Skip to content
Agentmart
Submit a tool

message-connections

Message qualified connections from the ICP Connections list.

Skill by Kasper-AI

IndexedMIT
Write a review

Chalk Labs

Need help deploying message-connections?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kasper-ai-message-connections

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Message qualified connections from the ICP Connections list. Use when user says "message connections", "message qualified connections", "work through connection list", or "DM my connections".

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/message-connections

What's inside

Skill name
message-connections
Description
Message qualified connections from the ICP Connections list. Use when user says "message connections", "message qualified connections", "work through connection list", or "DM my connections".
License
MIT
Instructions
31 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: references/api.md, references/storage.md

Files (1)

  • SKILL.md

SKILL.md (first lines)

## Browser Preflight (MANDATORY — do this FIRST)

Before delegating to any agent, attach the Claude Chrome extension to this session:

1. Tell the user in chat:
   > "I need browser access to LinkedIn. You may see a permission prompt — please approve it. I'll wait."
2. Navigate to `https://www.linkedin.com/feed/` using the Browser tool. This triggers Claude's permission system and attaches the Chrome extension to the session.
3. Confirm the LinkedIn feed page loaded (content visible, not an error/login wall). If it fails, tell the user the extension isn't connected and stop — do NOT delegate to the agent.

If LinkedIn already loaded earlier in this session, this step passes instantly.

Delegate to the **outreach** agent in **message-connections mode**:

- Read ICP connections: **Pro plan** — fetch from API via browser tab using `references/api.md` (`/v1/gtm/connections?status=new&icp_tier=1`); **Basic plan** — read from the "ICP Connections" tab in the user's spreadsheet
- Filter to Status = "New" (skip already messaged or skipped)
- For each connection:
  1. Check `messages-sent.json` — skip if already messaged
  2. Run the **Mandatory Message History Check** (see outreach agent) — skip if they fail the history rules
  3. Research their profile (brief — they're already ICP-qualified)
  4. Check existing LinkedIn message thread — if prior conversation exists, frame as follow-up
  5. Draft contextual DM following the 3-paragraph message structure
- Present messages one-by-one or as a clearly enumerated batch for user approval (Approve / Edit / Skip), including during `run-all`
- Update status to "Messaged" after sending — sync per `references/storage.md`
- Log all messages to agent memory (`messages-sent.json` with method "ConnectionListDM") and sync per `references/storage.md` using the canonical dashboard `lead_id` resolved from the matched lead (`id`, `_id.$oid`, then `original_id`), not a LinkedIn slug
- If a connection must be added as a lead first, sync/fetch the lead first, then write or sync the message
- Save `last-run-connections-list.json` with current timestamp
- Report: "{n} DMs sent, {m} skipped, {remaining} still in queue"

Rate limits: max 40-50 messages per day. Batch in groups of 15-20, pause between batches.

From Kasper-AI/gtm-kit-plugin, MIT.

More from Kasper-AI/gtm-kit-plugin

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 12, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Kasper-AI

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get message-connections running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying message-connections?

CallGet help
Cite this page

message-connections skill. Agent Mart. https://agentmart.dev/skills/kasper-ai-message-connections (last updated 2026-10-24)