Token导航 LogoToken导航

Agent Skill · 研究检索

pact-prepare-research(协议准备研究)

pact-prepare-research 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。

pact-prepare-research 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 59,000。

总安装 396周安装 17GitHub Stars 62下载 139核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:pact-prepare-research(协议准备研究)
来源仓库:https://github.com/profsynapse/pact-plugin
仓库路径:skills/pact-prepare-research
安装命令:
npx skills add https://github.com/profsynapse/pact-plugin --skill pact-prepare-research
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/profsynapse/pact-plugin --skill pact-prepare-research

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

pact-prepare-research 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。它适用于研究检索类任务,可结合来源仓库和原始 README 核验具体用法。

安装方式:通过 npx skills add 命令从 GitHub 仓库安装。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。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。

来源仓库内路径:skills/pact-prepare-research

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/profsynapse/pact-plugin --skill pact-prepare-r…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

pact-prepare-research 怎么安装?

在终端执行 npx skills add https://github.com/profsynapse/pact-plugin --skill pact-prepare-research。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

pact-prepare-research 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

pact-prepare-research 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

pact-prepare-research 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

pact-prepare-research 用的人多吗?

公开数据是累计安装 396 次,近一周安装 17 次,下载 139 次,GitHub 62 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

pact-prepare-research 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
pact-prepare-research

协议准备研究 · 本页

39662接触敏感数据未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

PACT Prepare Research Methodology

Structured approaches for the Prepare phase of PACT. This skill provides frameworks for systematic research, documentation gathering, and technology evaluation to build a solid foundation before architecture and implementation.

Research Workflow

Phase 1: Define Research Scope

Before starting research, clearly define:

## Research Scope Definition

### Primary Question
What specific problem are we trying to solve?

### Success Criteria
What would make a solution acceptable?
- [ ] Performance requirements
- [ ] Integration requirements
- [ ] Security requirements
- [ ] Budget constraints

### Constraints
What limitations must we work within?
- Technology stack restrictions
- Team expertise
- Timeline
- Licensing requirements

Phase 2: Source Prioritization

Prioritize sources by authority and reliability:

PrioritySource TypeExamplesTrust Level
1Official documentationDocs, API referencesHighest
2Official repositoriesGitHub READMEs, wikisVery High
3Maintainer contentBlog posts by core teamHigh
4Community verifiedStack Overflow accepted answersMedium
5Third-party tutorialsBlog posts, videosLow-Medium
6AI-generated contentChatGPT, CopilotVerify Required

Source Verification Checklist:

  • Publication date within 12 months (for version-specific info)
  • Author has verifiable credentials
  • Information matches official docs
  • Code examples actually work

Phase 3: Documentation Types to Gather

Collect these documentation types for complete understanding:

1. API References

## API Documentation Checklist
- [ ] Authentication methods
- [ ] Rate limits and quotas
- [ ] Available endpoints
- [ ] Request/response formats
- [ ] Error codes and handling
- [ ] SDK availability
- [ ] Webhook support

2. Configuration Guides

## Configuration Documentation
- [ ] Environment variables
- [ ] Configuration file formats
- [ ] Default values
- [ ] Required vs optional settings
- [ ] Security-sensitive configs

3. Migration Documentation

## Migration Considerations
- [ ] Breaking changes between versions
- [ ] Deprecation timelines
- [ ] Migration guides
- [ ] Data migration requirements

4. Security Advisories

## Security Documentation
- [ ] Known vulnerabilities (CVEs)
- [ ] Security best practices
- [ ] Authentication requirements
- [ ] Data handling guidelines

Phase 4: Evaluation Criteria

Use this framework to evaluate research findings:

CriterionQuestionsWeight
CurrencyUpdated within 12 months? Active development?High
AuthorityOfficial source? Maintainer authored?High
CompletenessCovers required use cases?Medium
PracticalityActionable? Working examples?Medium
CompatibilityWorks with existing stack?High
CommunityActive community? Good support?Medium
SecuritySecurity track record? Quick patches?High

