@olaservo/skill-jack-mcp 0.1.0 → 0.1.1

package/README.md

@@ -1,6 +1,8 @@
 # Skill Jack MCP
 
-An MCP server that jacks [Agent Skills](https://agentskills.dev) directly into your LLM's brain.
+An MCP server that jacks [Agent Skills](https://agentskills.io) directly into your LLM's brain.
+
+> **Recommended:** For best results, use an [MCP client](https://modelcontextprotocol.io/clients) that supports server instructions. This allows the LLM to see available skills in its system prompt, enabling automatic skill discovery and activation. Without this support, the model will still be able to call these tools, but you might need to provide more explicit instructions on what skills are available and the intended activation patterns.
 
 ## Features
 
@@ -52,7 +54,7 @@ skill-jack-mcp "C:/Users/you/skills"
 
 ## How It Works
 
-The server implements the [Agent Skills](https://agentskills.dev) progressive disclosure pattern:
+The server implements the [Agent Skills](https://agentskills.io) progressive disclosure pattern:
 
 1. **At startup**: Discovers skills from configured directory
 2. **On connection**: Server instructions (with skill metadata) are sent in the initialize response
@@ -96,7 +98,7 @@ Read files within a skill's directory (`scripts/`, `references/`, `assets/`, `sn
 
 This follows the Agent Skills spec's progressive disclosure pattern - resources are loaded only when needed.
 
-**Input:**
+**Read a single file:**
 ```json
 {
   "skill": "mcp-server-ts",
@@ -104,7 +106,14 @@ This follows the Agent Skills spec's progressive disclosure pattern - resources
 }
 ```
 
-**Output:** File content.
+**Read all files in a directory:**
+```json
+{
+  "skill": "algorithmic-art",
+  "path": "templates"
+}
+```
+Returns all files in the directory as multiple content items.
 
 **List available files** (pass empty path):
 ```json
@@ -213,6 +222,6 @@ npx @modelcontextprotocol/inspector@latest node dist/index.js /path/to/skills
 
 ## Related
 
-- [Agent Skills Specification](https://agentskills.dev)
+- [Agent Skills Specification](https://agentskills.io)
 - [MCP TypeScript SDK](https://github.com/modelcontextprotocol/typescript-sdk)
 - [Example MCP Clients](https://modelcontextprotocol.io/clients)

package/dist/skill-tool.js

@@ -87,7 +87,7 @@ const SkillResourceSchema = z.object({
     skill: z.string().describe("Skill name"),
     path: z
         .string()
-        .describe("Relative path (e.g., 'snippets/tool.ts'). Empty string lists all files."),
+        .describe("Relative path to file or directory. Examples: 'snippets/tool.ts' (single file), 'templates' (all files in directory), '' (list available files)."),
 });
 // Security constants (exported for reuse in skill-resources.ts)
 export const MAX_FILE_SIZE = 10 * 1024 * 1024; // 10MB max file size

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@olaservo/skill-jack-mcp",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "MCP server that discovers and serves Agent Skills. I know kung fu.",
   "type": "module",
   "main": "dist/index.js",