contest-retrospective SKILL.md skillA
contest-retrospective from fourteen1416/academic-agent-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fourteen1416/academic-agent-toolkit/contest-retrospective@git:20261025.6e5886cPins git:20261025.6e5886c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fourteen1416/academic-agent-toolkit
- Path
academic-toolkit/skills/contest-retrospective/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261025.6e5886c, committed Oct 25, 2026
- First version recorded
- Sep 23, 2026
- Size
- 10,409 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
赛后/项目后复盘与经验沉淀：从留痕取证分类典型场景、踩坑与交付清单，归因真实强制点，双写经验库并机检闭环。触发词：复盘、赛后总结、经验沉淀、教训清单、事故归因、post-mortem、retrospective、把教训写进项目、避免下届重踩、lessons learned、根因分析、强制点归因。.
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
# 赛后复盘与经验沉淀（contest-retrospective）
**一句话**：把"这次踩的坑"变成"下届踩不到的坑"。
判据只有一条——**每条教训都必须绑定一个仓库内真实存在的强制点**（代码 / 规则 / 模板）。
没有强制点的教训不算沉淀完成，它会在下一届原样复发。
## 何时用
- 一次真实参赛（CUMCM/MCM/统计建模赛等）或项目 run 结束后，需要把事故与决策固化进工具箱。
- 出现"上次就吃过这个亏"的重复事故——说明上届复盘只停在记忆层，没落到强制点。
- 收到一份外部诊断报告/审计报告，需要判断哪些结论成立、哪些要驳（**批判式吸收**，见 §3）。
**不用于**：赛事成绩申诉、论文正文修改、单纯的事故陈述（不落强制点的报告不收）。
## 0. 输入契约
评审类输入（`COMP_REVIEW_VERDICT.json` / `VISUAL_REVIEW_VERDICT.json` / `FINAL_REVIEW_VERDICT.json` / `EDITOR_CHANGELOG.md`）取自待复盘工作区根目录。
| 输入 | 必需 | 说明 |
|------|------|------|
| 工作区路径 | ✅ | 待复盘的工作区（含 `.engine/`、产物、交付文档） |
| 复盘范围 | 可选 | 默认全链路；可限定为某个阶段（day1/day2/day3/submission） |
| 既有经验库 | ✅ | `academic-toolkit/data/contest_lessons.{json,md}`（不存在则按其 schema 新建） |
| 外部诊断报告 | 可选 | 第三方报告；**必须逐条研判，不得整篇照抄** |
| `COMP_REVIEW_VERDICT.json` | 可选（有则必读） | 写稿前评审的机器裁定：`findings[].category`（取值以 `academic-toolkit/skills/comp-review/SKILL.md` 的裁定 schema 为准）/`severity`/`where`/`evidence`/`fix` + `fatal_count`；`category` 是 §6 归类回灌的键 |
| `VISUAL_REVIEW_VERDICT.json` | 可选（有则必读） | 图评审的机器裁定：`findings[]` + `fatal_count` + `status`（`pass\|fail\|manual_review\|unavailable`）；`unavailable` 只记缺口，不得按 pass 计入复盘结论 |
…Read the whole file at its exact version.
How to install
mdr add fourteen1416/academic-agent-toolkit/contest-retrospective@sha256:61aeb85a9e878fe5The line at the top of this page pins the label git:20261025.6e5886c, 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_auufbkritvu5z3oe)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Sep 23, 2026 and Oct 25, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261025.6e5886c latest | 2026-10-25 | 6e5886c | 10,409 B | A | view · diff |
| git:20261023.cb0b591 | 2026-10-23 | cb0b591 | 10,381 B | A | view · diff |
| git:20260927.a059f3a | 2026-09-27 | a059f3a | 8,560 B | A | view · diff |
| git:20260923.2013b81 | 2026-09-23 | 2013b81 | 8,739 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 (10409 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
fourteen1416/academic-agent-toolkit · 12 stars · license a license file GitHub does not identify · pushed 2026-10-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_auufbkritvu5z3oe GET https://markdownregistry.com/api/v1/resolve?ref=fourteen1416/academic-agent-toolkit/contest-retrospective GET https://markdownregistry.com/api/v1/blob/61aeb85a9e878fe53f3b53b498be9a83695434a15b5c8da8e1d216f6573d0ee0
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.