event-prospecting

77 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a research skill usually looks things up on the internet.

By browserbase/skills (GitHub) · research · 3,756 stars · scanned at commit 6811ca3

Event prospecting skill. Takes a conference / event speakers URL, extracts the people, filters their companies against the user's ICP, then deep-researches only the speakers at ICP-fit companies. Outputs a person-first HTML report where each card answers "why should the AE talk to this person?" with all public links and a one-click DM opener. Use when the user wants to: (1) find leads at a specific conference, (2) prep for an event, (3) research event speakers, (4) build a target list from a sp…

Works with any agent that supports SKILL.md skills.

What this skill can do

Downloads and installs other software

The author does not mention this.

Found in 2 places.

skills/event-prospecting/SKILL.md, line 19compatibility: Requires browse CLI (`npm install -g browse`) and BROWSERBASE_API_KEY env var. The same `browse` binary covers both API commands and JS-rendered
skills/event-prospecting/SKILL.md, line 30**Required**: `BROWSERBASE_API_KEY` env var and the `browse` CLI installed (`npm install -g browse`). Use `browse cloud ...` for API calls and `browse open` / `

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README.

Found in 26 places.

skills/event-prospecting/SKILL.md, line 79EVENT_SLUG=$(node -e 'const h = new URL(process.argv[1]).hostname.replace(/^www\./,""); console.log(h.split(".")[0])' "$EVENT_URL")
skills/event-prospecting/SKILL.md, line 99PROFILES=$(ls {SKILL_DIR}/profiles/*.json 2>/dev/null | xargs -n1 basename | sed 's/\.json$//' | grep -v '^example$')
skills/event-prospecting/SKILL.md, line 131node {SKILL_DIR}/scripts/recon.mjs {EVENT_URL} {OUTPUT_DIR}

Show 17 more

skills/event-prospecting/SKILL.md, line 145node {SKILL_DIR}/scripts/extract_event.mjs {OUTPUT_DIR} --user-company {USER_SLUG}
skills/event-prospecting/SKILL.md, line 154wc -l {OUTPUT_DIR}/people.jsonl {OUTPUT_DIR}/seed_companies.txt
skills/event-prospecting/SKILL.md, line 165wc -l {OUTPUT_DIR}/seed_companies.txt
skills/event-prospecting/SKILL.md, line 184node -e '
skills/event-prospecting/SKILL.md, line 230ls {OUTPUT_DIR}/companies/*.md | wc -l
skills/event-prospecting/SKILL.md, line 241THRESHOLD=6 # from --icp-threshold flag
skills/event-prospecting/SKILL.md, line 265while read slug; do
skills/event-prospecting/SKILL.md, line 294grep -l "triage_only: false" {OUTPUT_DIR}/companies/*.md | wc -l
skills/event-prospecting/SKILL.md, line 314TOTAL=$(wc -l < {OUTPUT_DIR}/people.jsonl)
skills/event-prospecting/SKILL.md, line 357if [ "$ENRICH_SCOPE" = "all" ]; then
skills/event-prospecting/SKILL.md, line 410ls {OUTPUT_DIR}/people/*.md | wc -l
skills/event-prospecting/SKILL.md, line 419node {SKILL_DIR}/scripts/compile_report.mjs {OUTPUT_DIR} --open
skills/event-prospecting/scripts/compile_report.mjs, line 910const { execSync } = await import('child_process');
skills/event-prospecting/scripts/compile_report.mjs, line 911try { execSync(`open "${join(dir, 'index.html')}"`); } catch {}
skills/event-prospecting/scripts/extract_event.mjs, line 7import { execFileSync } from 'child_process';
skills/event-prospecting/scripts/extract_event.mjs, line 17return execFileSync('browse', subargs, {
skills/event-prospecting/scripts/extract_page.mjs, line 9import { execFileSync } from "node:child_process";

and 6 more places

Connects to the internet

The author does not mention this. Expected for a research skill.

Found in 3 places.

skills/event-prospecting/references/workflow.md, line 585. BANNED TOOLS: WebFetch, WebSearch, Write, Read, Glob, Grep — ALL BANNED. Use ONLY Bash.
skills/event-prospecting/references/workflow.md, line 1467. BANNED TOOLS: WebFetch, WebSearch, Write, Read, Glob, Grep — ALL BANNED.
skills/event-prospecting/references/workflow.md, line 2596. BANNED TOOLS: WebFetch, WebSearch, Write, Read, Glob, Grep — ALL BANNED.

Safer alternatives

Low-risk skills in the same category (research) that look related. Check that one does what you need.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'event-prospecting' ] || [ -L ~/.agents/skills/'event-prospecting' ]; then echo 'A skill folder named event-prospecting already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/browserbase/skills' "$d" && git -C "$d" checkout --quiet '6811ca31163332d9d60309cff48e77f09de37a17' -- 'skills/event-prospecting' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/event-prospecting' ~/.agents/skills/'event-prospecting' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'event-prospecting' ~/.claude/skills/'event-prospecting' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for browserbase/skills shows the score of its lowest-scoring skill.

SkillTrust badge for browserbase/skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/browserbase/skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/browserbase/skills/)

Score history

Date	Version	Score
2026-11-08	`6811ca3`	77
2026-11-06	`6811ca3`	77