Skip to content
Agentmart
Submit a tool

web-research

Deep web scraping and structured lead research via Firecrawl web-agent.

Skill by TeddyJubu

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/teddyjubu-web-research

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Deep web scraping and structured lead research via Firecrawl web-agent.

Use cases: sales, research, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/web-research

What's inside

Skill name
web-research
Description
Deep web scraping and structured lead research via Firecrawl web-agent.
License
MIT
Instructions
45 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Web research (Firecrawl web-agent)

Use this skill when the operator asks for lead lists, market research, competitor scraping, or any task that needs many pages searched and structured output (CSV).

## Prerequisites

1. Firecrawl web-agent Express sidecar running (see `docs/web-agent-setup.md`).
2. `WABOT_AGENT_WEB_AGENT_ENABLED=true` on wabot-agent.
3. Call `web_research_health` before queueing a job.

## Workflow

1. Confirm the brief (targets, geography, exclusions, columns, minimum row count).
2. Call `start_web_research` with the **full** research prompt in `prompt` (do not shorten exclusion rules or column headers).
3. Tell the operator the job id and that results will arrive on WhatsApp when finished (may take 30–120+ minutes for 500+ leads).
4. Use `get_web_research_status` if they ask for progress.

## Output format

- Prefer `output_format=csv` and require CSV headers in the prompt.
- For strict JSON, use `output_format=json` and pass `output_schema_json` (JSON Schema string).

### Standard lead CSV headers

```
businessName,businessCategory,websiteUrl,googleMapsUrl,googleRating,googleReviewCount,address,phoneNumber,businessEmail,ownerName,ownerEmail,doctorOrPractitionerName,ownerLinkedInUrl,companyLinkedInUrl,facebookUrl,instagramUrl,bookingUrl,whatsappUrl,fitReason,personalisationLine,sourceUrl,notes
```

## Lead-gen prompt checklist

Include in every `start_web_research` prompt:

- **Target types** — clinic categories and geography (e.g. Singapore).
- **Exclusions** — hospital groups, government, major chains, franchises.
- **Research method** — Google Maps keywords, regions, directories; no guessed emails.
- **Quality** — dedupe, validate emails, source URL per row, no patient data.
- **Goal row count** — e.g. at least 500 independent clinics.

Pass the operator’s full brief verbatim when they provide one; do not drop exclusion lists or column definitions.

## Owner-only

`start_web_research` is restricted to owner WhatsApp numbers when `WABOT_AGENT_WEB_AGENT_OWNER_ONLY=true` (default).

From TeddyJubu/wabot-agent, MIT.

Signals

Stars
1
Forks
0
Open issues
14
Last commit (this folder)
May 18, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from TeddyJubu

Cite this page

web-research skill. Agent Mart. https://agentmart.dev/skills/teddyjubu-web-research (last updated 2026-10-24)