Skip to main content
skill CX Codex official · Anthropic

account-research · anthropics, common-room — Claude Code skill: what it does, how to install

account-research — a skill for Claude Code and Codex that pulls company intelligence from Common Room. Activates on research requests, domain queries, and account signal lookups.

Apache-2.0 ★ 36,654 updated 2026-10-24

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add anthropics/knowledge-work-plugins
/plugin install common-room@knowledge-work-plugins
Open on GitHub

What account-research does

The skill retrieves company information from Common Room using a domain or business name. It begins by loading the user's Me profile to default lookups to their assigned territory segments. Processing follows four scenarios: complete company briefs, single-field direct answers, scarce data handling, or reasoning against ideal customer profile criteria.

Web search runs only when Common Room records lack details or when recent news is explicitly requested, scoped to the past 30 days. Scores stay as raw numeric values or percentiles rather than qualitative tags. Every stated fact links directly to tool results, omitting empty sections without guesswork.

Running this skill requires configured Common Room MCP tools and account access.

What it helps with

  • pull structured company overviews with CRM metrics
  • check buying signals and activity spikes for an account
  • identify account owners and key contacts by company domain

Example prompts for the agent

  • Tell me about datadog.com
  • Who owns the Snowflake account?
  • Pull up signals for notion.so

How to install account-research

1Plugin marketplace

/plugin marketplace add anthropics/knowledge-work-plugins
/plugin install common-room@knowledge-work-plugins

This installs the whole common-room plugin with all its skills

2Skills CLI (Vercel)

npx skills add anthropics/knowledge-work-plugins --skill account-research -a claude-code

3Manually: put the files in place

~/.claude/skills/account-research/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/account-research/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about account-research

How to install account-research in Claude Code?

Register the marketplace using /plugin marketplace add anthropics/knowledge-work-plugins, then run /plugin install common-room@knowledge-work-plugins.

What does account-research do?

It queries Common Room for account details, pulling ownership, scores, top contacts, and RoomieAI summaries while falling back to web search when data is sparse.

What is required to run account-research?

You need an active Common Room integration exposing MCP endpoints so the assistant can authenticate and query account fields.

Source text

SKILL.md · Apache-2.0
---
name: account-research
description: "Research a company using Common Room data. Triggers on 'research [company]', 'tell me about [domain]', 'pull up signals for [account]', 'what's going on with [company]', or any account-level question."
---

# Account Research

Retrieve and synthesize account information from Common Room. Handles four interaction patterns: full overviews, targeted field questions, sparse data situations, and combined MCP data + LLM reasoning.

## Step 0: Load User Context (Me)

Before researching any account, fetch the `Me` object from Common Room. This provides:
- The user's profile, title, role, and Persona in CR
- The user's segments ("My Segments")

Default all queries to the user's own segments unless the user explicitly asks for a broader view. This keeps results scoped to their territory.

## Step 1: Identify the Interaction Pattern

Determine what the user actually needs before deciding how much data to fetch:

**Pattern 1 — Full Overview:** "Tell me about Datadog" / "Summarize cloudflare.com"
→ Fetch the full field set and produce a structured briefing.

**Pattern 2 — Targeted Question:** "Who owns the Snowflake account?" / "Is acme.io showing buying signals?" / "What's the employee count for notion.so?"
→ Fetch only the relevant field(s). Return a direct, concise answer — do not produce a full brief for a simple question.

**Pattern 3 — Sparse Data:** "Tell me about tiny-startup.io"
→ If Common Room has limited data for an account, say so honestly: "There is limited information available for this account." Never speculate or fill gaps with generic statements.

**Pattern 4 — Combined Reasoning:** Fetch structured MCP data, then layer in LLM analysis — e.g., "Stripe has 8,000 employees and is hiring heavily for AI roles. Based on your ICP of 1k–10k fintech companies, this is a strong fit."

## Step 2: Look Up the Account

Search Common Room for the account by domain or company name. Exact match first; if no result, try partial match and confirm with the user before proceeding.

## Step 3: Fetch the Right Fields

Use the Common Room object catalog to see available field groups and their contents. For full overviews, request all field groups. For targeted questions, request only what's relevant.

**Key field groups to know about:**
- **Scores** — always return as raw values or percentiles, never labels
- **Summary research** — RoomieAI output; often the richest qualitative signal
- **Top contacts** — sorted by score desc; use communityMemberID for full lookups

**Choosing what to fetch:**

| User query type | Fields to request |
|-----------------|------------------|
| Full account overview | All field groups |
| "Who owns this account?" | Company profiles & links, CRM fields |
| "Is this company a good fit?" | Key fields, scores, about |
| "What signals is this account showing?" | Scores, summary research, CRM fields |
| "Who are the top contacts?" | Top contacts |
| "What does RoomieAI say about them?" | Summary research, all research |
| "Find engineers at this account" | Prospects (with title filter) |

## Step 4: Web Search (Sparse Data Only)

Common Room is the primary data source. Do not run web search when CR returns rich data.

When CR data is sparse (Pattern 3 — few fields returned, no activity, no scores), run a targeted web search to fill gaps:
- `"[company name]" news` — scoped to the last 30 days
- Look for: funding rounds, acquisitions, product launches, executive changes, press coverage

If the user explicitly asks for external context or recent news, run web search regardless of data richness.

