# Dde Ext Search First

> DDE subordinate extension. Research-before-implementation workflow for dependency/library/approach selection. Can execute discovery commands, but cannot bypass DDE write gates.

- **Type:** Skill
- **Install:** `agentstack add skill-leslielinxinxiang-dde-agent-skills-dde-ext-search-first`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [LeslieLinXinxiang](https://agentstack.voostack.com/s/leslielinxinxiang)
- **Installs:** 0
- **Category:** [Search](https://agentstack.voostack.com/c/search)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [LeslieLinXinxiang](https://github.com/LeslieLinXinxiang)
- **Source:** https://github.com/LeslieLinXinxiang/dde-agent-skills/tree/main/skills/dde-ext-search-first

## Install

```sh
agentstack add skill-leslielinxinxiang-dde-agent-skills-dde-ext-search-first
```

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

## About

# DDE Extension: Search First

Skill Version: v0.1

## Authority Chain
- Commander: `dde-bootstrap`
- Write gate: `dde-code-guard`
- This skill is subordinate and cannot override Layer 0-4 docs.

## When to Use
- User asks to add a new feature likely having existing solutions.
- User asks to introduce dependencies, tools, or wrappers.
- DDE workflow requests pre-implementation research.

## Execution Scope
Allowed:
- Repo scan (`rg`, file reads, dependency inspection)
- External package/options comparison
- Produce recommendation matrix: Adopt / Extend / Build
- Run non-destructive checks

Not allowed:
- No direct requirement mutation
- No bypass of RFC flow
- No direct code write without DDE gate

## Mandatory Flow
1. Clarify target capability and constraints.
2. Search existing in-repo implementation first.
3. Search external maintained options.
4. Produce a ranked recommendation with tradeoffs.
5. If recommendation requires file changes, emit handoff:

`DDE_EXTENSION_HANDOFF_REQUIRED`

Handoff fields:
- Reason
- Target files
- Expected effect
- Risk notes

Then stop and re-enter `dde-code-guard` two-phase approval.

## Output Contract
- Short decision summary
- Candidate table (name, maturity, fit, risk)
- Final recommendation
- Handoff block if writes are required

## Source & license

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

- **Author:** [LeslieLinXinxiang](https://github.com/LeslieLinXinxiang)
- **Source:** [LeslieLinXinxiang/dde-agent-skills](https://github.com/LeslieLinXinxiang/dde-agent-skills)
- **License:** MIT

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-leslielinxinxiang-dde-agent-skills-dde-ext-search-first
- Seller: https://agentstack.voostack.com/s/leslielinxinxiang
- 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%.