gonzalezpazmonica/smart-routing
.claude/skills/smart-routing/SKILL.md
Enrutamiento inteligente de comandos y descubrimiento de herramientas para 400+ comandos
$ install --global
skillsauthnpx skillsauth add gonzalezpazmonica/pm-workspace smart-routingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 8:50 PM1.8s1 file scanned
SKILL.md
- name:
- smart-routing
- description:
- Enrutamiento inteligente de comandos y descubrimiento de herramientas para 400+ comandos
- summary:
- |
- maturity:
- stable
- model:
- sonnet
- context_cost:
- medium
- memory:
- project
- category:
- sdd-framework
- tags:
- ["routing", "discovery", "commands", "intent"]
- priority:
- high
Smart Routing for 400+ Commands
Intelligent command discovery and routing for large tool catalogs. Maps user intent to relevant command categories, loads only necessary tools, maintains usage frequency for Top-20 prioritization.
Core Components
Intent Classification
Parse user request to identify primary and secondary intents:
User: "¿Cómo está el sprint?"
→ Primary: sprint status tracking
→ Category: PM Operations
→ Tools: [sprint-status, board-flow, daily-routine]
Implemented in Step 1 (input analysis):
- Extract keywords (sprint, status, dashboard, report, security, etc.)
- Map to category probabilities
- Select top 1-2 categories
Frequency Tracking
Maintain data/tool-usage.jsonl with:
{ "command": "sprint-status", "count": 47, "last_used": "2026-03-06T15:30:00Z", "category": "pm" }
Update after each command execution.
Top-20 Algorithm
Always available commands (never unloaded):
- Most-used 10 commands (cross-category)
- 10 most-used from active category
Loaded only when explicitly searched or category active:
- Remaining 90% of catalog
- Loaded via
/tool-searchor/tool-catalog
Routing Logic (5 Steps)
Step 1: Intent Analysis (input)
- Extract keywords from user request
- Assign category probabilities (PM, Dev, Infra, Reporting, Compliance, Discovery, Admin)
- Identify secondary categories if applicable
Step 2: Category Selection
- Primary category: highest probability
- Secondary: if probability >30%, include its top tools
- Load 20-30 tools from selected categories
Step 3: Usage Frequency Weighting
- Boost: most-used commands in category (+priority in suggestions)
- Order results by: relevance + frequency
Step 4: Suggestion Generation
- Top 3 candidate commands for primary category
- 1-2 commands from secondary category
- Brief description + confidence score (%)
Step 5: User Confirmation
- Show suggestions with confidence
- User selects or enters new search
- Execute selected command or refine search
Data Structure
categories:
pm: [pbi-*, sprint-*, capacity-*, project-*]
dev: [spec-*, dev-*, arch-*, code-*]
infra: [infra-*, pipeline-*, deploy-*, env-*]
reporting: [report-*, audit-*, track-*, metric-*]
communication: [scheduled-*, notify-*, chat-*]
compliance: [security-*, compliance-*, aepd-*, equality-*]
discovery: [discovery-*, jtbd-*, prd-*, rules-*]
admin: [plugin-*, agent-*, profile-*, config-*]
usage_tracking: data/tool-usage.jsonl
command_metadata: .claude/commands/*.md
skill_metadata: .claude/skills/*/SKILL.md
agent_metadata: .claude/agents/*.md
Integration Points
/tool-search— Explicit search activation/tool-catalog— Browse categories- NL command resolution — Implicit routing
- Session init — Pre-load Top-20
Related Skills
gonzalezpazmonica/skill-creator
testing
VerifiedTrustedCommunity
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
40SKILL.mdUpdated May 24, 2026
gonzalezpazmonica/mcp-builder
tools
VerifiedTrustedCommunity
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
40SKILL.mdUpdated May 24, 2026
gonzalezpazmonica/wellbeing-guardian
tools
VerifiedTrustedCommunity
Sistema proactivo de bienestar individual
33SKILL.mdUpdated Apr 17, 2026
gonzalezpazmonica/web-research
development
VerifiedTrustedCommunity
Search the web to resolve context gaps — documentation, versions, CVEs, best practices. Auto-starts SearxNG Docker if available, falls back to WebSearch.
33SKILL.mdUpdated Apr 17, 2026