Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Research An Account

ASecurity

Research a target account or contact at the depth you need: a 30-second qualify on a URL, a full cited brief with site scrape and twelve weeks of news, an enrichment on a named person, or a warm-paths search across your CRM and LinkedIn. Every claim cites a real source - no invented news, funding, or connections.

113 stars
0 votes
0 copies
0 views
Added 9/19/2026
researchgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add gethouston/houston --skill research-an-account --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Research An Account?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Research An Account
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gethouston-research-an-account/badge)](https://www.skillsdirectory.com/skills/gethouston-research-an-account)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: research-an-account
description: "Research a target account or contact at the depth you need: a 30-second qualify on a URL, a full cited brief with site scrape and twelve weeks of news, an enrichment on a named person, or a warm-paths search across your CRM and LinkedIn. Every claim cites a real source - no invented news, funding, or connections."
version: 1
category: Sales
featured: no
image: handshake
integrations: [gmail, hubspot, salesforce, attio, linkedin, firecrawl, perplexityai]
x_houston:
  created_by: houston
  skill_schema: 1
---


# Research An Account

One skill, four research shapes. `depth` param pick pass. Source-citation + "never invent fact" discipline shared.

## Parameter: `depth`

- `quick-qualify`  -  30-sec read of single URL. One scrape, one decision (GOOD-FIT / BORDER / OUT), one angle if GOOD-FIT. Fast triage, not brief.
- `full-brief`  -  multi-pass cited brief on named account: site scrape, recent news (12 weeks), tech-stack detect, social scan, intent signals. Feeds outreach + call prep.
- `enrich-contact`  -  named person: firmographics, role context, reporting line if discoverable, recent posts/talks, trigger signals. For outreach personalization.
- `warm-paths`  -  first-degree intros: search connected LinkedIn/Gmail/CRM for people who know someone at target. Rank paths by strength.

User ask imply depth ("quick read", "go deep", "enrich this person", "who do I know there") → infer. Else ask ONE question naming 4 options.

## When to use

- Explicit triggers in description.
- Implicit: inside `write-my-outreach stage=cold-email` (cold email need signal  -  this skill find it) and `prep-a-meeting type=call` (call need brief).

## Connections I need

I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.

- **Scrape**  -  read the company's site, product pages, tech-stack signals. Required for `quick-qualify` and `full-brief`.
- **Search / research**  -  pull recent news, funding, hires for `full-brief` and `enrich-contact`. Required for those depths.
- **Social**  -  read public LinkedIn profile and posts for `enrich-contact` and `warm-paths`. Required for those depths.
- **CRM**  -  cross-reference first-degree connections and prior touches for `warm-paths`. Required for that depth.
- **Inbox**  -  cross-reference who you've emailed at the target for `warm-paths`. Optional.

If none of the required categories for the chosen depth are connected I stop and ask you to connect Firecrawl first since most depths build off the site read.

## Information I need

I read your sales context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.

- **Your sales playbook**  -  Required. Why I need it: Your ideal customer profile and differentiators ground the qualify decision and brief framing. If missing I ask: "I don't have your playbook yet  -  want me to draft it now?"
- **The target company name or URL**  -  Required for `quick-qualify`, `full-brief`, `warm-paths`. Why I need it: scrape and news search anchor on it. If missing I ask: "Which company should I research  -  paste the homepage URL or tell me the name?"
- **The target person's name and company**  -  Required for `enrich-contact`. Why I need it: the enrichment is grounded to a real LinkedIn profile. If missing I ask: "Who should I enrich  -  full name and company?"
- **Connected CRM**  -  Required for `warm-paths`. Why I need it: I cross-reference your past touches and mutual customers. If missing I ask: "Connect your CRM (HubSpot, Salesforce, Attio, Pipedrive, or Close) so I can find warm paths."

## Steps
<!-- houston-workflow:v1 -->

1. **Read ledger + playbook.** Gather missing required fields (ONE question each, best-modality first). Write atomically.

2. **Discover tools via Composio.** `composio search web-scrape` / `composio search search-research` / `composio search crm` / `composio search linkedin` per depth. No tool for required category connected → name category to link, stop.

3. **Branch on depth.**
   - `quick-qualify`: scrape URL (one request). Extract: what they do, who they sell to, team size signal, tech stack signal. Apply playbook disqualifiers. Output: **GOOD-FIT** / **BORDER** / **OUT** + one-sentence reason + one angle (single pain from playbook best matching them). Save tight `leads/{slug}/qualify-{YYYY-MM-DD}.md` (~150 words max).
   - `full-brief`: run scrape, search last 12 weeks news (funding, hires, product launches, leadership changes), detect tech stack (BuiltWith-style signals via scrape), scan company LinkedIn posts. Structure: **Snapshot** (one paragraph) → **Recent signals** (5-8 bullets, each cited w/ URL + date) → **Tech stack** (5-10 signals) → **Buying committee guesses** (pull from LinkedIn when available) → **Angles for outreach** (3 angles ranked, each tied to cited signal). Save to `accounts/{slug}/brief-{YYYY-MM-DD}.md`.
   - `enrich-contact`: search person via LinkedIn + connected CRM/email enrichment. Capture: title, company, tenure, prior companies, visible posts/talks/podcasts last 6 months, trigger signal (new role, speaker, press). Save to `leads/{slug}/enrichment-{YYYY-MM-DD}.md`.
   - `warm-paths`: via LinkedIn (Composio), find first-degree connections at target company. Cross-ref CRM for mutual-customer or mutual-investor paths. Rank: **Strong** (close connection, recent touch), **Medium** (weak tie, stale), **Weak** (third-degree only). Draft intro ask per strong path. Save to `leads/{slug}/warm-paths-{YYYY-MM-DD}.md`.

4. **Cite every claim.** No uncited facts. Any claim without URL or CRM field reference marked `(hypothesis  -  verify)`.

5. **Append to `outputs.json`**  -  read-merge-write atomically: `{ id (uuid v4), type: "account-brief" | "contact-enrichment" | "warm-paths" | "lead-batch" (for quick-qualify), title, summary, path, status: "ready", createdAt, updatedAt, domain: "outbound" }`.

6. **Summarize to user.** Top finding + path. Suggest next skill ("`write-my-outreach stage=cold-email` using angle #1?" or "`prep-a-meeting type=call` if this turns into meeting?").

## What I never do

- Invent news, funding, hires, tech-stack facts, connections. Every claim cite source.
- Scrape private data  -  LinkedIn public profile, company website, public news only.
- Enrich contact personal life beyond professional footprint.

## Outputs

- `quick-qualify` → `leads/{slug}/qualify-{YYYY-MM-DD}.md`
- `full-brief` → `accounts/{slug}/brief-{YYYY-MM-DD}.md`
- `enrich-contact` → `leads/{slug}/enrichment-{YYYY-MM-DD}.md`
- `warm-paths` → `leads/{slug}/warm-paths-{YYYY-MM-DD}.md`
- Appends to `outputs.json`.

Attribution

gethoustongethouston
View sourceMore from gethouston →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review...

452202 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

798221 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publi...

452201 votes

Exa Search

Semantic search, similar content discovery, and structured research using Exa API

304951 votes
View all in research →