# Agent Auto Sci Methodology

> 研究方法论与批判性思维子 skill。用于研究问题 SMART 化、假设生成、机制框架、实验/准实验/观察研究设计、系统综述方法、证据质量评价、偏倚识别、因果边界、理论贡献、空间正义框架和审稿前风险扫描。触发于 hypothesis generation、research design、scientific critical thinking、evidence grading、bias audit、method critique 等任务。

- **Type:** Skill
- **Install:** `agentstack add skill-lzy599775-agent-auto-sci-skills-agent-auto-sci-methodology`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Lzy599775](https://agentstack.voostack.com/s/lzy599775)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Lzy599775](https://github.com/Lzy599775)
- **Source:** https://github.com/Lzy599775/agent-auto-sci-skills/tree/main/skills/agent-auto-sci-methodology
- **Website:** https://lzy599775.github.io/agent-auto-sci-skills/

## Install

```sh
agentstack add skill-lzy599775-agent-auto-sci-skills-agent-auto-sci-methodology
```

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

## About

# Agent Auto Sci Methodology

Use this subskill when the research logic itself is uncertain or needs strengthening.

## Fast Workflow

1. Convert broad interests into answerable research questions.
2. Define concepts, constructs, variables, mechanisms, and scope.
3. Generate competing hypotheses or explanations.
4. Choose design: review, observational, quasi-experimental, modeling, or mixed methods.
5. Audit bias, confounding, validity, and evidence strength.
6. Convert critique into concrete changes.

Read `references/research_methodology_workflows.md`.

For full paper projects, this skill owns topic selection, SMART research questions, hypothesis design, innovation diagnosis, feasibility, scope boundaries, conceptual framework, and reviewer-risk logic. When the task spans the whole manuscript lifecycle, coordinate through `auto-sci-research/references/08_full_research_to_manuscript_pipeline.md`.

For deeper K-Dense-style encapsulation:

- `references/k_dense_methodology_mapping.md`: how hypothesis generation, critical thinking, scholar evaluation, and peer-review logic are adapted.
- `references/sport_geography_methodology_playbook.md`: sport geography research questions, spatial justice, exposure mechanisms, bias, and evidence-grading playbook.

## Related Helper Skills

- `hypothesis-generation`
- `scientific-brainstorming`
- `scientific-critical-thinking`
- `scholar-evaluation`
- `statistical-analysis`
- `sport-geography-review-bibliometric`

## Must Not Do

- Do not turn a concept into a measurable variable without stating assumptions.
- Do not treat correlation, SHAP importance, or bibliometric co-occurrence as causal proof.
- Do not claim equity or justice from distribution maps alone.
- Do not hide uncertainty in policy language.

## Source & license

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

- **Author:** [Lzy599775](https://github.com/Lzy599775)
- **Source:** [Lzy599775/agent-auto-sci-skills](https://github.com/Lzy599775/agent-auto-sci-skills)
- **License:** MIT
- **Homepage:** https://lzy599775.github.io/agent-auto-sci-skills/

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-lzy599775-agent-auto-sci-skills-agent-auto-sci-methodology
- Seller: https://agentstack.voostack.com/s/lzy599775
- 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%.