Token导航 LogoToken导航

Agent Skill · 研究检索

rnd-eligibility-assessment(研究资格评估)

rnd-eligibility-assessment 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。

rnd-eligibility-assessment 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,权限为只读;许可证为 MIT,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 62,819。

总安装 326周安装 14GitHub Stars 4下载 114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
MIT

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:rnd-eligibility-assessment(研究资格评估)
来源仓库:https://github.com/cleanexpo/ato
仓库路径:skills/rnd-eligibility-assessment
安装命令:
npx skills add https://github.com/cleanexpo/ato --skill rnd-eligibility-assessment
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/cleanexpo/ato --skill rnd-eligibility-assessment

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。

用于研究资格评估,适合在 AI 编程环境中快速检索和筛选相关技术资料。支持基于关键词或任务场景定位候选结果,适用于项目前期调研阶段。通过 npx 命令从指定 GitHub 仓库安装,需确认权限与维护状态。使用前应核实是否会触发联网、文件读写或外部命令执行。

rnd-eligibility-assessment 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/rnd-eligibility-assessment

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/cleanexpo/ato --skill rnd-eligibility-assessme…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

rnd-eligibility-assessment 怎么安装?

在终端执行 npx skills add https://github.com/cleanexpo/ato --skill rnd-eligibility-assessment。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

rnd-eligibility-assessment 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。

rnd-eligibility-assessment 需要什么权限?

权限级别是只读。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。

rnd-eligibility-assessment 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

rnd-eligibility-assessment 用的人多吗?

公开数据是累计安装 326 次,近一周安装 14 次,下载 114 次,GitHub 4 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。

rnd-eligibility-assessment 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 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

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
rnd-eligibility-assessment

研究资格评估 · 本页

3264只读MIT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

R&D Eligibility Assessment Skill

Systematic methodology for assessing R&D Tax Incentive eligibility under Division 355 ITAA 1997.

When to Use

Activate this skill when the task requires:

  • Evaluating if activities qualify as R&D
  • Classifying core vs supporting R&D activities
  • Quantifying eligible R&D expenditure
  • Calculating potential tax offsets
  • Preparing registration documentation

Division 355 Framework

Legislative Structure

Division 355 - R&D Tax Incentive
├── Subdivision 355-A: Guide
├── Subdivision 355-B: Entitlement to tax offset
│   ├── s 355-100: Tax offset for R&D entities
│   └── s 355-105: Amount of tax offset
├── Subdivision 355-C: Core R&D activities
│   └── s 355-25: Core R&D activity definition
├── Subdivision 355-D: Supporting R&D activities
│   └── s 355-30: Supporting R&D activity definition
├── Subdivision 355-E: Notional deductions
│   ├── s 355-200: R&D expenditure
│   └── s 355-205: Decline in value of R&D assets
└── Subdivision 355-F: Clawback provisions

Core R&D Activity Test (s 355-25)

The Four Requirements

An activity is a core R&D activity if it meets ALL of these:

