@markus-global/cli 0.4.17 → 0.4.19

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -11,8 +11,8 @@
11
11
  <script>
12
12
  (function(){var t=localStorage.getItem('markus-theme');if(t&&t!=='system')document.documentElement.classList.add(t)})();
13
13
  </script>
14
- <script type="module" crossorigin src="/assets/index-BgJ594-E.js"></script>
15
- <link rel="stylesheet" crossorigin href="/assets/index-CiYrdUAj.css">
14
+ <script type="module" crossorigin src="/assets/index-DVrJcKF4.js"></script>
15
+ <link rel="stylesheet" crossorigin href="/assets/index-3aaspe8C.css">
16
16
  </head>
17
17
  <body>
18
18
  <div id="root"></div>
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@markus-global/cli",
3
- "version": "0.4.17",
3
+ "version": "0.4.19",
4
4
  "description": "Markus — AI Digital Workforce Platform",
5
5
  "type": "module",
6
6
  "license": "AGPL-3.0-or-later",
@@ -35,7 +35,7 @@ You will receive the **live list** of available skills as dynamic context. **Che
35
35
 
36
36
  ## Guidelines
37
37
 
38
- - Instructions in SKILL.md should reference actual tools: `shell_execute`, `file_read`, `file_write`, `file_edit`, `grep`, `glob`, `web_fetch`, `web_search`, `gui` — or MCP tool names if the skill provides its own tools
38
+ - Instructions in SKILL.md should reference actual tools: `shell_execute`, `file_read`, `file_write`, `file_edit`, `grep_search`, `glob_find`, `list_directory`, `web_fetch`, `web_search`, `gui` — or MCP tool names if the skill provides its own tools
39
39
  - Be specific — include actual CLI commands, file paths, and URL patterns
40
40
  - Include error handling: what to do when commands fail, pages don't load, etc.
41
41
  - Provide examples of typical input/output for each workflow step
@@ -74,7 +74,7 @@ Over time you will discover which tools work best for specific situations. Recor
74
74
  ### When to Update Tool Preferences
75
75
 
76
76
  - You discover a tool is significantly better than another for a specific task type
77
- - You find optimal parameters or flags for a tool (e.g., `grep` with specific flags vs. `glob`)
77
+ - You find optimal parameters or flags for a tool (e.g., `grep_search` with specific flags vs. `glob_find`)
78
78
  - You learn that a tool has limitations you should work around
79
79
  - A tool combination (pipeline) works well for a recurring need
80
80
 
@@ -155,7 +155,7 @@ Once all files are written, tell the user:
155
155
 
156
156
  ## Guidelines
157
157
 
158
- - Instructions in SKILL.md should reference actual tools: `shell_execute`, `file_read`, `file_write`, `file_edit`, `grep`, `glob`, `web_fetch`, `web_search`, `gui` — or MCP tool names if the skill provides its own tools
158
+ - Instructions in SKILL.md should reference actual tools: `shell_execute`, `file_read`, `file_write`, `file_edit`, `grep_search`, `glob_find`, `list_directory`, `web_fetch`, `web_search`, `gui` — or MCP tool names if the skill provides its own tools
159
159
  - For MCP-based skills, document every tool with its prefixed name (e.g., `my-api__search`) in SKILL.md so the agent knows how to use them
160
160
  - Be specific — include actual CLI commands, file paths, and URL patterns
161
161
  - Include error handling: what to do when commands fail, pages don't load, etc.