# Ducktap Score

> Run the DuckTap scorecard against a generated CLI and explain the breakdown.

- **Type:** Skill
- **Install:** `agentstack add skill-zanni098-ducktap-ducktap-score`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [zanni098](https://agentstack.voostack.com/s/zanni098)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [zanni098](https://github.com/zanni098)
- **Source:** https://github.com/zanni098/DuckTap/tree/main/skills/ducktap-score
- **Website:** https://duck-tap.vercel.app

## Install

```sh
agentstack add skill-zanni098-ducktap-ducktap-score
```

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

## About

# /ducktap-score

```bash
/ducktap-score petstore
```

Runs `ducktap scorecard out/petstore.spec.json --out-dir ./out` and explains each
dimension (coverage, documentation, auth, typed_params, artifacts, naming,
domain_correctness). Suggest 1-3 concrete fixes for the lowest-scoring dimensions.

Pass `--fail-under ` to make the command exit non-zero below a threshold, which is
how it is used in CI.

For a stronger signal than the scorecard, run `ducktap verify  --source `:
it mechanically checks the generated CLI against the spec (no hallucinated paths, every
operation reachable, auth header matches, no write-only mirror tables).

## Source & license

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

- **Author:** [zanni098](https://github.com/zanni098)
- **Source:** [zanni098/DuckTap](https://github.com/zanni098/DuckTap)
- **License:** MIT
- **Homepage:** https://duck-tap.vercel.app

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:** no
- **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/skill-zanni098-ducktap-ducktap-score
- Seller: https://agentstack.voostack.com/s/zanni098
- 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%.