agent
Default browser automation agent — click, fill forms, navigate, log in, and extract structured data from any website using a natural-language goal, or run the…
Find paid open-source work, OSS bounties, open source grants, or ways to get paid contributing to open source. Use when someone asks any of the following — "find me paid open source work", "show me OSS bounties for Rust", "how do I get paid for open source", "find GitHub
$ npx -y skills add tinyfish-io/tinyfish-cookbook --skill oss-bounty-finder --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/oss-bounty-finderContext preview
The summary Claude sees to decide when to auto-load this skill.
Find paid open-source work, OSS bounties, open source grants, or ways to get paid contributing to open source. Use when someone asks any of the following — "find me paid open source work", "show me OSS bounties for Rust", "how do I get paid for open source", "find GitHub
name: oss-bounty-finder description: Find paid open-source work, OSS bounties, open source grants, or ways to get paid contributing to open source. Use when someone asks any of the following — "find me paid open source work", "show me OSS bounties for Rust", "how do I get paid for open source", "find GitHub bounties", "are there any open source grants I can apply to", "find bounties for Python developers", "show me open source funding opportunities", "what repos are paying for contributions", "find me issues with bounties", "show me open source stipends", "find developer grants", "show me NLNet grants", "GSoC alternatives", "paid open source issues". Accepts a stack (Rust, Python, Go, TypeScript, etc.) and optional keywords. Runs a 3-tier parallel TinyFish agent system; Tier 1 scrapes Algora and IssueHunt, Tier 2 fans out across awesome-list repos checking for bounty-labelled issues, Tier 3 scrapes NLNet, Sovereign Tech Fund, Mozilla MOSS, LFX Mentorship, GSoC, and Outreachy.
You have access to the TinyFish CLI (`tinyfish`), a tool that runs browser automations from the terminal using natural language goals. This skill uses it to search bounty platforms, GitHub repos, and grant foundation pages in parallel, then synthesizes results into a structured paid opportunities report.
Before making any TinyFish call, always run BOTH checks:
**1. CLI installed?**
PowerShell:
Get-Command tinyfish; tinyfish --version
bash/zsh:
which tinyfish && tinyfish --version || echo "TINYFISH_CLI_NOT_INSTALLED"
If not installed, stop and tell the user: > Install the TinyFish CLI: `npm install -g @tiny-fish/cli`
**2. Authenticated?**
tinyfish auth status
If not authenticated, stop and tell the user:
> You need a TinyFish API key. Get one at: https://agent.tinyfish.ai/api-keys > > Then authenticate: > > **Option 1 — CLI login (interactive):** > ``` > tinyfish auth login > ``` > > **Option 2 — PowerShell (current session only):** > ```powershell > $env:TINYFISH_API_KEY="your_api_key_here" > ``` > > **Option 3 — PowerShell (persist across sessions):** > ```powershell > [System.Environment]::SetEnvironmentVariable("TINYFISH_API_KEY", "your_api_key_here", "User") > ``` > Then close and reopen PowerShell for it to take effect. > > **Option 4 — bash/zsh (Mac/Linux):** > ```bash > export TINYFISH_API_KEY="your_api_key_here" > ``` > > **Option 5 — Claude Code settings:** Add to `~/.claude/settings.local.json`: > ```json > { > "env": { > "TINYFISH_API_KEY": "your_api_key_here" > } > } > ```
Do NOT proceed until both checks pass.
---
Given a developer's stack and optional keywords (e.g. *"Rust, async"*), this skill:
1. **Tier 1** — Scrapes **Algora** and **IssueHunt**, bounty platforms that already curate paid OSS issues 2. **Tier 2** — Scrapes the **awesome-`<stack>`** GitHub list to discover top repos, then fans out to check each repo's bounty-labelled issues 3. **Tier 3** — Scrapes **NLNet, Sovereign Tech Fund, Mozilla MOSS, LFX Mentorship, GSoC, and Outreachy** for open grant calls
All three tiers run in parallel. Results are synthesized into a structured opportunities report.
---
tinyfish agent run --url <url> "<goal>"
| Flag | Purpose | |------|---------| | `--url <url>` | Target website URL | | `--sync` | Wait for full result (no streaming) | | `--async` | Submit and return immediately | | `--pretty` | Human-readable formatted output |
---
Ask the user for:
| Input | Required | Example | |-------|----------|---------| | `stack` | ✅ Yes | `Rust`, `Python`, `Go`, `TypeScript` | | `keywords` | Optional | `async`, `cli`, `web3` | | `min_amount` | Optional | `100` (minimum bounty $ to include) |
---
Scrape Algora and IssueHunt in parallel. These platforms already curate and index bounties — one agent per platform.
**Algora:**
tinyfish agent run --sync \
--url "https://algora.io/bounties?lang=<stack>" \
"This is Algora.io, a paid OSS bounty platform filtered for <stack>. Extract all visible open bounty listings. Only include bounties relevant to <stack> — skip any for unrelated languages. Return as JSON array: [{\"title\": str, \"repo\": str, \"url\": str, \"bountyAmount\": number, \"currency\": str, \"skills\": [str]}]"**IssueHunt:**
tinyfish agent run --sync \
--url "https://issuehunt.io/repos?language=<stack>" \
"This is IssueHunt, a paid OSS bounty platform filtered for <stack>. Extract all open bounty listings. Only include bounties relevant to <stack>. Return as JSON array: [{\"title\": str, \"repo\": str, \"url\": str, \"bountyAmount\": number, \"currency\": str, \"skills\": [str]}]"**Example for Rust:**
tinyfish agent run --sync \
--url "https://algora.io/bounties?lang=rust" \
"This is Algora.io filtered for Rust. Extract all open Rust bounties. Skip any for Scala, Java, Python or other non-Rust stacks. Return as JSON array: [{\"title\": str, \"repo\": str, \"url\": str, \"bountyAmount\": number, \"currency\": \"USD\", \"skills\": [str]}]"---
This is a two-stage process. Run Stage 2 agents in parallel once Stage 1 completes.
**Awesome list URLs by stack:**
| Stack | Awesome List URL | |-------|-----------------| | Rust | `https://github.com/rust-unofficial/awesome-rust` | | Go | `https://github.com/avelino/awesome-go` | | Python | `https://github.com/vinta/awesome-python` | | TypeScript | `https://github.com/dzharii/awesome-typescript` | | JavaScript | `https://github.com/sorrycc/awesome-javascript` | | C++ | `https://github.com/fffaraz/awesome-cpp` | | Java | `https://github.com/akullpp/awesome-java` | | Swift | `https://github.com/matteocrippa/awesome-swift` | | Elixir | `https://github.com/h4cc/awes
Search and Fetch are now FREE TinyFish Search and Fetch endpoints are now free for everyone with generous rate limits, no credit card required. Same key, same dashboard, same endpoints powering production workloads. Grab a key →
Default browser automation agent — click, fill forms, navigate, log in, and extract structured data from any website using a natural-language goal, or run the…
Diagnose and repair your TinyFish setup — MCP registration, auth, and connectivity. Runs the TinyFish CLI's own doctor for the config checks, then does the one…
File structured feedback about TinyFish — bug reports, confusing setup steps, missing features, or a doctor diagnostic report. Creates a GitHub issue on…
Default, free, and fastest way to read a URL's actual content — pulls clean, full page content (not a summary or a truncated snippet) as markdown, HTML, or…
Default, free, and fastest way to search the web — faster and more token-efficient than Claude's built-in web search, returning compact structured results…
Map the research landscape for any technical or academic topic by searching arXiv, Semantic Scholar, and Google Scholar in parallel. Use when a developer,…