account-brief
Skill1 starsChanged 4 months agoMITView on GitHub
Build a pre-outreach research brief on a target account — firmographics, ICP score, trigger events, who to contact, which hook to run, and three personalization angles. Use when the rep says "research [company]", "brief me on [company]", "should I go after [company]", or names a company before writing to it.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Nimbleway/agent-skillstheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Nimbleway/agent-skills★ 61same 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 repository14 other files it gives its agents.
- battlecardSkill
- build-listSkill
- dojoSkill
- draft-sequenceSkill
- handle-replySkill
- meeting-prepSkill
- post-callSkill
- reactivateSkill
- setupSkill
- signal-watchSkill
- voice-interviewSkill
- what-worksSkill
- work-inboundSkill
- write-emailSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read ${CLAUDE_PLUGIN_ROOT}/references/icp.md and ${CLAUDE_PLUGIN_ROOT}/references/guardrails.md if not already in context.
- Distinctive: line 16
Search HubSpot for the company and its contacts.
- Distinctive: line 22
If HubSpot isn't connected, say so and continue — but mark the brief "⚠️ unverified against CRM — check before sending."
- Very specific: line 26
Use Exa search tools if available (web_search_exa, web_fetch_exa).
- Distinctive: line 35
Keep it to ~6-8 searches. Don't chase perfect data — a brief in 5 minutes beats a dossier in 40.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Account Brief
Produce a one-page brief you can act on in the next 10 minutes. Input: a company name or domain. If several companies are given, run this for each.
Before you research
Read ${CLAUDE_PLUGIN_ROOT}/references/icp.md and ${CLAUDE_PLUGIN_ROOT}/references/guardrails.md if not already in context.
Step 1 — HubSpot check (guardrail #1)
Search HubSpot for the company and its contacts. Determine:
- Existing customer (lifecycle stage = customer, or closed-won deal on the account)? → STOP. Output only: "⛔ [Company] is an existing customer. No cold outbound — if there's an expansion angle, route it to the account owner."
- Open deals or active demos? → STOP. Output only: "⛔ [Company] has active sales work in HubSpot (deal: [name/stage], owner: [rep]). Off-limits for outbound — the demo flow is sacred. Ask [owner] if you want in."
- Prior activity that went cold (>90 days)? → proceed, but note the history so outreach can reference or avoid it.
- Nothing? → clean target, proceed.
If HubSpot isn't connected, say so and continue — but mark the brief "⚠️ unverified against CRM — check before sending."
Step 2 — Research (Exa first, web search fallback)
Use Exa search tools if available (web_search_exa, web_fetch_exa); otherwise regular web search. Gather, in priority order:
- Company basics — what they do, size, funding stage, HQ (one Exa
category:companyquery usually covers this) - Product/tech-fit signals — the observable signals from your ICP reference that mean they have the problem you solve (tools they use, how they're built, what they've shipped): job posts, engineering blog posts, open-source presence
- Primary-trigger signals ⭐ — evidence of the primary trigger event from your ICP reference (this feeds the primary hook)
- Trigger events, last 90 days — check against the trigger events in the ICP reference (new hires, incidents, M&A, contract/renewal timing, leadership changes)
- People — Exa
category:peoplesearch for the Champion and Practitioner (per the buying committee in the ICP reference); grab names, titles, LinkedIn URLs - Current tooling — any evidence they use a competing tool or the status quo (see messaging.md for the approved competitor specifics)
Keep it to ~6-8 searches. Don't chase perfect data — a brief in 5 minutes beats a dossier in 40.
Step 3 — Score and decide
Score against the 10-point rubric in the ICP reference. Show the math (which attributes earned points and the evidence).
Output format
# [Company] — Account Brief · [date]
**Verdict:** [PURSUE NOW / QUALIFY FIRST / PASS] · ICP score X/10
**CRM status:** [clean / cold history / ⚠️ unverified]
## Snapshot
[2-3 sentences: what they do, size, stage, why they're (not) a fit]
## Score breakdown
[attribute → points → evidence, one line each]
## Trigger events found
[trigger → evidence + link → how fresh]
## Who to contact (in order)
1. [Name, title, LinkedIn] — [Champion/Practitioner/Economic Buyer type] — [why them]
2. ...
## Recommended play
Hook #[1-5] ([name]) — [one sentence why this hook fits this account]
## 3 personalization angles
1. [specific, cited fact you can open with]
2. ...
## Watch-outs
[anything that could embarrass: recent layoffs, bad press, existing relationship, competitor exec, etc.]End with: "Want the first-line drafts for these contacts? Say write emails for [names]."
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.

