# prospec

> prospec — benwu95-prospec. Use this tool when you need to streamline AI-driven development with Spec-Driven Development (SDD) and reduce token usage by 70-80%. It solves problems in brownfield and greenfield projects by integrating with AI coding agents like Claude Code, Copilot, and Codex, and accepts inputs via slash-commands and structured AI knowledge. Ideal for use with git, it provides a progressive disclosure interface for efficient development.

Canonical page: https://skillsregistry.net/skills/benwu95-prospec  
JSON: https://api.skillsregistry.net/v1/skills/benwu95-prospec

## Description

A shared, resumable AI development workflow backed by project-local specs, rules, and change records. Skills guide agents; the CLI handles deterministic steps.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/benwu95/prospec)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "benwu95-prospec"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/benwu95-prospec` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/benwu95-prospec/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt