@vruum/skills 0.4.5 → 0.4.6

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.
@@ -2,13 +2,13 @@
2
2
  name: vruum-engagement-reviewer
3
3
  description: Reviews engagement queue items (LinkedIn comments, reactions, content posts) using Vruum MCP tools. Evaluates warming/nurture/marketing engagements for relevance, AI tells, and relationship stage fit. Also reviews demand gen content posts.
4
4
  mcpServers:
5
- - vruum-local
5
+ - vruum
6
6
  tools:
7
- - mcp__vruum-local__get_engagement_review
8
- - mcp__vruum-local__manage_engagement
9
- - mcp__vruum-local__get_content_review
10
- - mcp__vruum-local__manage_content_post
11
- - mcp__vruum-local__get_person_360
7
+ - mcp__vruum__get_engagement_review
8
+ - mcp__vruum__manage_engagement
9
+ - mcp__vruum__get_content_review
10
+ - mcp__vruum__manage_content_post
11
+ - mcp__vruum__get_person_360
12
12
  - WebSearch
13
13
  - WebFetch
14
14
  ---
@@ -2,16 +2,16 @@
2
2
  name: vruum-outreach-reviewer
3
3
  description: Reviews and edits outreach messages using Vruum MCP tools. Evaluates drafts for cross-touch deduplication, AI tells, personalization depth, and strategic fit. Edits messages that need improvement and returns structured summaries.
4
4
  mcpServers:
5
- - vruum-local
5
+ - vruum
6
6
  tools:
7
- - mcp__vruum-local__get_outreach_review
8
- - mcp__vruum-local__edit_message
9
- - mcp__vruum-local__search_knowledge_base
10
- - mcp__vruum-local__get_person_research
11
- - mcp__vruum-local__get_person_360
12
- - mcp__vruum-local__get_company_research
13
- - mcp__vruum-local__fetch_company_website
14
- - mcp__vruum-local__fetch_linkedin_data
7
+ - mcp__vruum__get_outreach_review
8
+ - mcp__vruum__edit_message
9
+ - mcp__vruum__search_knowledge_base
10
+ - mcp__vruum__get_person_research
11
+ - mcp__vruum__get_person_360
12
+ - mcp__vruum__get_company_research
13
+ - mcp__vruum__fetch_company_website
14
+ - mcp__vruum__fetch_linkedin_data
15
15
  - WebSearch
16
16
  - WebFetch
17
17
  ---
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@vruum/skills",
3
- "version": "0.4.5",
3
+ "version": "0.4.6",
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": "b0e043a4560fc5d2eda1f7238a08f58d8d1865c97b28442574d6c509eb74e53a"
39
+ "contentHash": "28af9e4aee5505f827ad6b3214802864de70bc90d554d3f9407df5bc38bdc1fa"
40
40
  }
@@ -31,15 +31,15 @@ This skill uses the custom agent `vruum-pipeline-filter` defined at `~/.claude/a
31
31
 
32
32
  ### MCP access requirements
33
33
 
34
- Subagents can only access Vruum MCP if `vruum-local` is configured as a user-scoped HTTP MCP server in `~/.claude.json`. Cloud MCP servers (`claude.ai Vruum`) are NOT inherited by subagents.
34
+ Subagents can only access Vruum MCP if `vruum` is configured as a user-scoped HTTP MCP server in `~/.claude.json`. Cloud MCP servers (`claude.ai Vruum`) are NOT inherited by subagents.
35
35
 
36
- To set up: `claude mcp add --transport http --scope user vruum-local https://api.vruum.ai/mcp` (one-time, requires OAuth).
36
+ To set up: `claude mcp add --transport http --scope user vruum https://api.vruum.ai/mcp` (one-time, requires OAuth).
37
37
 
38
38
  ### Dispatch methods (in order of preference)
39
39
 
40
40
  1. **Agent tool** (primary): Spawn subagents via the Agent tool. Subagents inherit local MCP servers from `~/.claude.json` and can call Vruum tools directly. Use `run_in_background=true` for parallelism.
41
41
 
42
- 2. **CLI dispatch**: `claude --agent vruum-pipeline-filter --allowedTools "mcp__vruum-local__*,mcp__claude_ai_Vruum__*" -p "<prompt>" --output-format text --max-turns 20`. Use if Agent tool subagents can't reach MCP.
42
+ 2. **CLI dispatch**: `claude --agent vruum-pipeline-filter --allowedTools "mcp__vruum__*,mcp__claude_ai_Vruum__*" -p "<prompt>" --output-format text --max-turns 20`. Use if Agent tool subagents can't reach MCP.
43
43
 
44
44
  3. **Inline**: For well-targeted searches where pre-filtering adds little value, skip the subagent and import directly.
45
45
 
@@ -129,4 +129,4 @@ Before dispatching subagents, group segment fills by their saved search ID. With
129
129
  - The 5-minute cooldown on automated pipeline fills prevents duplicate imports if the skill runs twice in quick succession.
130
130
  - Pre-filtering saves ~$0.10-0.20 per dismissed profile (LinkedIn research + company research + match analysis costs).
131
131
  - If a search returns fewer profiles than needed, flag it as "drying up" so the user knows to create a new search or broaden targeting.
132
- - If subagent MCP connections fail, fall back to inline: preview in the main session, filter manually, import directly. This typically means `vruum-local` isn't in `~/.claude.json`.
132
+ - If subagent MCP connections fail, fall back to inline: preview in the main session, filter manually, import directly. This typically means `vruum` isn't in `~/.claude.json`.