┌──────────────────────────────────────────────────────────────────┐
│ ELEMENT 1: EXPERIMENTAL ACTIVITIES                               │
│                                                                  │
│ "Activities whose outcome cannot be known or determined in       │
│ advance on the basis of current knowledge, information or        │
│ experience, but can only be determined by applying a systematic  │
│ progression of work..."                                          │
│                                                                  │
│ Test Questions:                                                  │
│ □ Is there genuine technical uncertainty?                        │
│ □ Could a competent professional determine the outcome in        │
│   advance using existing knowledge?                              │
│ □ Is experimentation required to resolve the uncertainty?        │
└──────────────────────────────────────────────────────────────────┘
                              ↓
┌──────────────────────────────────────────────────────────────────┐
│ ELEMENT 2: SYSTEMATIC PROGRESSION OF WORK                        │
│                                                                  │
│ Work that:                                                       │
│ (a) proceeds from hypothesis to experiment                       │
│ (b) involves observation and evaluation                          │
│ (c) leads to logical conclusions                                 │
│                                                                  │
│ Test Questions:                                                  │
│ □ Was there a defined hypothesis or theory?                      │
│ □ Were experiments conducted methodically?                       │
│ □ Were results observed and evaluated?                           │
│ □ Were conclusions drawn from the work?                          │
└──────────────────────────────────────────────────────────────────┘
                              ↓
┌──────────────────────────────────────────────────────────────────┐
│ ELEMENT 3: PURPOSE - GENERATING NEW KNOWLEDGE                    │
│                                                                  │
│ Conducted for the purpose of generating new knowledge:           │
│ (a) new knowledge in any field                                   │
│ (b) including new or improved materials, products, devices,      │
│     processes or services                                        │
│                                                                  │
│ Test Questions:                                                  │
│ □ Is the outcome new to the field (not just to the company)?     │
│ □ Does it advance technical knowledge?                           │
│ □ Is it creating genuinely new capability?                       │
└──────────────────────────────────────────────────────────────────┘
                              ↓
┌──────────────────────────────────────────────────────────────────┐
│ ELEMENT 4: SCIENTIFIC METHOD (Principles)                        │
│                                                                  │
│ Based on principles of established science:                      │
│ - Uses scientific or technological principles                    │
│ - Follows rational, logical approach                             │
│ - Documents methodology and findings                             │
│                                                                  │
│ Test Questions:                                                  │
│ □ Is the work based on scientific/technical principles?          │
│ □ Is the methodology documented?                                 │
│ □ Are results recorded systematically?                           │
└──────────────────────────────────────────────────────────────────┘

Exclusions (s 355-25(2))

The following are NEVER core R&D activities:

❌ Market research, market testing, or sales promotion
❌ Quality control or routine testing
❌ Management studies or efficiency surveys
❌ Research in social sciences, arts, or humanities
❌ Mineral, petroleum, or gas exploration or extraction
❌ Commercial, legal, or administrative aspects of patenting
❌ Activities related to compliance with statutory requirements
❌ Development of internal administrative systems
❌ Developing, modifying, installing commercial software (routine)

Supporting R&D Activity Test (s 355-30)

An activity is a supporting R&D activity if:

Option 1: DIRECTLY RELATED
  - Directly related to core R&D activities

Option 2: DOMINANT PURPOSE
  - For the dominant purpose of supporting core R&D

Option 3: GOODS AND SERVICES
  - Producing goods or services to be used in core R&D

Note: Supporting activities must be reasonably proportioned to the core activities they support.

Assessment Methodology

Step 1: Activity Identification

Activity Template:
  name: "[Descriptive name]"
  description: "[What was done and why]"
  period: "[Date range of activity]"
  personnel: "[Who performed the work]"

  technical_uncertainty:
    - "[Uncertainty 1]"
    - "[Uncertainty 2]"

  hypothesis: "[Initial hypothesis or theory tested]"

  experiments:
    - "[Experiment 1 description]"
    - "[Experiment 2 description]"

  observations: "[Key observations from work]"

  conclusions: "[Conclusions reached]"

  new_knowledge: "[What new knowledge was generated]"

Step 2: Eligibility Scoring

For each activity, score against Division 355 criteria:

┌─────────────────────────────────────┬───────┬──────────┐
│ Criterion                           │ Score │ Evidence │
├─────────────────────────────────────┼───────┼──────────┤
│ Unknown outcome?                    │ 0-3   │          │
│ Systematic progression?             │ 0-3   │          │
│ New knowledge purpose?              │ 0-3   │          │
│ Scientific method?                  │ 0-3   │          │
├─────────────────────────────────────┼───────┼──────────┤
│ TOTAL                               │ /12   │          │
└─────────────────────────────────────┴───────┴──────────┘

Scoring Guide:
0 = Does not meet
1 = Partially meets
2 = Meets
3 = Strongly meets

Eligibility Assessment:
10-12: High confidence eligible
7-9:   Likely eligible, document well
4-6:   Uncertain, seek Finding
0-3:   Not eligible

Step 3: Expenditure Calculation

R&D Expenditure Categories:

1. SALARY & WAGES
   = (Employee annual salary × R&D time %)
   + Superannuation (11%)
   + Workers compensation
   + Payroll tax

