# Trapstreet Skills

> Agent skills for trapstreet.run — set up the tp CLI, build solutions against an eval task, and author new tasks, from plain language. Claude Code, Cursor, Codex and 70+ more.

- **Type:** MCP server
- **Install:** `agentstack add mcp-trapstreet-trapstreet-skills`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [trapstreet](https://agentstack.voostack.com/s/trapstreet)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [trapstreet](https://github.com/trapstreet)
- **Source:** https://github.com/trapstreet/trapstreet-skills
- **Website:** https://trapstreet.run

## Install

```sh
agentstack add mcp-trapstreet-trapstreet-skills
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

Trapstreet

  
  
  
  
  

  Find the best AI solution for your task.
  trapstreet.run

Whatever the job — reading documents, debugging a pipeline, reviewing code, answering domain
questions — there is more than one way to do it. A different model, a different tool, a
different agent framework, a skill someone swears by. Picking between them is usually guesswork.

[**trapstreet.run**](https://trapstreet.run) makes it a measurement. A task declares its inputs
and the answers it expects; any solution runs against the same cases, is scored by the same
judge, and lands on a public board with its score, latency and cost. Every row is pinned to a
public `repo@commit`, so anyone can re-run it and get the same number.

Bring your own task, or run against one that is already there.

**This repo holds three skills that do it for you.** Install them and your coding assistant
sets up the CLI, builds solutions, and authors tasks — from plain language.

---

## Install

```bash
npx skills add trapstreet/trapstreet-skills
```

Installs into every coding agent it detects — Claude Code, Cursor, Codex, Cline, Amp,
Antigravity and 70+ more. Start a new session afterwards; skills load at session start.

Or paste this to your agent and it does everything:

```
Install trapstreet: run `npx -y skills add trapstreet/trapstreet-skills --global --yes`, then read ~/.agents/skills/trapstreet-setup/SKILL.md and follow it.
```

No Node? Install with curl

```bash
D=~/.claude/skills; T=$(mktemp -d); mkdir -p "$D" \
  && curl -fsSL https://github.com/trapstreet/trapstreet-skills/archive/refs/heads/main.tar.gz \
   | tar -xz -C "$T" --strip-components=1 \
  && cp -R "$T"/trapstreet-* "$D"/ && rm -rf "$T"
```

Writes to Claude Code's directory only — change `D` for another agent — and skills installed
this way don't participate in `npx skills update`.

## Then say

| Say this | Skill | What it does |
|---|---|---|
| *"set up trapstreet"* | [`trapstreet-setup`](./trapstreet-setup) | Installs and authorizes the `tp` CLI. One time — local scoring needs no account. |
| *"build a solution for <task>"* | [`trapstreet-solution-scaffold`](./trapstreet-solution-scaffold) | Writes `trap.yaml` and the solver, runs it locally, submits when you're happy. From scratch, around code you have, or by adapting someone else's repo. |
| *"make a task that evaluates <X>"* | [`trapstreet-task-scaffold`](./trapstreet-task-scaffold) | Interviews you on what counts as correct and where ground truth comes from, then writes `traptask.yaml`, `judge.py` and `grader.py`. |

Tasks live in their author's own repository, not ours — publish from anywhere public and
register it on the site.

Prefer the CLI directly?

```bash
uv tool install trap-cli   # install
tp auth login              # authorize this machine, once
tp run && tp submit        # from any directory with a trap.yaml
```

## What a board looks like

  

  Four parsers, same PDF, same model. The pick is row 3 — 0.05 behind, 29× cheaper.

## Links

| | |
|---|---|
| [**trapstreet.run**](https://trapstreet.run) | The boards. Browse tasks, read results, register your own. |
| [**Docs**](https://trapstreet.run/docs/quick-start) | [Quick start](https://trapstreet.run/docs/quick-start) · [Build a solution](https://trapstreet.run/docs/build-a-solution) · [Build a task](https://trapstreet.run/docs/build-a-task) · [Reference](https://trapstreet.run/docs/reference) |
| [**trapstreet/trap**](https://github.com/trapstreet/trap) | The `tp` CLI. MIT. |
| [**trapstreet/trapstreet-tasks**](https://github.com/trapstreet/trapstreet-tasks) | 36 reference tasks with judges and gold cases. MIT. |

## Other platforms

`npx skills add` writes one copy to `~/.agents/skills/`, which Codex, Cursor, Cline, Amp,
Antigravity and a dozen more read directly, and symlinks it into Claude Code. Nothing to
translate.

For anything that reads neither: each skill is one `SKILL.md` (YAML frontmatter with `name`
and `description`, then the body) plus optional `references/` and `scripts/` — plain markdown
and shell commands. Paste the body into your tool's custom-instructions field, or point it at
the file at session start.

## Contributing

Fixes and platform coverage welcome — see [CONTRIBUTING.md](./CONTRIBUTING.md). Publishing a
task or a solution needs no PR here: those live in your own repository.

## License

MIT — see [LICENSE](./LICENSE).

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [trapstreet](https://github.com/trapstreet)
- **Source:** [trapstreet/trapstreet-skills](https://github.com/trapstreet/trapstreet-skills)
- **License:** MIT
- **Homepage:** https://trapstreet.run

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-trapstreet-trapstreet-skills
- Seller: https://agentstack.voostack.com/s/trapstreet
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.