Research Company

B2B company research producing professional PDF reports. Use when asked to research a company, analyze a business, create an account profile, or generate market intelligence from a company URL. Outputs a beautifully formatted, downloadable PDF report.

Security Scan

The skill's code, instructions, and requirements align with its stated purpose (web research → build JSON → generate PDF); nothing requests unexplained credentials or installs arbitrary remote binaries.

Purpose & Capability

Name/description (company research, PDF reports) match the included assets: SKILL.md describes web searches and data assembly and a bundled PDF generator script (scripts/generate_report.py). No unrelated credentials, binaries, or services are requested.

Instruction Scope

Runtime instructions are scoped to: run web fetch/search tools, assemble a JSON matching the provided schema, run the local PDF generator, and save/deliver the PDF. The instructions do not ask the agent to read unrelated system files, environment variables, or post data to unexpected endpoints.

Install Mechanism

There is no registry install spec (instruction-only), which is low risk. SKILL.md suggests 'pip install reportlab' prior to running the script — a normal dependency install from PyPI. Installing packages from PyPI has standard supply-chain risk but is proportionate to generating PDFs.

Credentials

The skill declares no required environment variables, no credentials, and no config paths. The agent's web fetch/search tools will access public web data as needed; no sensitive secrets are requested by the skill itself.

Persistence & Privilege

always:false (not force-included). The skill does not modify other skills or request persistent system-level privileges. It can be invoked autonomously per platform defaults, which is expected for skills.

Assessment

This skill appears internally consistent and implements what it claims: use agent web search/fetch to collect public info, assemble a JSON, and produce a PDF using the included Python script. Before installing/using: (1) confirm you trust the agent's web-fetch/search tools because the skill will request public webpages (these could contain personal or sensitive information depending on the target); (2) be prepared to run 'pip install reportlab' in the execution environment (PyPI install risk is ordinary but non-zero); (3) inspect scripts/generate_report.py yourself if you want to be certain no network calls or secret access are added (the provided script appears local-only and reportlab-based); (4) avoid running the skill against targets where you do not have permission to scrape or collect data. Overall the skill is coherent and proportionate to its purpose.

Company Research

Generate comprehensive Account Research Reports as professionally styled PDFs from a company URL.

Workflow

1. Research the company (web fetch + searches)
2. Build JSON data structure
3. Generate PDF via scripts/generate_report.py
4. Deliver PDF to user

Phase 1: Research (Parallel)

Execute these searches concurrently to minimize context usage:

WebFetch: [company URL]
WebSearch: "[company name] funding news 2024"
WebSearch: "[company name] competitors market"
WebSearch: "[company name] CEO founder leadership"

Extract from website: company name, industry, HQ, founded, leadership, products/services, pricing model, target customers, case studies, testimonials, recent news.

Phase 2: Build Data Structure

Create JSON matching this schema (see references/data-schema.md for full spec):

{
  "company_name": "...",
  "source_url": "...",
  "report_date": "January 20, 2026",
  "executive_summary": "3-5 sentences...",
  "profile": { "name": "...", "industry": "...", ... },
  "products": { "offerings": [...], "differentiators": [...] },
  "target_market": { "segments": "...", "verticals": [...] },
  "use_cases": [{ "title": "...", "description": "..." }],
  "competitors": [{ "name": "...", "strengths": "...", "differentiation": "..." }],
  "industry": { "trends": [...], "opportunities": [...], "challenges": [...] },
  "developments": [{ "date": "...", "title": "...", "description": "..." }],
  "lead_gen": { "keywords": {...}, "outreach_angles": [...] },
  "info_gaps": ["..."]
}

Phase 3: Generate PDF

# Install if needed
pip install reportlab

# Save JSON to temp file
cat > /tmp/research_data.json << 'EOF'
{...your JSON data...}
EOF

# Generate PDF
python3 scripts/generate_report.py /tmp/research_data.json /path/to/output/report.pdf

Phase 4: Deliver

Save PDF to workspace folder and provide download link:

[Download Company Research Report](computer:///sessions/.../report.pdf)

Quality Standards

• Accuracy: Base claims on observable evidence; cite sources
• Specificity: Include product names, metrics, customer examples
• Completeness: Note gaps as "Not publicly available"
• No fabrication: Never invent information

Resources

• scripts/generate_report.py - PDF generator (uses reportlab)
• references/data-schema.md - Full JSON schema with examples