2. CONTRACTOR PAYMENTS
   = Total payments to R&D contractors
   (Must be at arm's length)

3. DIRECT MATERIALS
   = Cost of materials consumed in R&D
   (Not assets, consumables only)

4. DEPRECIATION
   = Decline in value of R&D assets × R&D use %
   (Assets used predominantly for R&D)

5. OVERHEADS
   = Rent × R&D allocation %
   + Utilities × R&D allocation %
   + Other overheads × R&D allocation %

TOTAL R&D EXPENDITURE = Sum of above

Step 4: Offset Calculation

For Small Business (Turnover < $20M):

Tax Offset = Total R&D Expenditure × 43.5%

Example:
$100,000 eligible expenditure × 43.5%
= $43,500 refundable tax offset

Note: Refundable means cash refund even if in loss position!

Documentation Requirements

Contemporaneous Records

The ATO requires records created at the time of the R&D:

  1. Project Records

- Project plans and specifications - Technical design documents - Progress reports

  1. Time Records

- Timesheets showing R&D hours - Project allocation records - Team member roles

  1. Experiment Records

- Hypothesis statements - Test plans and protocols - Test results and data - Analysis and conclusions

  1. Financial Records

- Invoices and receipts - Payroll records - Asset purchase records

Registration Documentation

For each R&D activity (max 1,500 words per activity):

## [Activity Title]

### Description of Activity
[What R&D was conducted]

### Technical Uncertainty
[What couldn't be known in advance]

### Systematic Progression
[How hypothesis-experiment-observation-conclusion was followed]

### New Knowledge Outcome
[What new knowledge was generated]

### Relationship to Other Activities
[How this relates to other R&D projects if applicable]

Output Format

<rnd_eligibility_assessment>
  <project id="RND-001">
    <name>[Project Name]</name>
    <period>
      <start>2023-07-01</start>
      <end>2024-06-30</end>
    </period>

    <classification>Core R&D | Supporting R&D | Not eligible</classification>
    <confidence>High | Medium | Low</confidence>

    <criteria_assessment>
      <unknown_outcome score="3">
        <evidence>[How outcome was uncertain]</evidence>
      </unknown_outcome>
      <systematic_progression score="2">
        <evidence>[How methodology was followed]</evidence>
      </systematic_progression>
      <new_knowledge score="3">
        <evidence>[What new knowledge was generated]</evidence>
      </new_knowledge>
      <scientific_method score="2">
        <evidence>[Scientific basis of work]</evidence>
      </scientific_method>
      <total_score>10</total_score>
    </criteria_assessment>

    <expenditure>
      <salary_wages>$45,000</salary_wages>
      <contractors>$15,000</contractors>
      <materials>$5,000</materials>
      <depreciation>$3,000</depreciation>
      <overheads>$7,000</overheads>
      <total>$75,000</total>
    </expenditure>

    <tax_offset>
      <rate>43.5%</rate>
      <amount>$32,625</amount>
      <refundable>true</refundable>
    </tax_offset>

    <documentation_status>
      <timesheets>Yes | No | Partial</timesheets>
      <project_records>Yes | No | Partial</project_records>
      <experiment_records>Yes | No | Partial</experiment_records>
    </documentation_status>

    <recommendations>
      <item priority="high">[Required action]</item>
    </recommendations>
  </project>
</rnd_eligibility_assessment>

Key Precedents

CasePrinciple
Moreton Resources [2018] AATA 3378Technical uncertainty must be genuine
Core Surveys [2008] AATA 989Systematic progression is essential
Harding [2019] FCAFC 29Software can be R&D if innovative
AusNet [2020] AATA 1972Routine implementation not R&D

Common Pitfalls

PitfallAvoidance
No contemporaneous recordsImplement time tracking immediately
Mixing R&D and non-R&DClearly separate activities
Over-claimingUse conservative allocations
Missing deadlineRegister within 10 months
Poor activity descriptionsUse structured format above

平台分布

Claude Code

28.17%
按下载量换算32

Cursor

23.25%
按下载量换算27

windsurf

18.08%
按下载量换算21

OpenCode

11.88%
按下载量换算14

Codex

9.01%
按下载量换算10

Antigravity

3.31%
按下载量换算4

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

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。

继续浏览同类 Skills