## Step 5: Apply Reasoning (Pattern 4)

When the user's question invites synthesis — not just data retrieval — layer in analysis:
- Compare account data to known ICP criteria from session context
- Identify fit signals (size, industry, tech stack, hiring patterns)
- Note timing signals (funding, trial status, recent activity spike)
- Frame insights as clearly derived from data, not assumed

When the user's company context is available (see `references/my-company-context.md`), position findings relative to the user's value proposition and ICP.

## Step 6: Produce Output

Only include sections where Common Room returned actual data. Omit sections entirely rather than filling them with guesses.

**Full overview (when data is rich):**

```
## [Company Name] — Account Overview

**Snapshot**
[2–3 sentences: what they do, plan/stage, relationship status]

**Key Details**
[Employee count, industry, location, domain, funding — from key fields]

**CRM & Ownership** [If CRM fields returned]
[Owner, opp stage, ARR]

**Scores** [If scores returned]
[All available scores as raw values or percentiles]

**Signal Highlights** [If activity/signals exist]
[3–5 most important signals with dates]

**Top Contacts** [If contacts returned]
[Name | Title | Score — top 5 sorted by score desc]

**RoomieAI Research** [If summary research is non-null]
[Summary research output; list all available research topic names]

**Recommended Next Steps**
[2–3 specific, signal-backed actions]
```

**Targeted question:** 1–3 sentence direct answer. No full brief needed.

**Sparse data (few fields returned, most sections would be empty):**

```
## [Company Name] — Account Overview (Limited Data)

**Data available:** [List exactly what Common Room returned]

[Present only the returned fields]

**Web Search**
[Findings from web search — or "No significant recent news found"]

**Note:** Common Room has limited data on this account. The account may need enrichment in Common Room.
```

## Quality Standards

- Scores must always be raw values or percentiles — never categorical labels
- For targeted questions, answer precisely and don't over-deliver
- Be explicit when data is missing or stale — don't speculate
- Keep full briefings readable in 2–3 minutes
- **Every fact must trace to a tool call** — don't include data not returned by Common Room

## Reference Files

- **`references/signals-guide.md`** — signal type taxonomy and interpretation guide

© Common Room · Apache-2.0 · anthropics/knowledge-work-plugins

Similar skills

All skills for Agent setup: memory, context, orchestration →

account-research by other authors comes first.

account-research official anthropics account-research researches target prospect companies, checks fit against your ICP, and cross-references CRM records before outreach. CX Codex +1 3,600installs account-research crustdata account-research — a skill that researches a company by combining public data with your own history of dealing with them, then returns a plan, org chart, stack or battlecard. CX Codex +1 344installs Apollo.io MCP Server Inferensys Hands your AI assistant the Apollo.io API: lead search, contact enrichment, CRM records and email sequences without leaving the editor. CX Codex +1 ★ 6repo stars Person Enrichment — Professional Profile from Email axel-belfort Person Enrichment — Professional Profile from Email is an MCP server that finds a person's professional profile from an email for lead research and CRM updates. CX Codex +1 2,555installs FullEnrich FullEnrich FullEnrich connects verified B2B prospecting to AI agents. It discovers business email addresses and direct phone numbers using multi-vendor waterfall lookups. CX Codex +1 ★ 14repo stars ZoomInfo Zoominfo ZoomInfo connects company intelligence and corporate contact directories directly to your assistant. Helps build prospect lists and prepare for sales calls. CX Codex +1 ★ 10repo stars sales-account-segmentation Maya-Beth Finotti sales-account-segmentation builds an account segmentation model between ICP and tier structure. It computes a fit score from 12 months of closed-won deals and maps expansion whitespace for CRM operations. CX Codex +1 33,600installs prospecting coreyhaines31 prospecting — a skill for discovering and vetting prospects in B2B outbound sales. It walks you through defining ICP, assembling a candidate list from multiple sources, verifying contacts, and scoring leads by buying signals and fit. CX Codex +1 77,400installs

From the same set263

The whole set →
draft-announcement The draft-announcement Claude Code command drafts a formatted Slack announcement and saves it for review. It asks about the channel, audience, message, timing, and tone when those details are missing. CX Codex +1 ★ 36,654repo stars channel-digest The channel-digest Claude Code command summarizes recent activity across Slack channels. It extracts discussion topics, decisions, questions, and notable messages. CX Codex +1 ★ 36,654repo stars prospect This Claude Code skill builds company and contact lists with Common Room Prospector. It activates for requests to find companies by criteria, locate contacts, or build a prospect list. CX Codex +1 ★ 36,654repo stars call-prep Skill for Claude Code builds a meeting brief using Common Room account signals and participant data. Runs on any call preparation request mentioning a company name. CX Codex +1 ★ 36,654repo stars weekly-brief The weekly-brief Claude Code command builds a weekly meeting prep brief from a calendar and Common Room. It researches external calls in a chosen date range and sorts the notes by meeting date. CX Codex +1 ★ 36,654repo stars generate-account-plan The generate-account-plan Claude Code command builds a strategic plan for a company account. It reviews account, contact, and activity data, with web search as a supplement when requested or when data is sparse. CX Codex +1 ★ 36,654repo stars generate-guidelines generate-guidelines — a Claude Code command that turns brand documents, transcripts, or discovery reports into voice guidelines. It brings the findings together and saves the guide in the working folder. CX Codex +1 ★ 36,654repo stars enforce-voice The enforce-voice Claude Code command applies brand guidelines to a content request. It checks the draft’s voice, tone and terminology against those rules. CX Codex +1 ★ 36,654repo stars

Project sponsors

Companies that keep this analytics open