feat: add agent skills and guardrails functionality

- Introduced new tools for managing agent skills and guardrails, including add, remove, and list operations.
- Updated README.md to document new commands and usage patterns for skills and guardrails.
- Enhanced server configuration to support longer read and write timeouts.
- Increased maximum upload size for files to 100 MB and adjusted related configurations.
- Created database migrations for agent skills, guardrails, and their associations with projects.
- Updated relevant code files to integrate new skills and guardrails into the application logic.

internal/mcpserver/server.go

@@ -33,6 +33,7 @@ type ToolSet struct {
 	Calendar      *tools.CalendarTool
 	Meals         *tools.MealsTool
 	CRM           *tools.CRMTool
+	Skills        *tools.SkillsTool
 }
 
 func New(cfg config.MCPConfig, toolSet ToolSet) http.Handler {
@@ -306,6 +307,69 @@ func New(cfg config.MCPConfig, toolSet ToolSet) http.Handler {
 		Description: "Append a stored thought to a contact's notes.",
 	}, toolSet.CRM.LinkThought)
 
+	// Agent Skills
+	addTool(server, &mcp.Tool{
+		Name:        "add_skill",
+		Description: "Store a reusable agent skill (behavioural instruction or capability prompt).",
+	}, toolSet.Skills.AddSkill)
+
+	addTool(server, &mcp.Tool{
+		Name:        "remove_skill",
+		Description: "Delete an agent skill by id.",
+	}, toolSet.Skills.RemoveSkill)
+
+	addTool(server, &mcp.Tool{
+		Name:        "list_skills",
+		Description: "List all agent skills, optionally filtered by tag.",
+	}, toolSet.Skills.ListSkills)
+
+	// Agent Guardrails
+	addTool(server, &mcp.Tool{
+		Name:        "add_guardrail",
+		Description: "Store a reusable agent guardrail (constraint or safety rule).",
+	}, toolSet.Skills.AddGuardrail)
+
+	addTool(server, &mcp.Tool{
+		Name:        "remove_guardrail",
+		Description: "Delete an agent guardrail by id.",
+	}, toolSet.Skills.RemoveGuardrail)
+
+	addTool(server, &mcp.Tool{
+		Name:        "list_guardrails",
+		Description: "List all agent guardrails, optionally filtered by tag or severity.",
+	}, toolSet.Skills.ListGuardrails)
+
+	// Project Skills & Guardrails
+	addTool(server, &mcp.Tool{
+		Name:        "add_project_skill",
+		Description: "Link an agent skill to a project.",
+	}, toolSet.Skills.AddProjectSkill)
+
+	addTool(server, &mcp.Tool{
+		Name:        "remove_project_skill",
+		Description: "Unlink an agent skill from a project.",
+	}, toolSet.Skills.RemoveProjectSkill)
+
+	addTool(server, &mcp.Tool{
+		Name:        "list_project_skills",
+		Description: "List all skills linked to a project. Call this at the start of a project session to load existing agent behaviour instructions before generating new ones.",
+	}, toolSet.Skills.ListProjectSkills)
+
+	addTool(server, &mcp.Tool{
+		Name:        "add_project_guardrail",
+		Description: "Link an agent guardrail to a project.",
+	}, toolSet.Skills.AddProjectGuardrail)
+
+	addTool(server, &mcp.Tool{
+		Name:        "remove_project_guardrail",
+		Description: "Unlink an agent guardrail from a project.",
+	}, toolSet.Skills.RemoveProjectGuardrail)
+
+	addTool(server, &mcp.Tool{
+		Name:        "list_project_guardrails",
+		Description: "List all guardrails linked to a project. Call this at the start of a project session to load existing agent constraints before generating new ones.",
+	}, toolSet.Skills.ListProjectGuardrails)
+
 	return mcp.NewStreamableHTTPHandler(func(*http.Request) *mcp.Server {
 		return server
 	}, &mcp.StreamableHTTPOptions{