findings-synthesis SKILL.md skillA
findings-synthesis 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/findings-synthesis@git:20260720.26d5eefPins git:20260720.26d5eef 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/findings-synthesis/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260720.26d5eef, committed Jul 20, 2026
- First version recorded
- Jul 3, 2026
- Size
- 4,246 bytes
- Repository stars
- 10
- License
- a license file GitHub does not identify
综合研究发现（乔淼PhD · AI学术训练营 · AI学术工作流 · 数据分析终点）。把多轮/多 skill 的数据分析产出整合成对应研究问题的研究发现：逐子问题/假设给结论判定 + 证据整合（定量 effect size 与定性主题并列）+ 方法间 convergence/divergence + 置信度局限 + 来源对照表，合法呈现零结果，绝不编造。产出 研究发现.md（全文初稿 Results/Findings 节的权威输入）。Trigger on："综合发现"、"把各轮分析汇总成研究发现"、"整合数据分析结果"、"synthesize my analysis results"、"combine quant and qual findings"、"write up findings from all analysis rounds"。.
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
# Findings Synthesis · 综合研究发现（数据分析最终产出） 把数据分析的**全部轮次、全部 skill 的产出**整合成一份对应研究问题的研究发现。这不是某一个 skill 的原始输出，而是面向 RQ 的综合发现。 ## 调用约定（独立运行） **必填**：分析产出所在位置——默认当前工作目录，或用户指定的任意目录/文件清单。 **RQ / 假设来源**按优先级：① 用户直接给的清单（并对照研究设计核实，若有）；② `研究设计初稿.md`（RQ + 假设）+ `选题.md`（贡献定位）；③ 都没有 → 请用户列出主 RQ 与各子问题/假设（一次问齐）。 **分析框架**（可选）：`研究设计-设计说明.md` 的 B3（原计划的方法链/整合规则），存在则读。 **分析账本**：读 `分析日志.md` 掌握一共跑了几轮、各轮用了哪个 skill、分别针对哪个子问题。该文件不存在 → 扫描产出目录下的全部文件自行归并。 **输出落盘**：`研究发现.md`（默认当前工作目录）。 - **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。 ## 第一步 · 读全部输入 1. RQ / 假设清单（按上方优先级确定） 2. 分析框架 B3（若有） 3. 分析日志（若有） 4. 全部产出：读产出目录下**所有**轮次产出（quant-* / qual-* / 各 skill 前缀的结果表 / 回归 / 编码本 / 主题图 / analytic-memo 等） ## 硬约束 - 只综合产出目录里**已经实际跑出来**的结果，逐条可回溯到具体产出文件（标注来源文件名/轮次）。缺哪块就明说"该子问题尚无分析支撑"，**绝不编造数值或访谈引语**。 - 定量结论必报 effect size + 显著性 + N；定性结论必报主题支持片段数 + 代表性引语。 - 零结果 / 不显著结果合法呈现（引 Neuman p.426），不得为了"好看"而夸大或隐藏。 - 多方法/多轮针对同一子问题时，必须做**交叉印证**：指出 quant 与 qual（或不同轮次）是相互支持（convergence）还是冲突（divergence），冲突时如实并陈、给可能解释，不强行调和。 ## 输出 · 写入 研究发现.md ``` ## 摘要（3-5 句）：本研究数据层面回答了什么 ## 逐子问题 / 逐假设的发现 对每个子问题 / 假设： - **结论判定**：支持 / 不支持 / 混合 / 证据不足（含合法零结果） …
Read the whole file at its exact version.
How to install
mdr add qiaomiaojoe/ai-academic-workflow/findings-synthesis@sha256:1e699de671e2ad92The line at the top of this page pins the label git:20260720.26d5eef, 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_ragr6phemcxxxl6t)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 3, 2026 and Jul 20, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260720.26d5eef latest | 2026-07-20 | 26d5eef | 4,246 B | A | view · diff |
| git:20260717.59c14bf | 2026-07-17 | 59c14bf | 3,916 B | A | view · diff |
| git:20260704.8f9ae45 | 2026-07-04 | 8f9ae45 | 4,018 B | A | view · diff |
| git:20260703.eabb41d | 2026-07-03 | eabb41d | 4,032 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 (4246 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_ragr6phemcxxxl6t GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/findings-synthesis GET https://markdownregistry.com/api/v1/blob/1e699de671e2ad9273ffbce6df340e389a3cc62ed5b85c4d443ea7b91ad9e9c7
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.