@theronap/cortex-mcp 0.9.1 → 0.9.2
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.
- package/README.md +3 -1
- package/package.json +1 -1
- package/skills/context/SKILL.md +25 -0
package/README.md
CHANGED
|
@@ -19,13 +19,15 @@ Connect your AI assistant to **Cortex** — your org's projects, recent activity
|
|
|
19
19
|
}
|
|
20
20
|
```
|
|
21
21
|
|
|
22
|
-
3. Restart Claude Code. Your AI now sees your org context automatically
|
|
22
|
+
3. Restart Claude Code. Your AI now sees your org context automatically, and the managed startup skill
|
|
23
|
+
will prefer query-centered `session_context` on substantive session opens.
|
|
23
24
|
|
|
24
25
|
No clone, no path, no build step — `npx` fetches and runs it.
|
|
25
26
|
|
|
26
27
|
## Tools
|
|
27
28
|
|
|
28
29
|
- **my_context** — your projects, recent activity, gaps, and directives.
|
|
30
|
+
- **session_context** — opening-query-centered context seeded from the most relevant node and its neighborhood.
|
|
29
31
|
- **search_org** — search your visible activity and projects by keyword.
|
|
30
32
|
- **project_status** — status of a specific project by key.
|
|
31
33
|
|
package/package.json
CHANGED
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: cortex-context
|
|
3
|
+
description: Automatically hydrate Cortex context at the start of a substantive session. Use when Cortex MCP is available and the user has made a real request, so the first answer is grounded in query-centered org context instead of the static baseline alone.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
> **Cortex-managed skill.** This file is installed and kept up to date by Cortex. Local edits are
|
|
7
|
+
> restored on the next session (a backup of your version is saved alongside). Don't rely on changes here.
|
|
8
|
+
|
|
9
|
+
## When to use
|
|
10
|
+
|
|
11
|
+
At the beginning of a work session, once the user has given a real request or question. Skip trivial
|
|
12
|
+
chit-chat and requests where org context is obviously irrelevant.
|
|
13
|
+
|
|
14
|
+
## Steps
|
|
15
|
+
|
|
16
|
+
1. Call `session_context` with the user's opening request, preserving the actual topic in their words.
|
|
17
|
+
2. Use that returned block as the primary Cortex grounding for the first response.
|
|
18
|
+
3. If `session_context` is unavailable or errors, fall back to `my_context`.
|
|
19
|
+
4. If the conversation materially changes topics later, call `session_context` again for the new topic.
|
|
20
|
+
|
|
21
|
+
## Safety rules
|
|
22
|
+
|
|
23
|
+
- Do not fabricate Cortex context if the tool fails.
|
|
24
|
+
- Prefer the query-centered `session_context` over static `my_context` whenever the user's topic is clear.
|
|
25
|
+
- Do not call `session_context` for every tiny follow-up; refresh only when the topic meaningfully shifts.
|