Account Research
SkillProductivityThis skill lets your AI research companies and people and turn the findings into actionable sales intel. Once added, you can ask about a prospect or account and get information you can act on for sales work. It runs on its own using web search, and gives better results when you connect enrichment tools or your CRM.
Use Account Research in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Account Research and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Account Research skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
After adding it, ask your AI something like research [company] or look up [person] to pull your first round of sales intel. If you use a CRM or enrichment tools, connect them so results go deeper.
What your AI can do with it
- Research a company and get actionable sales intel
- Look up a person or prospect and learn who they are
- Answer questions like who is [name] at [company]
- Give a rundown on a company when you say tell me about [company]
- Work from web search alone, with nothing else connected
- Deliver richer results when enrichment tools or your CRM are connected
What this skill tells your AI
The instructions your AI receives, as published by navinspire-ia/navin in navin/skills/account-research/SKILL.md and read by Ahel’s review.
Walk into every meeting knowing more about their context than they expect. Timebox research; separate facts from hypotheses.
When to use
- Before discovery calls, demos, or strategic meetings
- Deep-dive on a single target account
When not to use
- Bulk list building (
lead-prospector) - Presenting hypotheses as facts to the prospect
The account sheet
## Account - <Company> (<date>)
### Company
- What they do (their words) - size, geography, structure
- Business model & who THEIR clients are
- Recent news: funding, projects, expansions, incidents (URL + date)
### People (per attendee)
- Role, tenure, background, recent public statements
- Likely personal win from this project
### Signals
- Tech stack hints (site, job postings)
- Hiring patterns → priorities
- Public tenders / projects when relevant
### Hypotheses (to verify in meeting)
- Top 3 likely pains with evidence
- Budget/timing signals
### Angles
- Openers & smart questions
- Relevant references/cases of ours
- Risks (incumbent? bad history?)
Sources
web_fetch site (about, news, careers) · web_search news + hiring · public profiles · reviews · tender platforms · entity-research · buying-signals.
Workflow
- Timebox: 15 min routine / 45 min big meeting / half-day strategic.
- Fill the sheet; tag every claim with source URL or
unverified. - Store
sales/accounts/<company>/research.md; brief top 5 points in chat. - After the meeting: update via discovery notes - the sheet lives.
Rules
- Public sources only.
- Hypotheses are for the meeting to test - never sell them as facts.
- Prefer recent evidence (<90 days) for timing claims.
Anti-patterns
- Wall of unstructured browser notes
- Invented org charts
Signals
- GitHub stars
- 36
- Forks
- 4
- Last commit
- Oct 2026
Advanced
- Item type
- skill
- Key
account-research- Source
- github.com/navinspire-ia/navin
github.com/navinspire-ia/navin