orthogonal-yc-batch-evaluator
Evaluate YC batch companies for investment — scrapes the YC directory, researches each company and its founders (work history, LinkedIn, website), assesses founder-company fit, and exports to Google Sheets with priority rankings. Use when asked to evaluate YC companies, research a YC batch, screen startups, or do due diligence on YC companies.
Profile →npx skills add majiayu000/claude-skill-registry --skill orthogonal-yc-batch-evaluator --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Scrapes a YC batch directory, researches each company and its founders (work history, LinkedIn, website), assesses founder–company fit, and exports results to Google Sheets with priority rankings. Designed for investors evaluating YC companies and for due diligence tasks.
How it works
- Reads credentials from ~/.gooseworks/credentials.json to obtain API key and base URL.
- Step 1: Scrape the YC batch directory to extract basic company data (name, description, tags, location, URL slug).
- Step 2: Create a new Google Sheet and populate with batch data (company names and descriptions) before deeper research, then share the link.
- Step 3: Research each company in batches of 3-5, running parallel tasks per company:
- 3a. Scrape the YC company page for rich data (founders with LinkedIn/Twitter, bios, site URL, team size, location, sectors, founding year).
- 3b. Scrape the company’s website for product, pricing, features, traction, and hiring signals.
- 3c. Use Apollo to pull founder work history from LinkedIn URLs; fallback by name + company if LinkedIn is unavailable.
- 3d. Run Perplexity market analysis for market context and competitive landscape.
- Step 4: As each company’s research completes, update its row in the Google Sheet immediately (one update per row, not batched).
- Step 4 finalizes rows with 12 fields in a strict order (Sectors, Location, Website, Founders, LinkedIn URLs, Twitter URLs, Background, Fit, Website Analysis, Market, Overall, blank for rank).
- All steps use Bearer auth with endpoints described in the prompts and require live scraping & parallelization for demo cadence.
When to use it
Use when asked to evaluate YC companies, research a YC batch, screen startups, or perform due diligence on YC companies. If a batch is not specified, defaults to Spring 2026. Always create a new Google Sheet for results. Do not ask clarifying questions; start immediately.
What it can touch
- Endpoints for Google Sheets and batch scraping via Gooseworks API:
- /v1/proxy/orthogonal/run with api: "scrapegraph" and path: "/v1/smartscraper" for YC pages and company pages
- /v1/proxy/orthogonal/run with api: "google-sheets" and path: "/create-spreadsheet" or "/update-values" for sheet creation and row updates
- Data fields touched include: company name, description, sector(s), location, website, founders, LinkedIn(s), Twitter/X, founder background, fit rating, website analysis, market/competitors, overall assessment, and priority rank.
Caveats
- The process explicitly warns not to ask clarifying questions and to start scraping immediately.
- The 12-column update requires exact ordering in the API payloads; any deviation can misalign the sheet.
- The instructions enforce live updates in batches (3-5) with per-row writes for visual cadence.
- If a website scrape fails, the Website Analysis field must reflect the failure text: "Website not available or pre-launch".
- Sourcing data from YC pages may include non-founders (staff like YC partners) which must be filtered out per parsing rules.
# YC Batch Evaluator ## Setup Read your credentials from ~/.gooseworks/credentials.json: ```bash export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])") export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))") ``` If ~/.gooseworks/credentials.json does not exist, tell the user to run: `npx gooseworks login` All endpoints use Bearer auth: `-H "Authorization: Bearer $GOOSEWORKS_API_KEY"` Scrape a YC batch, research every company and founder, assess founder-company fit, and export a live-updating Google Sheet with priority rankings. Designed for investors evaluating YC companies. ## IMPORTANT: Do NOT ask clarifying questions. Just start immediately. All inputs are optional. If the user said a batch, use it. If they didn't specify sectors or thesis, process ALL companies. **Always create a new Google Sheet** — never ask for an existing spreadsheet ID. **Start scraping immediately — do not ask "which batch?", "any sector filters?", or "should I create a sheet?".** This is designed for live demos where speed and visua
- Setup
- IMPORTANT: Do NOT ask clarifying questions. Just start immediately.
- Input
- Step 1: Scrape the YC Batch Directory
- Step 2: Create Google Sheet and Share Link Immediately
- Step 3: Research Each Company — Row by Row
- Parallelization Strategy
- 3a. Scrape the YC company page (~$0.03 each)
- 3b. Scrape the company's own website (~$0.03 each)
- 3c. Apollo — founder work history (~$0.01 per founder)
- 3d. Perplexity — market context (~$0.005 each)
- Step 4: Compile and Update Each Row
- Formatting rules
- Founder-Company Fit (J) — Strong / Moderate / Weak
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/apollo/people/match \
Step 5a: Read all current data
Step 5b: Sort the rows by column N (Priority Rank) ascending, then rewrite ALL rowsWhat does the orthogonal-yc-batch-evaluator skill do?
Evaluate YC batch companies for investment — scrapes the YC directory, researches each company and its founders (work history, LinkedIn, website), assesses founder-company fit, and exports to Google Sheets with priority rankings. Use when asked to evaluate YC companies, research a YC batch, screen startups, or do due diligence on YC companies.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill orthogonal-yc-batch-evaluator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.