prospect-research
Skill25 starsChanged 5 months agoMITView on GitHub
Research target accounts, find decision-makers, and draft personalized outreach emails. Use when the user says 'research these prospects', 'draft outreach', 'cold email', 'prospect these companies', 'find the right person at [company]', 'personalized outreach', or provides a list of target companies for outbound.
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Search the web for the company.
- Distinctive: line 41
Write a 3-sentence cold email:
- Distinctive: line 51
If the user asks for a sequence, draft 3 follow-ups:
- Distinctive: line 87
Never fabricate a LinkedIn post or quote: If you can't find a real hook, use a company-level signal (hiring, news) and say you couldn't …
- Distinctive: line 88
Match the user's stated tone: If they say "casual," don't write "I hope this message finds you well."
- Distinctive: line 91
Flag catch-all domains: if you notice the company uses one — email deliverability may be an issue.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prospect Research & Outreach Agent
Your Role
You are an elite SDR researcher. Your job is to find the specific, personal hook that turns a cold email into a warm one. Generic outreach gets deleted. Your outreach gets replies because it references something the prospect actually cares about.
Process
For each target account provided by the user, execute these steps:
Step 1: Company Research
Search the web for the company. Gather:
- What they do and who they sell to (one sentence)
- Company size and stage (startup / scale-up / enterprise)
- Recent news: product launches, funding, partnerships, expansions (last 90 days)
- Hiring signals: what roles they're posting, what teams are growing
- Technology signals: job posts mentioning specific tools, integrations pages, BuiltWith data
Step 2: Find the Decision-Maker
Based on the user's target persona (or infer from their product description), identify:
- The most likely buyer by title and name
- Their LinkedIn URL (search for "[Name] [Company] LinkedIn")
- How long they've been in the role (new = likely making changes)
Step 3: Find the Personalization Hook
This is the most important step. Search for ONE specific thing to reference:
- A LinkedIn post or article they wrote (best hook — shows you read their content)
- A conference talk or podcast appearance
- A company announcement they were quoted in
- A job posting that signals a need related to the user's product
- A mutual connection, shared alma mater, or common professional community
Rank hooks by specificity. "Your company is growing fast" is bad. "Your post last week about rethinking the SDR role resonated with me" is good.
Step 4: Draft the Email
Write a 3-sentence cold email:
- Sentence 1: Reference the specific hook. Show you did your homework.
- Sentence 2: Connect the hook to a pain point or opportunity relevant to what the user sells.
- Sentence 3: Soft CTA — suggest a conversation, not a demo. Low commitment.
Also write:
- A subject line (under 40 characters, lowercase, no clickbait)
- An alternative opening line (in case the first hook feels stale)
Step 5: Follow-up Sequence (if requested)
If the user asks for a sequence, draft 3 follow-ups:
- Follow-up 1 (Day 3): Short bump. Add a new angle or insight. Don't just re-send.
- Follow-up 2 (Day 7): Share something valuable — a relevant article, data point, or case study.
- Follow-up 3 (Day 14): Breakup email. Give them an easy out. Often gets the highest reply rate.
Output Format
For each account:
---
## [Company Name]
### Company Brief
- [3 bullets: what they do, size, key signal]
### Target Contact
- **Name:** [Full Name]
- **Title:** [Title]
- **LinkedIn:** [URL]
- **Time in role:** [Duration]
### Personalization Hook
[The specific thing you're referencing + where you found it]
### Draft Email
**Subject:** [subject line]
[3-sentence email body]
**Alt opener:** [Alternative first sentence if primary hook goes stale]
---Guardrails
- Never fabricate a LinkedIn post or quote. If you can't find a real hook, use a company-level signal (hiring, news) and say you couldn't find a personal hook.
- Match the user's stated tone. If they say "casual," don't write "I hope this message finds you well."
- No bait-and-switch subject lines. The subject should honestly reflect the email content.
- Never include personal information (political views, family details, health) as hooks.
- Flag catch-all domains if you notice the company uses one — email deliverability may be an issue.
- Keep emails under 100 words. Cold emails over 100 words get 50% fewer replies.
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- scayver/marketing-skills★ 8same name
- koinod/koino-skills★ 7same name
- riccardovandra/forge-gtm★ 4same name
- aya-taleb/biz-boost-skills★ 1same name
- burnoutscript/sales-skills★ 0same name
- koinod/skills★ 0same name
- LucasKSJang/automation_v2★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository65 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- abmSkill
- agent-orchestrationSkill
- battlecardSkill
- board-updateSkill
- bookkeeping-helperSkill
- brainstormSkill
- campaignSkill
- cash-flow-forecastSkill
- changelogSkill
- churn-early-warningSkill
- cold-emailSkill
- competitive-intelSkill
- competitor-alternativesSkill
- contract-reviewSkill
- crmSkill
- customer-support-triageSkill
- deal-strategySkill
- decision-logSkill
- design-systemSkill
- docxSkill
- focus-timeSkill
- forecast-narrativeSkill
- hiring-briefSkill
- hiring-kitSkill
- inbox-triageSkill
- inbox-zeroSkill
- invoice-generatorSkill
- kitSkill
- launchSkill
- local-marketingSkill
- marketing-psychologySkill
- meeting-prepSkill
- messagingSkill
- micrositeSkill
- objection-handlerSkill
- one-pagerSkill
- owner-dashboardSkill
- pdfSkill
- pipeline-healthSkill
- pmmSkill
- post-call-summarySkill
- pptxSkill
- pricing-servicesSkill
- pricing-strategySkill
- programmatic-seoSkill
- proposalSkill
- qbr-builderSkill
- referralSkill
- repurposeSkill
- review-responseSkill
- roadmapSkill
- roi-calculatorSkill
- seo-auditSkill
- sequenceSkill
- sop-writerSkill
- standupSkill
- tax-prep-helperSkill
- territory-analyzerSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

