Need help implementing this on your team?
We'll install the skills, customize them to your workflow, and run the output through your team's combined LinkedIn network. Skills do the research, Linkd does the motion.
Live
Research
Pre-call prep
Pre-call briefings on any account, anchored to real sources.
Drop a company name or URL. Get a structured Markdown brief: company snapshot, signals from the last 90 days, key people, tech stack, and conversation hooks. Every claim traces back to a source with a date.
A brief you can actually use.
Most pre-call docs read like the company's About page rewritten. This skill is built for the opposite job: surface what a salesperson would miss in 20 minutes of focused research, and tell them where the evidence is thin.
It accepts a company name, a domain, a LinkedIn URL, or all three plus context about the meeting. It pulls signals from the company's own site, recent news (last 90 days), funding databases, job boards, and LinkedIn. Every claim that lands in the brief has a date and a source URL attached.
The output is a 2 to 3 minute read. Tldr at the top, six structured sections, a "what I could not find" section at the bottom that's required, not optional.
Any of these will work.
Research Acme Corp. I have a demo with their VP RevOps next Tuesday.
Give me a brief on stripe.com. Cold outreach, pitching dev tools.
Prep me for a meeting with Globex. Selling a security platform.
Background on this company before my call: snowflake.com
Five steps. Honest at every one.
01
Confirm the target
Resolves ambiguous names (Apex could be six companies), asks briefly about meeting context if not given.
02
Gather signals
Parallel research across news, funding, leadership changes, hiring, tech stack, financial signals if public.
03
Filter by date
Strict 90-day window for "recent" claims. A 2-year-old funding round is not news. Stale signals get cut.
04
Cluster into sections
Company snapshot, recent signals, key people, tech, pain signals, conversation hooks. Each hook tied to a specific signal.
05
Emit the brief
Clean Markdown file with tldr at top, confidence notes at bottom, and an explicit list of what could not be found.
Built around the things that usually go wrong.
!
Never invents names or signals
If the buyer's name isn't visible on LinkedIn, the brief says "VP RevOps, name not found via public search." No pattern-matched guesses.
@
Date filtering is strict
A 2024 funding round in a 2026 brief is not "recent." Anything outside the 90-day window is treated as background, not signal.
?
Conversation hooks must be anchored
Every hook ties to a specific signal in the brief. No "saw you've been busy lately" filler. If a hook has no anchor, it gets cut.
×
Gaps are surfaced, not hidden
Every brief ends with "what I could not find." That tells you where to fill in from your own knowledge before the call.
A scannable Markdown briefing.
The brief is structured so you can read top-to-bottom in 2 to 3 minutes before a call, or jump to one section if you only need that. Every section that contains claims also contains source URLs.
Sample structure
# Account Brief: Acme Corp
Prepared: 2026-05-21
## TL;DR
- 3 to 5 bullets you'd whisper before the call
## 1. Company snapshot
## 2. Recent signals (last 90 days)
## 3. Key people
## 4. Tech & product signals
## 5. Pain & opportunity signals
## 6. Conversation hooks
## What I could NOT find
- Specific RevOps team structure
- Current ARR (not public)
Brief contract
- Output
- Markdown (.md)
- Read time
- 2 to 3 minutes
- Signal window
- Last 90 days
- Required tools
- web_search, web_fetch
- Source anchors
- Every claim
- Time to produce
- 5 to 15 searches
Pick your Claude. Drop in the skill.
The download is a zip containing two things: the .skill file (what you upload to Claude) and a SKILL.md sidecar (the human-readable instructions). Unzip first, then follow the steps for your Claude.
⌘
Most people
Claude.ai or Desktop
- Download and unzip the bundle.
- Open or create a Project in Claude.
- Go to Project knowledge, click Add content.
- Upload the
.skillfile from the unzipped bundle. - Start a new chat in that project. Ask it to run the skill.
Download bundle ↓
No restart needed
›_
Developers
Claude Code
- Download and unzip the bundle.
- Unzip the inner
.skillfile too (it's also a zip). - Move the resulting folder into
~/.claude/skills/ - Restart Claude Code.
- Type a prompt that fits the trigger. The skill loads automatically.
Download bundle ↓
macOS / Linux / WSL
{ }
Builders
API or Agent SDK
- Download and unzip the bundle.
- Open the SKILL.md sidecar to read the full instructions.
- Load via the Skills API, or paste the instructions into your agent's system prompt.
- Make sure your agent has
web_searchand file output enabled. - Ship it.
View SKILL.md ↓
v1.0
Read the full instructions.
This is exactly what Claude reads when the skill triggers. No hidden prompts, no separate config. What you see here is what you get.
account-research-brief-SKILL.md
⌄
account-research-brief-SKILL.md
Loading SKILL.md...