/*============================================================================*/
Selects optimal specialized agents from registry using semantic matching and capability analysis.
/plugin marketplace add DNYoussef/context-cascade/plugin install dnyoussef-context-cascade@DNYoussef/context-cascadeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
CHANGELOG.mdQUICK-REFERENCE.mdmanifest.jsonprocess.dot/============================================================================/ /* AGENT-SELECTOR SKILL :: VERILINGUA x VERIX EDITION / /============================================================================*/
name: agent-selector version: 2.1.0 description: | [assert|neutral] Intelligent agent selection from 203-agent registry using semantic matching and capability analysis [ground:given] [conf:0.95] [state:confirmed] category: orchestration tags:
/----------------------------------------------------------------------------/ /* S0 META-IDENTITY / /----------------------------------------------------------------------------*/
[define|neutral] SKILL := { name: "agent-selector", category: "orchestration", version: "2.1.0", layer: L1 } [ground:given] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ /* S1 COGNITIVE FRAME / /----------------------------------------------------------------------------*/
[define|neutral] COGNITIVE_FRAME := { frame: "Evidential", source: "Turkish", force: "How do you know?" } [ground:cognitive-science] [conf:0.92] [state:confirmed]
Kaynak dogrulama modu etkin.
/----------------------------------------------------------------------------/ /* S2 TRIGGER CONDITIONS / /----------------------------------------------------------------------------*/
[define|neutral] TRIGGER_POSITIVE := { keywords: ["agent-selector", "orchestration", "workflow"], context: "user needs agent-selector capability" } [ground:given] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ /* S3 CORE CONTENT / /----------------------------------------------------------------------------*/
Kaynak dogrulama modu etkin.
Before selecting agents:
.claude/expertise/agent-selection.yamlIntelligently selects the most appropriate specialized agent from the 203-agent registry based on:
Critical for Phase 4 routing to ensure Claude Code uses specialized agents instead of generic ones.
4-Step Process:
Parse Task Requirements
Semantic Search (Memory MCP)
Capability Matching
Return Selection + Reasoning
// Skill invocation
Skill("agent-selector")
// Agent will prompt you for:
// 1. Task description (what needs to be done)
// 2. Domain hint (optional: backend, frontend, testing, etc.)
// 3. Phase hint (optional: development, testing, deployment)
// Output:
{
"selected_agent": "dev-backend-api",
"agent_source": "delivery/development/backend/dev-backend-api.md",
"agent_category": "delivery/development/backend",
"capabilities": ["Express.js", "REST APIs", "JWT", "OpenAPI"],
"selection_reasoning": "Specialized backend API agent with exact match for Express.js + REST requirements",
"alternatives_considered": [
{
"name": "backend-specialist",
"score": 0.82,
"reason": "Less API-specific, more general backend work"
}
],
"confidence": 0.95
}
Automatic Integration:
When Phase 4 routing runs, it MUST use this skill (or inline equivalent) to select agents:
// Phase 4 Routing
for (const task of plan.tasks) {
// Invoke agent-selector
const agentSelection = Skill("agent-selector", {
task: task.description,
domain: task.domain,
phase: task.phase
});
// Use selected agent in Phase 5
task.agent = agentSelection.selected_agent;
task.agent_source = agentSelection.agent_source;
task.agent_capabilities = agentSelection.capabilities;
task.agent_reasoning = agentSelection.selection_reasoning;
}
Exact Capability Match (score: 1.0)
Domain Specialization (score: 0.9)
Tool Requirements (score: 0.8)
/----------------------------------------------------------------------------/ /* S4 SUCCESS CRITERIA / /----------------------------------------------------------------------------*/
[define|neutral] SUCCESS_CRITERIA := { primary: "Skill execution completes successfully", quality: "Output meets quality thresholds", verification: "Results validated against requirements" } [ground:given] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ /* S5 MCP INTEGRATION / /----------------------------------------------------------------------------*/
[define|neutral] MCP_INTEGRATION := { memory_mcp: "Store execution results and patterns", tools: ["mcp__memory-mcp__memory_store", "mcp__memory-mcp__vector_search"] } [ground:witnessed:mcp-config] [conf:0.95] [state:confirmed]
/----------------------------------------------------------------------------/ /* S6 MEMORY NAMESPACE / /----------------------------------------------------------------------------*/
[define|neutral] MEMORY_NAMESPACE := { pattern: "skills/orchestration/agent-selector/{project}/{timestamp}", store: ["executions", "decisions", "patterns"], retrieve: ["similar_tasks", "proven_patterns"] } [ground:system-policy] [conf:1.0] [state:confirmed]
[define|neutral] MEMORY_TAGGING := { WHO: "agent-selector-{session_id}", WHEN: "ISO8601_timestamp", PROJECT: "{project_name}", WHY: "skill-execution" } [ground:system-policy] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ /* S7 SKILL COMPLETION VERIFICATION / /----------------------------------------------------------------------------*/
[direct|emphatic] COMPLETION_CHECKLIST := { agent_spawning: "Spawn agents via Task()", registry_validation: "Use registry agents only", todowrite_called: "Track progress with TodoWrite", work_delegation: "Delegate to specialized agents" } [ground:system-policy] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ /* S8 ABSOLUTE RULES / /----------------------------------------------------------------------------*/
[direct|emphatic] RULE_NO_UNICODE := forall(output): NOT(unicode_outside_ascii) [ground:windows-compatibility] [conf:1.0] [state:confirmed]
[direct|emphatic] RULE_EVIDENCE := forall(claim): has(ground) AND has(confidence) [ground:verix-spec] [conf:1.0] [state:confirmed]
[direct|emphatic] RULE_REGISTRY := forall(agent): agent IN AGENT_REGISTRY [ground:system-policy] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ /* PROMISE / /----------------------------------------------------------------------------*/
[commit|confident] <promise>AGENT_SELECTOR_VERILINGUA_VERIX_COMPLIANT</promise> [ground:self-validation] [conf:0.99] [state:confirmed]
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.