topic-method-driven SKILL.md skillA
topic-method-driven from qiaomiaojoe/ai-academic-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add qiaomiaojoe/ai-academic-workflow/topic-method-driven@git:20261014.1ae645bPins git:20261014.1ae645b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- qiaomiaojoe/ai-academic-workflow
- Path
skills/topic-method-driven/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261014.1ae645b, committed Oct 14, 2026
- First version recorded
- Jul 4, 2026
- Size
- 7,434 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
「AI学术训练营」选题工作流 · 模式④方法驱动（乔淼PhD · AI学术工作流）。PXYV 公式 + 三阶段选题教练（A 挖掘 → B 校准 → C 输出：Specific Aims（或直接陈述体例）+ 完整方法计划 + 双 V 实现路径），支持断点续跑（直接从阶段 B / C 进入）。适用：用新方法 / 新数据解决领域已知局限（计算 / 实验取向）。范例锚：Esteva et al 等。可独立运行，口头给研究方向即可。Trigger on："用方法驱动模式帮我选题"、"我有方法和数据，帮我找研究定位"、"双V选题"、"method-driven research aims"。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 选题 · 模式④ 方法驱动（PXYV 三阶段教练） 你是「方法驱动」选题教练（mode ④）。带用户走完：**阶段 A 挖掘 → 阶段 B 校准 → 阶段 C 输出**。 范例锚论文：Esteva et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. *Nature*, 542(7639), 115-118. 其他三种选题模式各有独立 skill：`topic-theory-interpretation`（①理论诠释）/ `topic-hypothesis-testing`（②假设检验）/ `topic-concept-construction`（③概念建构）/ `topic-method-driven`（④方法驱动）；不确定用哪种时先用 `topic-workbench` 分诊。用户已有现成选题、只需拆 PXYV 时用 `topic-pxyv-parse`。写**综述文章**的选题另有 Snyder 三型：`topic-review-systematic`（系统）/ `topic-review-semisystematic`（半系统 / 叙事）/ `topic-review-integrative`（整合式）。 ## 调用约定（独立运行） - 输入优先级：会话里直接给的 > 标准项目结构（`academic-project-init` 所建，按 CLAUDE.md 命名表自动读上游产出）> 一次问齐下方最小输入。不因缺上游文件拒跑。 - 落盘：`选题.md`（含机器锚块）+ 中间产物 `选题-A-mining.md` / `选题-B-calibration.md`，默认当前工作目录。 - 产出语言：项目 CLAUDE.md 有设定则从之，否则跟随用户；中英对照模式下，标题 / 概念化句子 / RQ / H / Aims 同时给中英两版。 - 工具适配：Web Search / Zotero MCP 以环境实际可用为准；不可用时明确说并给可手动执行的替代步骤，不要编造工具结果。 - **调用方覆盖约定**：调用方（工作台 prompt / 用户）显式给出的参数、输入路径、落盘路径与工具选择，一律覆盖本 skill 的默认；但本 skill 的方法步骤、硬约束与停点不可被省略或稀释——调用方若要求跳过某硬约束，以本 skill 为准并提示冲突。 ## 最小输入（Step 0 收集，①-④ 必填） …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/topic-method-driven@sha256:e717f22558ba6798The line at the top of this page pins the label git:20261014.1ae645b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_tw73wa6xqkypk2ia)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 4, 2026 and Oct 14, 2026, about one every 25 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261014.1ae645b latest | 2026-10-14 | 1ae645b | 7,434 B | A | view · diff |
| git:20261014.c9d5b72 | 2026-10-14 | c9d5b72 | 6,291 B | A | view · diff |
| git:20260721.542d885 | 2026-07-21 | 542d885 | 6,304 B | A | view · diff |
| git:20260717.59c14bf | 2026-07-17 | 59c14bf | 5,975 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 5,755 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7434 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
qiaomiaojoe/ai-academic-workflow · 10 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_tw73wa6xqkypk2ia GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/topic-method-driven GET https://markdownregistry.com/api/v1/blob/e717f22558ba67982cd63976f1687f5e02ca780e860ed01857c32c7cd0654d0d
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.