Token导航 LogoToken导航TokenDH.com
研究检索执行命令github未标认证来源可访问clear审计未展示

ideationideation 搜索

Agent Skill

ideation 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

1,270

周安装

54

GitHub Stars

公开资料未说明

下载量

445
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

2

许可证

MIT

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:ideation(ideation 搜索)
来源仓库:https://github.com/nicknisi/claude-plugins
仓库路径:skills/ideation
安装命令:
npx skills add nicknisi/claude-plugins --skill "ideation"
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。

AgentSkills.tonpx skills
npx skills add nicknisi/claude-plugins --skill "ideation"

简介

用于查找、检索和筛选相关信息,支持基于关键词和任务场景的搜索。

  • 适合在多种宿主环境中快速定位候选结果。
  • 可结合来源仓库和原始文档核验具体功能。
  • 安装前建议确认权限范围和维护状态。ideation 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 注意是否涉及联网、命令执行或文件访问。

SKILL.md

name
ideation
description
Transform raw brain dumps (dictated freestyle) into structured implementation artifacts. Use when user has messy ideas, scattered thoughts, or dictated stream-of-consciousness about something they want to build. Produces contracts, phased PRDs, and implementation specs written to ./docs/ideation/{project-name}/.

Ideation

Transform unstructured brain dumps into structured, actionable implementation artifacts through a confidence-gated workflow.

Critical: Use AskUserQuestion Tool

ALWAYS use the AskUserQuestion tool when asking clarifying questions. Do not ask questions in plain text. The tool provides structured options and ensures the user can respond clearly.

Use AskUserQuestion for:

  • Clarifying questions during confidence scoring (Phase 2)
  • Project name confirmation before writing artifacts
  • Contract approval before PRD generation
  • PRD review feedback before spec generation
  • Any decision point requiring user input

Workflow Pipeline

INTAKE → CONTRACT FORMATION → PRD GENERATION → SPEC GENERATION → EXECUTION HANDOFF
              ↓                                                        ↓
         confidence < 95%?                                     [Fresh Session]
              ↓                                                        ↓
         ASK QUESTIONS                                         /execute-spec
              ↓                                                        ↓
         (loop until ≥95%)                                    Review → Test → Commit

Phase 1: Intake

Accept whatever the user provides:

  • Scattered thoughts and half-formed ideas
  • Voice dictation transcripts (messy, stream-of-consciousness)
  • Bullet points mixed with rambling
  • Topic jumping and tangents
  • Contradictions and unclear statements
  • Technical jargon mixed with vague descriptions

Don't require organization. The mess is the input.

Acknowledge receipt and begin analysis. Do not ask for clarification yet.

Phase 2: Contract Formation

2.1 Analyze the Brain Dump

Extract from the raw input:

  1. Problem signals: What pain point or need is being described?
  2. Goal signals: What does the user want to achieve?
  3. Success signals: How will they know it worked?
  4. Scope signals: What's included? What's explicitly excluded?
  5. Contradictions: Note any conflicting statements

2.2 Calculate Confidence Score

Load references/confidence-rubric.md for detailed scoring criteria.

Score each dimension (0-20 points):

DimensionQuestion
Problem ClarityDo I understand what problem we're solving and why it matters?
Goal DefinitionAre the goals specific and measurable?
Success CriteriaCan I write tests or validation steps for "done"?
Scope BoundariesDo I know what's in and out of scope?
ConsistencyAre there contradictions I need resolved?

Total: /100 points

2.3 Confidence Thresholds

ScoreAction
< 70Major gaps. Ask 5+ questions targeting lowest dimensions.
70-84Moderate gaps. Ask 3-5 targeted questions.
85-94Minor gaps. Ask 1-2 specific questions.
≥ 95Ready to generate contract.

2.4 Ask Clarifying Questions

When confidence < 95%, MUST use AskUserQuestion tool to ask clarifying questions. Structure questions with clear options when possible.

Using AskUserQuestion effectively:

  • Provide 2-4 options per question when choices are clear
  • Use multiSelect: true when multiple answers apply
  • Keep question headers short (max 12 chars)
  • Include descriptions that explain implications of each choice

Question strategy:

  • Target the lowest-scoring dimension first
  • Be specific, not open-ended
  • Offer options when possible ("Is it A, B, or C?")
  • Reference what was stated ("You mentioned X, did you mean...?")
  • Limit to 3-5 questions per round
  • After each round, recalculate confidence

Question templates by dimension:

Problem Clarity:

  • "What specific problem are you trying to solve?"
  • "Who experiences this problem and how often?"
  • "What's the cost of NOT solving this?"

