菜单
Deep research on a single company — signals, hiring, news, tech stack, and LinkedIn presence. Uses the Saber CLI for signal data and any available MCP tools for broader research.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Activate company-level signal tracking. Runs signals via the Saber CLI if available; without it, outputs a research playbook and suggests alternative tracking methods.
Generate 12–15 structured, weighted research signals from a structured ICP, ready to activate in Saber. Each signal includes answer type, weight, and interpretation rules for automatic scoring.
End-to-end guided workflow — take one prospect domain, run your saved research signals, find named contacts on the buying committee, and write a hyper-personalised cold email and LinkedIn DM grounded in the signal answers. First run defines the source-company ICP, contact-search targets, and ≤5 weighted signals (saved to disk); every subsequent run reuses them. Use when you want full SDR research-and-write for a single prospect, not write-outreach in isolation.
End-to-end guided workflow — build a Saber company list, run research signals across every company in parallel, find named contacts, and export a combined CSV to the desktop. Walks the user through each stage with confirmations and a credit-discipline guard. Use when you want one signed-off CSV instead of running build-account-list, create-company-signals, and build-contact-list separately.
Build a target account list and run company signals against it. Works with the Saber CLI, Apollo, HubSpot, or any available prospecting tool — with a manual fallback.
Set up native scoring — create a profile, translate signal templates into rules, and bulk-assign a list so fit and urgency scores compute automatically. Bridges the weighted model from generate-signals into the platform.
| name | research-account |
| description | Deep research on a single company — signals, hiring, news, tech stack, and LinkedIn presence. Uses the Saber CLI for signal data and any available MCP tools for broader research. |
Use this skill to build a comprehensive picture of a target company before reaching out or prioritising them for outreach.
Produce a research brief covering: company overview, recent news and events, hiring signals, tech stack, LinkedIn presence, and any Saber signal results — ready to inform outreach or qualification decisions.
Ask the user for the company name or domain if not already in conversation context.
Check what research tools are available:
Saber CLI (saber --help): runs signals against the domain for structured data. An account brief is mostly commodity facts, which is exactly what the five prebuilt signals return — saber signal funding|mna|tech|open-jobs|firmographics --domain <domain>, structured and source-cited, no question design needed. For anything the brief needs that isn't one of those five facts — a product capability, a specific hiring pattern, a qualification judgement — write a custom --question.
MCP tools: scan available tools for:
Note what's available — use everything you can find.
Run these in parallel where possible:
saber signal firmographics --domain <domain> → size, HQ, industry, employee count, founded year (structured + sourced)Focus on the last 6–12 months.
saber signal funding --domain <domain> (rounds, amounts, investors) and saber signal mna --domain <domain> (acquisitions, as acquirer or target) — both source-citedsaber signal open-jobs --domain <domain> → open-role count, hiring themes, locations, and what they're hiring forsaber signal tech --domain <domain> --category crm (or --category erp, or --technology "<name>" for a specific product) → current systems, each backed by public web evidenceIf a LinkedIn MCP is available, look up the company page:
If the Saber CLI is available, the prebuilt signals above are the fastest way to get structured, source-cited data for this domain. Each consumes credits — check the balance first (saber credits), then fire them in parallel and collect:
saber signal funding --domain <domain> --no-wait
saber signal mna --domain <domain> --no-wait
saber signal open-jobs --domain <domain> --no-wait
saber signal firmographics --domain <domain> --no-wait
saber signal tech --domain <domain> --category crm --no-wait
saber signal get <signalId> # for each returned id, once complete
For a fact no prebuilt signal covers, run a custom question: saber signal --domain <domain> --question "<question>" --answer-type boolean.
If pre-defined signal subscriptions exist for a list containing this company, retrieve those results:
saber subscription list
saber subscription get <subscriptionId>
If a HubSpot MCP is available, look up whether this company already exists as a contact or deal in HubSpot — note the current stage and any logged activity.
Structure the output as a brief:
## [Company Name] — Research Brief
**Overview:** 2–3 sentence summary of what they do and why they matter.
**Recent signals:**
- [Funding / M&A — from `saber signal funding` / `mna`, with source URL]
- [Hiring — from `saber signal open-jobs`]
- [Any subscription signal results]
**Tech stack:** [CRM/ERP and notable tools — from `saber signal tech`, with evidence URLs]
**LinkedIn:** [Employee count, growth trend, notable activity]
**HubSpot status:** [Known / not known; deal stage if applicable]
**Outreach angle:** 1–2 sentence recommendation for how to approach them based on the research.
After presenting the brief, suggest:
write-outreach to draft a personalised message using this researchqualify-inbound if you need a formal signal-based qualification scoreenrich-contacts to find specific contact details for the people to reach out to