Skip to content

himself65/finance-skills / plugins/social-readers/skills/yc-reader

yc-reader

Unverified

Look up Y Combinator companies and batches from the public yc-oss API, a static JSON dataset refreshed daily: company profiles, batch rosters (e.g. W25, S24), companies by industry or tag, top companies, who is hiring, founder-diversity lists, and overall YC stats. Use this skill whenever the user asks about YC-backed startups, a YC batch, YC companies in a sector or tag or that are hiring, the Y Combinator portfolio, or startup and venture research that draws on YC data. Read-only.

Y Combinator Reader (Read-Only)

If your host has not already executed the shell probes below (for example, in Codex), run the commands inside the ! wrappers with its shell tool before choosing a setup path. Use the actual output; if shell access is unavailable, report that limitation.

Fetches Y Combinator company data from the yc-oss/api, an unofficial open-source API that indexes all publicly launched YC companies. The data is sourced from YC's Algolia search index and updated daily via GitHub Actions.

This is a read-only data source. It provides company profiles, batch listings, industry/tag breakdowns, hiring status, and diversity data. No write operations exist — the API serves static JSON files.

No authentication required. The API is public and free. Just use curl to fetch JSON endpoints.


Step 1: Verify Prerequisites

This skill only needs curl (to fetch data) and jq (to parse/filter JSON). Both are pre-installed on most systems.

!`(command -v curl > /dev/null && echo "CURL_OK" || echo "CURL_MISSING") && (command -v jq > /dev/null && echo "JQ_OK" || echo "JQ_MISSING")`

If JQ_MISSING, install it:

# macOS
brew install jq

# Linux (Debian/Ubuntu)
sudo apt-get install jq

If jq is unavailable, you can still fetch raw JSON with curl and parse it inline with Python or other tools — but jq makes filtering much easier.


Step 2: Identify What the User Needs

Match the user's request to the appropriate endpoint. See references/api_reference.md for full details.

User RequestEndpointNotes
Overall YC statsmeta.jsonCompany count, batch list, industry/tag lists
All companiescompanies/all.jsonFull dataset (~5,700 companies) — large response
Top companiescompanies/top.json~91 top-performing YC companies
Companies hiringcompanies/hiring.json~1,400 currently hiring
Non-profit companiescompanies/nonprofit.jsonYC-backed non-profits
Diversity datacompanies/black-founded.json, hispanic-latino-founded.json, women-founded.jsonFounder diversity
Specific batchbatches/{batch-name}.jsone.g., winter-2026.json, spring-2026.json, fall-2025.json
Single company profilebatches/{batch-name}/{slug}.jsone.g., batches/summer-2009/stripe.json, batches/winter-2009/airbnb.json
By industryindustries/{industry}.jsone.g., fintech.json, healthcare.json
By tagtags/{tag}.jsone.g., ai.json, developer-tools.json

Batch name format

Batches use {season}-{year} format: winter-2026, spring-2026, summer-2026, fall-2025. Older batches follow the same pattern back to summer-2005. The short form (w09, s21) also works for the per-company endpoint.

Industry and tag name format

Use lowercase with hyphens for multi-word names: real-estate, developer-tools, machine-learning.


Step 3: Execute the Request

Base URL

https://yc-oss.github.io/api/

General pattern

# Fetch and pretty-print
curl -s https://yc-oss.github.io/api/companies/top.json | jq .

# Count companies in a result
curl -s https://yc-oss.github.io/api/batches/winter-2025.json | jq length

# Filter by field (e.g., hiring companies in a batch)
curl -s https://yc-oss.github.io/api/batches/winter-2025.json | jq '[.[] | select(.isHiring == true)]'

# Extract specific fields
curl -s https://yc-oss.github.io/api/companies/top.json | jq '.[] | {name, one_liner, batch, team_size, website}'

# Search by name (case-insensitive)
curl -s https://yc-oss.github.io/api/companies/all.json | jq '[.[] | select(.name | test("stripe"; "i"))]'

Key rules

  1. Use -s flag with curl to suppress progress output
  2. Pipe through jq for readable output and filtering
  3. Avoid fetching companies/all.json unless necessary — it's a large response (~5,700 companies). Prefer more specific endpoints (batches, industries, tags) when possible
  4. Use jq select/filter to narrow results client-side when the API doesn't have a specific endpoint for what the user wants
  5. Batch names are lowercase with hyphens — winter-2025 not Winter 2025 or W25
  6. Tag and industry names are lowercase with hyphens — developer-tools not Developer Tools

Common jq filters

FilterPurpose
jq lengthCount results
jq '.[0]'First company
jq '.[:10]'First 10 companies
jq '[.[] | select(.isHiring == true)]'Only hiring companies
jq '[.[] | select(.status == "Active")]'Only active companies
jq '[.[] | select(.team_size > 100)]'Companies with 100+ employees
jq '.[] | {name, one_liner, batch, website}'Select specific fields
jq '[.[] | select(.name | test("query"; "i"))]'Search by name
jq 'sort_by(-.team_size) | .[:10]'Top 10 by team size

Step 4: Present the Results

Summarize rather than dump JSON. For each company, give the name, one-liner, batch, team size, status, hiring status (a growth signal), and website. For a batch, lead with its size and notable companies; for an industry or tag, the count and which companies are top or hiring; for research questions, aggregate stats such as counts, common industries, and team-size distribution. Mention that the dataset refreshes daily.


Step 5: Diagnostics

If a request fails:

ErrorCauseFix
404 Not FoundInvalid batch, industry, or tag nameCheck meta.json for valid names
Empty array []No companies match the queryBroaden the search or check spelling
curl: Could not resolve hostNo internet connectionCheck network connectivity
Large/slow responseFetching companies/all.json (5,700+ entries)Use a more specific endpoint or add jq filters

To discover valid batch, industry, and tag names:

# List all batches
curl -s https://yc-oss.github.io/api/meta.json | jq '.batches[].name'

# List all industries
curl -s https://yc-oss.github.io/api/meta.json | jq '.industries[].name'

# List all tags (there are 333+)
curl -s https://yc-oss.github.io/api/meta.json | jq '.tags[].name'

Reference Files

  • references/api_reference.md — Complete endpoint reference with company schema, all endpoint URLs, and research workflow examples

Read the reference file when you need the exact company field schema, valid batch/industry/tag names, or detailed research workflow patterns.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.Stars: 195kUpdated Claude CodeCodexVerifiedInstall
internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).Stars: 195kUpdated Claude CodeCodexVerifiedInstall