Goal Definition:

  • "What does success look like for this project?"
  • "How will you measure whether this worked?"
  • "What specific metrics should improve?"

Success Criteria:

  • "How will you know when you're done?"
  • "What tests would prove this feature works?"
  • "What would a QA person check?"

Scope Boundaries:

  • "What is explicitly NOT part of this project?"
  • "Are there related features we should defer?"
  • "What's the MVP vs. nice-to-have?"

Consistency:

  • "You mentioned [X] but also [Y]. Which takes priority?"
  • "These requirements seem to conflict. Can you clarify?"
  • "How should we handle [edge case]?"

2.5 Generate Contract

When confidence ≥ 95%, generate the contract document.

  1. Use AskUserQuestion to confirm project name if not obvious from context
  2. Convert to kebab-case for directory name
  3. Create output directory: ./docs/ideation/{project-name}/
  4. Write contract.md using references/contract-template.md
  5. Use AskUserQuestion to get approval: "Does this contract accurately capture your intent?"

Do not proceed to PRD generation until contract is explicitly approved.

Phase 3: PRD Generation

After contract is approved:

3.1 Determine Phases

Analyze the contract and break scope into logical implementation phases.

Phasing criteria:

  • Dependencies (what must be built first?)
  • Risk (tackle high-risk items early)
  • Value delivery (can users benefit after each phase?)
  • Complexity (balance phases for consistent effort)

Typical phasing:

  • Phase 1: Core functionality / MVP
  • Phase 2: Enhanced features
  • Phase 3: Polish and optimization
  • Phase N: Future considerations

3.2 Generate PRDs

For each phase, generate prd-phase-{n}.md using references/prd-template.md.

Include:

  • Phase overview and rationale
  • User stories for this phase
  • Functional requirements (grouped)
  • Non-functional requirements
  • Dependencies (prerequisites and outputs)
  • Acceptance criteria

3.3 Present for Review

Show all PRDs to user. Use AskUserQuestion to gather feedback:

Question: "Do these PRD phases look correct?"
Options:
- "Approved" - Phases and requirements look good, proceed to specs
- "Adjust phases" - Need to move features between phases
- "Missing requirements" - Some requirements are missing or unclear
- "Start over" - Need to revisit the contract

Iterate until user explicitly approves.

Phase 4: Spec Generation

After PRDs are approved:

4.1 Generate Implementation Specs

For each approved phase, generate spec-phase-{n}.md using references/spec-template.md.

Include:

  • Technical approach
  • File changes (new and modified)
  • Implementation details with code patterns
  • Testing requirements
  • Error handling
  • Validation commands

4.2 Final Review

Present specs to user. Proceed to execution handoff.

Phase 5: Execution Handoff

After specs are generated, create task list and hand off for implementation.

5.1 Create Task List

Generate a unique task list ID and create initial phase tasks:

// Generate unique ID
const taskListId = `{project-name}-${Date.now()}`;

// Create phase tasks with dependencies
TaskCreate({
  subject: "Phase 1: {phase title from PRD}",
  description: "Execute spec-phase-1.md",
  activeForm: "Implementing Phase 1",
  metadata: { phase: 1, specFile: "spec-phase-1.md" }
});

// Phase 2 blocked by Phase 1
TaskCreate({
  subject: "Phase 2: {phase title}",
  description: "Execute spec-phase-2.md",
  activeForm: "Implementing Phase 2",
  metadata: { phase: 2, specFile: "spec-phase-2.md" }
});

TaskUpdate({
  taskId: "{phase2-id}",
  addBlockedBy: ["{phase1-id}"]
});

5.2 Write Tasks Manifest

Create ./docs/ideation/{project-name}/tasks-manifest.md:

# Tasks Manifest

**Task List ID:** `{task-list-id}`
**Created:** {timestamp}
**Project:** {project-name}

## Quick Start

Start fresh session with task tracking

CLAUDE_CODE_TASK_LIST_ID={task-list-id} claude


Then run: `/execute-spec docs/ideation/{project-name}/spec-phase-1.md`

## Phases

| Phase | Status | Spec File |
|-------|--------|-----------|
| 1 | pending | spec-phase-1.md |
| 2 | blocked | spec-phase-2.md |
| ... | ... | ... |

## Cross-Session Coordination

Tasks sync automatically across Claude sessions. To work in parallel:

Terminal 1

CLAUDE_CODE_TASK_LIST_ID={task-list-id} claude

Work on independent Component A

Terminal 2

CLAUDE_CODE_TASK_LIST_ID={task-list-id} claude

Work on independent Component B


Check progress anytime with `TaskList`.

