account-research
Skill4 starsChanged 29 days agoMITView on GitHub
Use before reaching out to a specific company or person - what to find, where to find it, and how to turn it into one relevant angle. Covers company research (news, funding, hiring, tech stack, positioning) and person research (role, posts, background, triggers), the time-box per account tier, and how to avoid the creepy-but-irrelevant trap. Feeds outreach-personalization and cold-email-writing.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- LeadMagic/leadmagic-claude-plugintheir own version, first seen Nov 3, 2026
- RouterGrowth/skillstheir own version, first seen Nov 1, 2026
- desktop-commander/skillstheir own version, first seen Oct 17, 2026
- haroExplorium/sales-skills-for-claude-code-account-researchtheir own version, first seen Oct 15, 2026
- anthropics/knowledge-work-pluginstheir own version, first seen Oct 13, 2026
- akachandan1/proofstacktheir own version, first seen Oct 11, 2026
Used with
Projects with it also use frontend-design.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
BlockSkillfrontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Also in 3 projects that use this
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- anthropics/knowledge-work-plugins★ 35ksame name
- explorium-ai/gtm-skills★ 346same name
- KarlRaf/gtm-starter-kit★ 213same name
- extruct-ai/gtm-skills★ 108same name
- alebgl77/claude-inc★ 21same name
- crustdata/skills★ 11same name
- zime-skills/global★ 8same name
- zime-skills/zime-skills★ 8same name
- desktop-commander/skills★ 4same name
- RouterGrowth/skills★ 2same name
5 more not listed
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 repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- cold-email-writingSkill
- content-marketing-engineSkill
- discovery-and-qualificationSkill
- email-deliverabilitySkill
- generative-engine-optimizationSkill
- gtm-automation-with-chronosSkill
- gtm-strategySkill
- ideal-customer-profileSkill
- lead-sourcing-and-enrichmentSkill
- linkedin-outreachSkill
- multichannel-sequencesSkill
- outbound-metrics-and-benchmarksSkill
- outreach-personalizationSkill
- positioning-and-messagingSkill
- reply-handling-and-objectionsSkill
- seo-fundamentalsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
3
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 20
Trigger-first: start by looking for a recent change (the "why now"), because that's usually your opener.
- Distinctive: line 25
What they do / positioning: - read it in *their* words on their own site.
- Distinctive: line 63
Do look for a trigger event first.
“Common” is measured: kept by at least 6 in 10 of the 12 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
Account research
Overview
Research is the raw material of relevance. The goal isn't a dossier - it's one true, specific angle that makes a cold message land. The skill is knowing what to look for and when to stop, so research doesn't eat the whole day.
Trigger-first: start by looking for a recent change (the "why now"), because that's usually your opener. If you find one, you can often stop there.
Company research - the checklist
- What they do / positioning - read it in their words on their own site.
- Recent news - funding, launches, M&A, expansion, awards, press.
- Hiring - open roles signal priorities and pain (10 SRE roles = scaling pain).
- Tech stack - tools they use (from job posts, BuiltWith-style data, their blog).
- Size & segment - headcount, revenue band, geography (ties to
ideal-customer-profile). - Public pain - reviews, support forums, outages, compliance deadlines.
Person research - the checklist
- Role & tenure - are they the buyer, user, or gatekeeper? New in seat = open to change.
- Recent activity - LinkedIn posts/comments, talks, podcasts (their own words = best).
- Background - past companies, shared history, mutual connections.
- What they signal caring about - themes they post or engage on.
Time-box by tier
Match effort to account value (see ideal-customer-profile):
- A-tier: 5-15 min - find a trigger + their own words + a tailored angle.
- B-tier: ~1 min - one solid research line (recent post, role, company news).
- C-tier: 0 min of 1:1 - use role/industry/stack relevance instead.
Over-researching a C-account is as wrong as under-researching a whale.
Turn research into one angle
Pipe the single best finding into one opener line (handed to
outreach-personalization / cold-email-writing). Signal-to-noise matters: one
sharp, verified observation beats three generic facts. And verify before you
reference - a wrong detail is worse than no personalization.
The creepy line
Relevant-to-their-work = good ("you're hiring SREs → scaling pain"). Personal-but- irrelevant = creepy ("saw your kid's soccer post"). Stay on the work side.
Do / Don't
- Do look for a trigger event first; it's usually the opener.
- Do time-box research to the account's tier.
- Don't reference anything you haven't verified.
- Don't mine personal details that have nothing to do with your value.
Common mistakes
- Research rabbit-holes that produce a dossier and zero sent emails.
- Facts that are true but irrelevant to why they'd buy.
- Referencing a stale or wrong detail (they changed jobs last month).
- Equal effort on every account regardless of fit.
Go live with Chronos (optional)
geo_research- pull structured company/person facts and recent signals.geo_analyze_website- read a target's site for positioning and pain.geo_linkedin_get_prospect_profile/geo_linkedin_list_prospect_posts- their role and their own recent words.geo_enrich_contact- fill firmographic/technographic fields for scoring.
Connect in ~30s → CONNECT-CHRONOS.md. Free, no card.
See also: outreach-personalization, ideal-customer-profile, cold-email-writing.
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.