Quick Reference Templates

Technology Comparison

For structured side-by-side comparisons: See technology-comparison-matrix.md

Quick Comparison Template:

| Criterion | Option A | Option B | Winner |
|-----------|----------|----------|--------|
| Learning curve | Steep | Gentle | B |
| Performance | Fast | Very Fast | B |
| Documentation | Good | Excellent | B |
| Community size | Large | Medium | A |
| **Total** | 1 | 3 | **B** |

API Documentation Summary

For capturing API details systematically: See api-exploration-template.md

Quick API Summary:

## API: [Name]

**Base URL**: `https://api.example.com/v1`
**Auth**: Bearer token in header
**Rate Limit**: 100 req/min

### Key Endpoints
| Endpoint | Method | Purpose |
|----------|--------|---------|
| /users | GET | List users |
| /users/:id | GET | Get user |
| /users | POST | Create user |

### Authentication

curl -H "Authorization: Bearer YOUR_TOKEN" \ https://api.example.com/v1/users

Requirements Analysis

For comprehensive requirements documentation: See requirements-analysis.md

Quick Requirements Template:

## Feature: [Name]

### User Story
As a [user type], I want [action] so that [benefit].

### Acceptance Criteria
- [ ] Given [context], when [action], then [result]
- [ ] Given [context], when [action], then [result]

### Technical Requirements
- Performance: [target]
- Security: [requirements]
- Integration: [dependencies]

### Dependencies
- Depends on: [other features/services]
- Blocked by: [blockers]

Research Output Format

Standard Research Document Structure

# Research: [Topic]

## Executive Summary
[2-3 sentence summary of findings and recommendation]

## Background
[Why this research was needed]

## Methodology
[How research was conducted]

## Findings

### Option 1: [Name]
**Pros:**
- [Pro 1]
- [Pro 2]

**Cons:**
- [Con 1]
- [Con 2]

**Evidence:**
- [Link to source]
- [Link to source]

### Option 2: [Name]
[Same structure]

## Comparison Matrix
[Side-by-side comparison table]

## Risk Assessment
| Risk | Probability | Impact | Mitigation |
|------|-------------|--------|------------|
| [Risk] | High/Med/Low | High/Med/Low | [Strategy] |

## Recommendation
[Clear recommendation with rationale]

## Next Steps
1. [Action item]
2. [Action item]

## References
- [Source 1]
- [Source 2]

Quality Checklist

Before completing Prepare phase research:

Source Quality

  • All critical information from official sources
  • Version numbers explicitly stated
  • Publication dates verified (within 12 months for technical details)
  • No single point of information failure (multiple sources for key facts)

Completeness

  • All evaluation criteria addressed
  • Alternatives presented with pros/cons
  • Security implications documented
  • Performance characteristics noted
  • Integration requirements identified

Actionability

  • Recommendations backed by evidence
  • Next steps clearly defined
  • Risks identified with mitigations
  • Dependencies mapped

Documentation

  • Research document follows standard structure
  • All sources linked and accessible
  • Key decisions documented with rationale
  • Output saved to docs/{feature}/preparation/

Common Research Patterns

Library/Framework Selection

  1. Define requirements and constraints
  2. Identify 3-5 candidates
  3. Evaluate against criteria matrix
  4. Prototype with top 2 candidates
  5. Document decision rationale

API Integration Research

  1. Gather official API documentation
  2. Test authentication flow
  3. Document all required endpoints
  4. Identify rate limits and quotas
  5. Plan error handling strategy

Technology Migration

  1. Document current state
  2. Research target technology
  3. Identify breaking changes
  4. Plan migration path
  5. Define rollback strategy

Detailed References

For comprehensive templates and frameworks:

- Full API documentation template - Authentication testing guide - Error handling documentation

- User story templates - Acceptance criteria patterns - Non-functional requirements

- Weighted scoring templates - Multi-criteria decision analysis - Risk assessment frameworks

平台分布

Codex

37.6%
按下载量换算52

Claude

30.24%
按下载量换算42

Cursor

18.99%
按下载量换算26

Gemini CLI

10.04%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills