@vruum/skills 0.4.12 → 0.4.13
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
CHANGED
|
@@ -6,29 +6,54 @@ Pairs with the Vruum MCP server at [https://api.vruum.ai/mcp](https://api.vruum.
|
|
|
6
6
|
|
|
7
7
|
## Install
|
|
8
8
|
|
|
9
|
-
### Claude Code
|
|
9
|
+
### Claude Code
|
|
10
10
|
|
|
11
|
-
Add
|
|
11
|
+
Add to `~/.claude.json`:
|
|
12
12
|
|
|
13
|
-
```
|
|
14
|
-
|
|
13
|
+
```json
|
|
14
|
+
{
|
|
15
|
+
"mcpServers": {
|
|
16
|
+
"vruum-local": { "type": "http", "url": "https://api.vruum.ai/mcp" }
|
|
17
|
+
}
|
|
18
|
+
}
|
|
15
19
|
```
|
|
16
20
|
|
|
17
|
-
|
|
21
|
+
Slash commands appear automatically once registered. You don't need this npm package for Claude Code.
|
|
18
22
|
|
|
19
|
-
|
|
23
|
+
### Codex CLI
|
|
20
24
|
|
|
21
|
-
|
|
25
|
+
Add to `~/.codex/config.toml`:
|
|
22
26
|
|
|
23
|
-
|
|
27
|
+
```toml
|
|
28
|
+
[mcp_servers.vruum-local]
|
|
29
|
+
url = "https://api.vruum.ai/mcp"
|
|
30
|
+
```
|
|
24
31
|
|
|
25
|
-
|
|
32
|
+
Then run this installer to bring the skill bundle into your Codex skills directory:
|
|
26
33
|
|
|
27
34
|
```bash
|
|
28
35
|
npx @vruum/skills install
|
|
29
36
|
```
|
|
30
37
|
|
|
31
|
-
Detects
|
|
38
|
+
Detects `~/.codex/skills/` automatically. For other harnesses without a known path:
|
|
39
|
+
|
|
40
|
+
```bash
|
|
41
|
+
npx @vruum/skills install --target /path/to/skills/dir
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
### Cursor / VS Code Copilot / Cline
|
|
45
|
+
|
|
46
|
+
Register the MCP server via your editor's MCP setup (each one has its own UI / config path). Connect to `https://api.vruum.ai/mcp` (HTTP, OAuth via standard MCP flow). Skills surface as slash commands automatically — you don't need this npm package.
|
|
47
|
+
|
|
48
|
+
### Claude Desktop / Claude.ai (Cowork)
|
|
49
|
+
|
|
50
|
+
Install the Vruum plugin via the official plugin directory — bundles the connector and slash commands in one step:
|
|
51
|
+
|
|
52
|
+
[github.com/vruum-gtm/skills/releases/latest/download/vruum-plugin.zip](https://github.com/vruum-gtm/skills/releases/latest/download/vruum-plugin.zip)
|
|
53
|
+
|
|
54
|
+
Download and upload via **Settings → Customize → Plugins → "+"**.
|
|
55
|
+
|
|
56
|
+
### ChatGPT / Windsurf / other harnesses without MCP prompts
|
|
32
57
|
|
|
33
58
|
```bash
|
|
34
59
|
npx @vruum/skills install --target /path/to/skills/dir
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@vruum/skills",
|
|
3
|
-
"version": "0.4.
|
|
3
|
+
"version": "0.4.13",
|
|
4
4
|
"description": "Vruum AI skills for Claude Code, Claude Desktop, Codex CLI, and any AI assistant with a skill directory. Slash commands for outreach triage, engagement triage, pipeline filling, prospect enrichment, and reply diagnosis. Pairs with the Vruum MCP server at https://api.vruum.ai/mcp.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"repository": {
|
|
@@ -36,5 +36,5 @@
|
|
|
36
36
|
"outreach",
|
|
37
37
|
"gtm"
|
|
38
38
|
],
|
|
39
|
-
"contentHash": "
|
|
39
|
+
"contentHash": "a3981e97abb16b2688efd1fc76f8565288dd9006aea5d1a200a6bb8f9561f874"
|
|
40
40
|
}
|
|
@@ -38,7 +38,7 @@ Reviewing inline burns tokens fast. Subagents with their own context windows do
|
|
|
38
38
|
|
|
39
39
|
This skill dispatches the `vruum-engagement-reviewer` subagent (bundled at `agents/vruum-engagement-reviewer.md`). That agent reviews both engagement items AND content posts.
|
|
40
40
|
|
|
41
|
-
**Dispatch via
|
|
41
|
+
**Dispatch a subagent of role `vruum-engagement-reviewer`** via your runtime's native subagent mechanism (Claude Code's `Agent` tool with `subagent_type`; Codex's equivalent). Supports `run_in_background=true` for parallelism.
|
|
42
42
|
|
|
43
43
|
Falls back to general-purpose subagent with MCP tool names in the prompt if the subagent type isn't recognized.
|
|
44
44
|
|
|
@@ -30,7 +30,7 @@ This skill uses the custom agent `vruum-outreach-reviewer` (bundled at `agents/v
|
|
|
30
30
|
- Web search for prospect research
|
|
31
31
|
- Complete review instructions baked into its system prompt
|
|
32
32
|
|
|
33
|
-
**Dispatch via
|
|
33
|
+
**Dispatch a subagent of role `vruum-outreach-reviewer`** via your runtime's native subagent mechanism (Claude Code's `Agent` tool with `subagent_type`; Codex's equivalent). Supports `run_in_background=true` for parallelism. Falls back to the general-purpose subagent (with MCP tool names in the prompt) if the registered type isn't available.
|
|
34
34
|
|
|
35
35
|
For small queues (5 or fewer) or when subagents can't access MCP, review directly in the main session.
|
|
36
36
|
|
|
@@ -41,7 +41,7 @@ Before any other Step 3 work, call `get_research_playbook(segment_id=<id>)`. If
|
|
|
41
41
|
|
|
42
42
|
> Vruum MCP not configured as a user-scoped server. Run:
|
|
43
43
|
>
|
|
44
|
-
> `
|
|
44
|
+
> Register the Vruum MCP server in your assistant once: Claude Code → `~/.claude.json` `mcpServers.vruum-local = {"type":"http","url":"https://api.vruum.ai/mcp"}`; Codex CLI → `~/.codex/config.toml` `[mcp_servers.vruum-local]` with `url = "https://api.vruum.ai/mcp"`; other assistants → connect to `https://api.vruum.ai/mcp` (HTTP, OAuth via standard MCP flow).
|
|
45
45
|
>
|
|
46
46
|
> and retry. (The cloud `claude.ai Vruum` connector doesn't propagate to subagents — they need `vruum` configured at the user scope in `~/.claude.json`.)
|
|
47
47
|
|
|
@@ -43,19 +43,19 @@ This skill uses two subagents (defined in `.claude/agents/`):
|
|
|
43
43
|
|
|
44
44
|
### MCP access requirements (load-bearing)
|
|
45
45
|
|
|
46
|
-
Subagents
|
|
46
|
+
Subagents need access to the Vruum MCP server. Register it once in your AI assistant:
|
|
47
47
|
|
|
48
|
-
|
|
48
|
+
- **Claude Code**: `~/.claude.json` → `mcpServers.vruum-local` = `{"type": "http", "url": "https://api.vruum.ai/mcp"}`
|
|
49
|
+
- **Codex CLI**: `~/.codex/config.toml` → `[mcp_servers.vruum-local]` with `url = "https://api.vruum.ai/mcp"`
|
|
50
|
+
- **Other**: connect to `https://api.vruum.ai/mcp` (HTTP, OAuth via standard MCP flow)
|
|
49
51
|
|
|
50
|
-
The orchestrator's MCP precheck at the top of Step 3 (`get_research_playbook` call) catches
|
|
52
|
+
The orchestrator's MCP precheck at the top of Step 3 (`get_research_playbook` call) catches misconfiguration upfront. Don't skip it.
|
|
51
53
|
|
|
52
54
|
### Dispatch methods (in order of preference)
|
|
53
55
|
|
|
54
|
-
1. **
|
|
56
|
+
1. **Subagent dispatch** (primary): Use your runtime's native subagent mechanism (Claude Code's `Agent` tool with `subagent_type: vruum-company-deep-researcher` / `vruum-prospect-deep-researcher`; Codex's equivalent). Subagents should inherit MCP access from the runtime config. Run waves of up to 10 company-research subagents and up to 5 prospect-research subagents in parallel.
|
|
55
57
|
|
|
56
|
-
2. **
|
|
57
|
-
|
|
58
|
-
3. **Inline**: For very small fills (1–3 prospects) where dispatching subagents is overhead, run the research inline in the main session.
|
|
58
|
+
2. **Inline**: If subagents can't reach Vruum MCP in your runtime, run the research inline in the main session instead. Do NOT bounce through another CLI as a workaround — that is a runtime-configuration problem to surface to the user.
|
|
59
59
|
|
|
60
60
|
## Inputs
|
|
61
61
|
|