5.3 Present Handoff Summary

Ideation complete. Artifacts written to `./docs/ideation/{project-name}/`.

## Execution Ready

Task list created: `{task-list-id}`

**To implement with shared task tracking:**

CLAUDE_CODE_TASK_LIST_ID={task-list-id} claude


Then run: `/execute-spec docs/ideation/{project-name}/spec-phase-1.md`

**For parallel execution (multiple terminals):**

Terminal 1

CLAUDE_CODE_TASK_LIST_ID={task-list-id} claude

Work on Component A

Terminal 2

CLAUDE_CODE_TASK_LIST_ID={task-list-id} claude

Work on Component B (if independent)


Tasks sync automatically across sessions.

5.4 Why Fresh Sessions?

  • Ideation consumes significant context (contract, PRDs, specs)
  • Execution benefits from clean context focused on the spec
  • Human review between phases catches issues early
  • Each phase is independently committable
  • Task list persists - progress isn't lost between sessions

Output Artifacts

All artifacts written to ./docs/ideation/{project-name}/:

contract.md              # Lean contract (problem, goals, success, scope)
prd-phase-1.md           # Phase 1 requirements
prd-phase-2.md           # Phase 2 requirements (if applicable)
...
spec-phase-1.md          # Phase 1 implementation spec
spec-phase-2.md          # Phase 2 implementation spec
...
tasks-manifest.md        # Task list ID and cross-session coordination info

Bundled Resources

References

  • references/contract-template.md - Template for lean contract document
  • references/prd-template.md - Template for phased PRD documents
  • references/spec-template.md - Template for implementation specs
  • references/confidence-rubric.md - Detailed scoring criteria for confidence assessment

Workflow Example

User provides brain dump (via dictation):

okay so i'm thinking about this feature where users can like save their
favorite items you know like bookmarking but also they should be able to
organize them into folders or something maybe tags actually tags might be
better because folders are too rigid and oh we should probably have a
search too because if they have a lot of bookmarks it'll be hard to find
anything and maybe some kind of sharing eventually but that's probably
phase 2 or something and it should work offline too because people might
be on planes or whatever and sync when they come back online

Process:

  1. Intake: Accept without judgment
  1. Analysis:

- Problem: Users need to save and organize content - Goals: Save items, organize with tags, search, offline support - Unclear: What items? Why tags > folders? Sharing scope? Offline priority? - Confidence: ~55/100 (low problem clarity, unclear scope)

  1. Questions (round 1):

- "What type of items are users bookmarking? Articles, products, posts?" - "You mentioned tags over folders. Should tags be user-created or predefined?" - "Is offline support MVP or can it wait for phase 2?" - "When you say 'sharing eventually,' what does that look like?"

  1. User responds → Recalculate confidence → Repeat if needed
  1. Confidence reaches 96% → Generate contract
  1. Contract approved → Generate PRDs:

- Phase 1: Core bookmarking with tags - Phase 2: Search and filtering - Phase 3: Offline support - Phase 4: Sharing (future)

  1. PRDs approved → Generate specs for each phase
  1. Execution handoff: Summarize artifacts and next steps for fresh-session execution
  1. Implementation (fresh sessions): For each phase:

- Start fresh Claude session - Run /execute-spec spec-phase-{n}.md - Review, test, commit - Repeat for next phase

Important Notes

  • ALWAYS use AskUserQuestion tool for clarifications and approvals. Never ask questions in plain text.
  • Never skip the confidence check. Don't assume understanding.
  • Always write artifacts to files. Don't just display them.
  • Each phase should be independently valuable.
  • Specs should be detailed enough to implement without re-reading PRDs.
  • Keep contracts lean. Heavy docs slow iteration.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

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

Claude Code

30.35%
按下载量换算135

OpenCode

24.12%
按下载量换算107

Antigravity

18.77%
按下载量换算84

Codex

11.58%
按下载量换算52

Gemini CLI

8.81%
按下载量换算39

windsurf

3.33%
按下载量换算15

安全审计

暂无安全审计结果可展示。

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add nicknisi/claude-plugins --skill "ideation" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。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

继续浏览同类 Skills