研究检索只读github未标认证来源可访问许可证需确认审计提醒

concept-dev（概念开发）

Agent Skill

concept-dev 用于查找、检索和筛选相关信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

总安装

423

周安装

GitHub Stars

下载量

148

CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息，不托管安装包，也不代用户安装。

GitHub

来源数

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手，先确认命令和权限，再让它执行。

请帮我安装这个 Agent Skill：concept-dev（概念开发）
来源仓库：https://github.com/ddunnock/claude-plugins
仓库路径：skills/concept-dev
安装命令：
npx skills add https://github.com/ddunnock/claude-plugins --skill concept-dev
安装前请先检查当前环境是否支持对应 CLI，并向我确认将要执行的命令、安装目录、联网范围和文件读写权限；确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill；本站只展示命令，不托管安装包，也不自动执行。

skills.shnpx skills

npx skills add https://github.com/ddunnock/claude-plugins --skill concept-dev

简介

concept-dev 引导完成 NASA Phase A 级别的概念开发流程，产出工程技术白皮书。

适用于 Codex、Claude、Cursor、Gemini CLI 中从零构建解决方案选项与成熟路径。
保持解法 agnostic 直至细化阶段，确保问题定义准确性与方案多样性。
安装前请确认是否引用航天标准、生成专利敏感内容或用于政府资助项目文档。
适用宿主包括 Codex、Claude、Cursor、Gemini CLI，接入前应确认版本、权限和运行环境要求。

SKILL.md

Concept Development (NASA Phase A)

Walk users through the engineering concept lifecycle — from wild ideas to a polished concept document with cited research. The process remains solution-agnostic through most phases, identifying solution OPTIONS (not picking them) only at the drill-down phase.

Overview

This skill produces two deliverables:

Concept Document — Problem, concept, capabilities, ConOps, maturation path (modeled on engineering concept papers)
Solution Landscape — Per-domain approaches with pros/cons, cited references, confidence ratings

The five phases build progressively:

Spit-Ball — Open-ended ideation with feasibility probing
Problem Definition — Refine ideas into a clear, bounded problem statement
Black-Box Architecture — Define functional blocks, relationships, and principles without implementation
Drill-Down — Decompose blocks, research domains, identify gaps, list solution approaches with citations
Document — Generate final deliverables with section-by-section approval

Phases

Phase 1: Spit-Ball (`/concept:spitball`)

Open-ended exploration. User throws out wild ideas; Claude probes feasibility via WebSearch, asks "what if" questions, captures ideas with feasibility notes. No structure imposed. After accumulating feasibility notes, the skeptic agent reviews all claims before theme clustering. Gate: user selects which themes have energy.

Phase 2: Problem Definition (`/concept:problem`)

Refine viable ideas into a clear problem statement using adapted 5W2H questioning. Metered questioning (4 questions then checkpoint). Solution ideas captured but deferred to Phase 4. Gate: user approves problem statement.

Phase 3: Black-Box Architecture (`/concept:blackbox`)

Define concept at functional level — blocks, relationships, principles — without specifying implementation. Claude proposes 2-3 approaches with trade-offs, user selects, Claude elaborates with ASCII diagrams. Gate: user approves architecture section by section.

Phase 4: Drill-Down & Gap Analysis (`/concept:drilldown`)

Decompose each functional block to next level. For each: research domains, identify gaps, list potential solution APPROACHES (not pick them) with cited sources. Supports AUTO mode for autonomous research. Gate: user reviews complete drill-down.

Phase 5: Document Generation (`/concept:document`)

Produce Concept Document and Solution Landscape. Section-by-section user approval. Mandatory assumption review before finalization. Gate: user approves both documents.

Commands

Command	Description	Reference
`/concept:init`	Initialize session, detect research tools	concept.init.md
`/concept:spitball`	Phase 1: Wild ideation	concept.spitball.md
`/concept:problem`	Phase 2: Problem definition	concept.problem.md
`/concept:blackbox`	Phase 3: Black-box architecture	concept.blackbox.md
`/concept:drilldown`	Phase 4: Drill-down + gap analysis	concept.drilldown.md
`/concept:document`	Phase 5: Generate deliverables	concept.document.md
`/concept:research`	Web research with crawl4ai	concept.research.md
`/concept:status`	Session status dashboard	concept.status.md
`/concept:resume`	Resume interrupted session	concept.resume.md

Scripts

Script	Purpose	Usage
`init_session.py`	Create workspace + init state	`python3 ${CLAUDE_PLUGIN_ROOT}/scripts/init_session.py [dir]`
`check_tools.py`	Detect research tool availability	`python3 ${CLAUDE_PLUGIN_ROOT}/scripts/check_tools.py`
`update_state.py`	Atomic state.json updates	`python3 ${CLAUDE_PLUGIN_ROOT}/scripts/update_state.py show`
`source_tracker.py`	Manage source registry	`python3 ${CLAUDE_PLUGIN_ROOT}/scripts/source_tracker.py list`
`assumption_tracker.py`	Track assumptions	`python3 ${CLAUDE_PLUGIN_ROOT}/scripts/assumption_tracker.py review`
`web_researcher.py`	Crawl4ai web research	`python3 ${CLAUDE_PLUGIN_ROOT}/scripts/web_researcher.py crawl <url> --query "..."`

Quick Reference

State file: .concept-dev/state.json
Output directory: .concept-dev/
Source registry: .concept-dev/source_registry.json
Assumption registry: .concept-dev/assumption_registry.json
Artifacts: IDEAS.md, PROBLEM-STATEMENT.md, BLACKBOX.md, DRILLDOWN.md, CONCEPT-DOCUMENT.md, SOLUTION-LANDSCAPE.md

Additional Resources

Reference Files

references/research-strategies.md — Tool tier definitions, search patterns, fallback chains
references/verification-protocol.md — Source confidence hierarchy and verification rules
references/questioning-heuristics.md — Adaptive questioning modes: open, metered, structured
references/concept-doc-structure.md — Target document structure for Phase 5
references/solution-landscape-guide.md — Neutral solution presentation rules

适合场景

用户想查找某类 Agent Skill 时

需要根据任务场景推荐可安装能力包时

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明，方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用；具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.52%

按下载量换算50

Claude

29.1%

按下载量换算43

Cursor

21.32%

按下载量换算32

Gemini CLI

9.47%

按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容，本身偏只读；真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息，不托管安装包，不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果，不能写成本站确认安全。当前只有一个来源，正式发布前建议补源仓库或其他目录站核验。

来源信息

GitHub 仓库

github.com

/ddunnock/claude-plugins

SKILL.md 来源

github.com

/ddunnock/claude-plugins/tree/main/skills/concept-dev

skills-sh

skills.sh

/ddunnock/claude-plugins/concept-dev

继续浏览同类 Skills

更多研究检索 Skills（73,675）返回 Skills 目录

上一个 Skill

conan-vcpkg（柯南 vcpkg）

conan-vcpkg 用于查找、检索和筛选相关信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

下一个 Skill

concept-development（概念发展）

concept-development 用于查找、检索和筛选相关信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。