/event-prospecting

name: event-prospecting
description: |
  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 sponsor/exhibitor page,
  (5) scrape conference speakers and rank by ICP fit.
  Triggers: "find leads at {event}", "research speakers at",
  "prospect this conference", "stripe sessions leads",
  "ai engineer summit prospects", "event prospecting",
  "scrape conference speakers", "who should I meet at".
license: MIT
compatibility: Requires browse CLI (`npm install -g browse`) and BROWSERBASE_API_KEY env var. The same `browse` binary covers both API commands and JS-rendered page fallback.
allowed-tools: Bash Agent AskUserQuestion
metadata:
  author: browserbase
  version: "0.1.0"

Event Prospecting

Take a conference URL → get a ranked list of people the AE should talk to, with a "why reach out" rationale per person.

**Required**: `BROWSERBASE_API_KEY` env var and the `browse` CLI installed (`npm install -g browse`). Use `browse cloud ...` for API calls and `browse open` / `browse get markdown` for JS-heavy speaker pages.

**Path rules**: Always use the full literal path in all Bash commands — NOT `~` or `$HOME` (both trigger "shell expansion syntax" approval prompts). Resolve the home directory once and use it everywhere. When constructing subagent prompts, replace `{SKILL_DIR}` with the full literal path (typically `/Users/jay/skills/skills/event-prospecting`).

**Output directory**: All event prospecting output goes to `~/Desktop/{event_slug}_prospects_{YYYY-MM-DD-HHMM}/`. Final deliverable is `index.html` (people grouped by company, ranked by company ICP), with `companies.html` and `people.html` (filterable) as alternate views, plus `results.csv` for cold-outbound import.

**CRITICAL — Tool restrictions (applies to main agent AND all subagents)**:

• All web searches: use `browse cloud search`. NEVER use WebSearch.
• All page content extraction: use `node {SKILL_DIR}/scripts/extract_page.mjs "<url>"`. This script fetches via `browse cloud fetch --output`, parses title + meta tags + visible body text, and automatically falls back to `browse get markdown` when fetch fails or returns thin JS-rendered content. NEVER hand-roll a `browse cloud fetch | sed` pipeline. NEVER use WebFetch.
• All research output: subagents write **one markdown file per company OR per person** to `{OUTPUT_DIR}/companies/{slug}.md` or `{OUTPUT_DIR}/people/{slug}.md` using bash heredoc. NEVER use the Write tool or `python3 -c`. See `references/example-research.md` for both file formats.
• Report compilation: use `node {SKILL_DIR}/scripts/compile_report.mjs {OUTPUT_DIR} --open`.
• **Subagents must use ONLY the Bash tool. No other tools allowed.**
• **HARD TOOL-CALL CAPS**: ICP triage = 1 call/company; deep research = 5 calls/company; person enrichment = 4 calls/person. See `references/workflow.md` for enforcement detail.

**CRITICAL — Anti-hallucination rules (applies to main agent AND all subagents)**:

• NEVER infer `product_description`, `industry`, or a person's `role_reason` from a site's fonts, framework, design system, or typography. These are cosmetic and say nothing about what the company sells or what the person does.
• NEVER let the user's own ICP leak into a target's description. If you don't know what the target does, write `Unknown` — do not pattern-match them onto the ICP.
• `product_description` MUST quote or paraphrase a specific phrase from `extract_page.mjs` output. If none of TITLE/META/OG/HEADINGS/BODY yield a recognizable product statement, write `Unknown — homepage content not accessible` and cap `icp_fit_score` at 3.
• A person's `hook` MUST quote or paraphrase a specific finding from a `browse cloud search` result (podcast title, blog headline, GitHub repo, talk abstract). If no public signal exists in the last 6 months, fall back to event-context (their talk title at this event).

**CRITICAL — Minimize permission prompts**:

• Subagents MUST batch ALL file writes into a SINGLE Bash call using chained heredocs. One Bash call = one permission prompt.
• Batch ALL searches and ALL fetches into single Bash calls using `&&` chaining.

Pipeline Overview

Follow these 10 steps in order. Do not skip steps or reorder.

0. **Setup** — output dir + clean slate 1. **Load profile** — read `profiles/{user_slug}.json` 2. **Recon** — detect event platform 3. **Extract people** — `people.jsonl` 4. **Group by company** — `seed_companies.txt` 5. **ICP triage** — fast company-level scoring (1 call/company) 6. **Filter** — companies with `icp_fit_score >= --icp-threshold` 7. **Deep research** — full Plan→Research→Synthesize on ICP fits 8. **Enrich speakers** — ask user: ICP-fit only (default) or all speakers 9. **Compile report** — HTML + CSV, open in browser

The user invokes the skill with a URL like `/event-prospecting <URL>`. Parse `EVENT_URL` from that invocation message. Defaults: `DEPTH=deep`, `ICP_THRESHOLD=6`. The `USER_SLUG` (ICP profile) is auto-resolved in Step 1 from whatever profile files exist locally — there is no built-in default profile. Do NOT ask the user to confirm the URL — they already gave you it.

---

Step 0: Setup Output Directory

Derive the output directory from the URL the user gave you. Do NOT hardcode any event name.

# EVENT_URL came from the invocation message (whatever the user typed after `/event-prospecting`)
EVENT_SLUG=$(node -e 'const h = new URL(process.argv[1]).hostname.replace(/^www\./,""); console.log(h.split(".")[0])' "$EVENT_URL")
TIMESTAMP=$(date +%Y-%m-%d-%H%M)
OUTPUT_DIR=/Users/jay/Desktop/${EVENT_SL