invocation.

  • skill recommendation
  • clarification prompts

Files

SKILL.mdMarkdownGitHub ↗

Skill Router

An intelligent router that analyzes user requests and recommends the most appropriate Claude Code skill for the task.

When This Skill Activates

This skill activates when you:

  • Ask "which skill should I use?" or "what skill can help with...?"
  • Say "use a skill" without specifying which one
  • Express a need but aren't sure which skill fits
  • Mention "skill router" or "help me find a skill"

Available Skills Catalog

Meta & Workflow

SkillBest For
skill-routerFinding and selecting the right skill for a task
create-prCreating pull requests with bilingual documentation checks
session-loggerSaving session summaries and activity logs
workflow-orchestratorCoordinating multi-skill workflows and triggers
self-improving-agentLearning from completed skill workflows
auto-triggerDeclaring trigger relationships between skills

Core Development

SkillBest For
commit-helperWriting Git commit messages, formatting commits
code-reviewerReviewing PRs, code changes, quality checks
debuggerDiagnosing bugs, errors, unexpected behavior
refactoring-specialistImproving code structure, reducing technical debt

Documentation & Testing

SkillBest For
documentation-engineerWriting README, technical docs, code documentation
api-documenterCreating OpenAPI/Swagger specifications
test-automatorWriting tests, setting up test frameworks
qa-expertTest strategy, quality gates, QA processes

Architecture & DevOps

SkillBest For
api-designerDesigning REST/GraphQL APIs, API architecture
security-auditorSecurity audits, vulnerability reviews, OWASP Top 10
performance-engineerPerformance optimization, speed analysis
deployment-engineerCI/CD pipelines, deployment automation

Planning & Analysis

SkillBest For
prd-plannerCreating PRDs with persistent file-based planning
prd-implementation-precheckPrechecking PRDs/specs before implementation
architecting-solutionsNon-PRD solution design, architecture, and requirements analysis
planning-with-filesMulti-step task planning, persistent file-based organization
long-task-coordinatorMulti-session, delegated, or resumable work that needs explicit state and recovery

Design & UX

SkillBest For
figma-designerAnalyzing Figma designs and producing implementation-ready visual specs/PRDs

Routing Process

Step 1: Intent Analysis

Analyze the user's request to identify:

  • Task Type: What does the user want to accomplish?
  • Context: What is the working domain (web, mobile, data, etc.)?
  • Complexity: Is this a simple task or complex workflow?

Step 2: Skill Matching

Match the identified intent to the most relevant skill(s) using:

  • Keyword matching: Compare request keywords with skill descriptions
  • Semantic similarity: Understand the meaning behind the request
  • Context awareness: Consider project state and previous actions

Step 3: Interactive Clarification

If the request is ambiguous, guide the user with targeted questions:

  • What is the primary goal?
  • What type of output is expected?
  • Are there specific constraints or preferences?

Step 4: Recommendation & Execution

Present the recommended skill with:

  • Skill name and brief description
  • Why it fits the current request
  • Option to proceed or ask for alternatives

Routing Examples

Example 1: Clear Intent

User: "I need to review this pull request"

Router Analysis:

  • Keywords: "review", "pull request"
  • Intent: Code review
  • Recommendation: code-reviewer

Example 2: Ambiguous Intent

User: "Use a skill to help with my project"

Router Questions: 1. What type of task are you working on? 2. Are you designing, coding, testing, or documenting?

Based on answers → Recommend appropriate skill

Example 3: Multi-Skill Scenario

User: "I'm building a new API and need help with the full workflow"

Router Recommendation: Consider using multiple skills in sequence: 1. api-designer - Design the API structure 2. api-documenter - Document endpoints with OpenAPI 3. test-automator - Set up API tests 4. code-reviewer - Review implementation

Interactive Question Templates

When user intent is unclear, use these question patterns:

Goal Clarification

  • "What are you trying to accomplish with this task?"
  • "What would the ideal outcome look like?"

Domain Identification

  • "What area does this relate to: development, testing, documentation, or deployment?"
  • "Are you working on code, APIs, infrastructure, or something else?"

Stage Assessment

  • "What stage are you at: planning, implementing, testing, or maintaining?"

Preference Confirmation

  • "Do you want a quick solution or a comprehensive approach?"
  • "Are there specific tools or frameworks you're using?"

Best Practices

1. Start Broad, Then Narrow

  • Begin with general category questions
  • Drill down into specifics based on responses

2. Explain Your Reasoning

  • Tell the user why a particular skill is recommended
  • Build trust through transparency

3. Offer Alternatives

  • Present the top recommendation
  • Mention 1-2 alternatives if applicable

4. Handle Edge Cases

  • If no skill fits perfectly, suggest the closest match
  • Offer to help without a specific skill if better

5. Learn from Context

  • Consider previous interactions
  • Remember user preferences for future routing

Advanced Routing Patterns

Semantic Routing

Use semantic similarity when keywords don't match directly:

  • "clean up my code" → refactoring-specialist
  • "make my app faster" → performance-engineer
  • "check for security issues" → security-auditor
  • "resume this interrupted workflow" → long-task-coordinator

Multi-Skill Orchestrations

Suggest skill combinations for complex workflows:

  • New Feature: architecting-solutionsdebuggercode-reviewer
  • API Project: api-designerapi-documentertest-automator
  • Production Readiness: security-auditorperformance-engineerdeployment-engineer

Confidence Levels

Indicate confidence in recommendations:

  • High: Direct keyword match, clear intent
  • Medium: Semantic similarity, reasonable inference
  • Low: Ambiguous request, clarification needed

Error Recovery

If the recommended skill doesn't fit: 1. Acknowledge the mismatch 2. Ask follow-up questions to refine understanding 3. Provide alternative recommendations 4. Fall back to general assistance if needed

Output Format

When recommending a skill, use this format:

## Recommended Skill: {skill-name}

{brief description of why this skill fits}

**What it does:** {one-sentence skill description}

**Best for:** {specific use cases}

---

Would you like me to activate this skill, or would you prefer to see other options?

References

Related skills

FAQ

How does skill-router pick a skill?

skill-router analyzes the user request with intent classification and semantic matching against the installed skill catalog, then recommends the best fit. It can ask clarifying questions when multiple skills score similarly.

How do you install skill-router?

skill-router installs by symlinking the agent-playbook skills/skill-router directory into ~/.claude/skills/skill-router so Claude Code can load the router alongside other catalog skills.

Is Skill Router safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

AI & Agent Buildingagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.