Linkedin First Dm
Write the first DM under 150 characters once a connection is accepted, two variants, value-first and asking for nothing. Use right after a target accepts your request.
Install
$ agentstack add skill-styfinity-linkedin-engine-linkedin-first-dm ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-styfinity-linkedin-engine-linkedin-first-dm) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
LinkedIn First DM
The accept is not the win, the conversation is. This skill writes the opener that earns a reply without asking for anything.
Inputs
- The accepted target and the hook that connected you (a post, a comment thread, a mutual, a shared signal): $ARGUMENTS
- The brief (persona tone, pains, offer) loads automatically.
Do this
Write two first-DM variants so the operator can pick:
- Variant A - value-first. Reference the real hook, give one genuine, specific observation about their world, then end on an open question.
- Variant B - genuinely curious. Lead with curiosity about something specific to them, no observation needed, then end on a different open question.
Both must be UNDER 150 characters. Count every character. Ask for nothing: no call, no offer, no link, no pitch. End each on an open question they would actually want to answer.
Output
Variant A and Variant B, each labelled with its exact character count. After both, a one-line note: stop-on-reply (do not send a follow-up until they reply). If the operator wants the message smoothed before sending, run /linkedin-humanizer on the draft. When replies land, hand them to /linkedin-reply-triager.
Rules
- Under 150 characters, counted and shown. If over, cut and recount.
- No ask, no pitch, no link. Value or curiosity only.
- Every variant ends on an open question about their world.
- No em-dashes, no exclamation marks, no "hope you're well", no "I came across your profile".
- Reads like a text from a peer, references one real, specific hook.
- Draft only. Claude drafts, the operator approves. Nothing is sent without explicit approval, and sending happens only through the connected CLI/MCP layer wired to your own LinkedIn session or a provider key, hard-capped at 20 actions per day for new accounts.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: styfinity
- Source: styfinity/linkedin-engine
- License: MIT
- Homepage: https://styfinity.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.