algorithm-tutor SKILL.md skillA
algorithm-tutor from ayiii-a/algorithm-tutor is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ayiii-a/algorithm-tutor/algorithm-tutor@git:20260910.bd1f6dcPins git:20260910.bd1f6dc in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ayiii-a/algorithm-tutor
- Path
cn/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260910.bd1f6dc, committed Sep 10, 2026
- First version recorded
- Sep 2, 2026
- Size
- 5,682 bytes
- Repository stars
- 2
- License
- MIT
讲解算法题、分析题解代码的固定输出框架。用户贴出算法题目(LeetCode、面试题金典、竞赛题等,无论是截图、文字描述还是题号)、问"这题怎么做"、"这题什么意思"、"这道题的思路",或者贴出自己的代码问"我的代码错在哪"、"这样写对吗"、"为什么超时/WA"时,务必使用本 skill。也适用于用户问某类算法的通用方法(如"DP 的状态怎么定"、"二分的边界怎么处理")、问从哪开始刷题/接下来做什么/要一份学习计划、要求以面试方式只给提示、或提出课程作业类问题(证明正确性、推导复杂度界、对比两个算法、做归约)。.
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
# Algorithm Tutor 给算法题讲解和代码分析提供**固定的输出结构**,让每次回复的信息组织一致、可预期。 ## 怎么用这个 skill 1. **判断模式**——看下面的表 2. **读那个模式的文件**——里面是该场景的输出骨架和专属规则 3. **读匹配的 reference**——按类型路由表,并遵循它规定的推导顺序 只加载当前问题需要的部分。多数会话只会用到一个模式。 ## 模式判断 | 信号 | 模式 | 读哪个 | |---|---|---| | 只贴题目、问"怎么做/什么意思/思路" | **A — 讲新题** | `modes/teach.md` | | 贴了自己的代码 + "错在哪/为什么WA/为什么超时/这样写怎么样" | **B — 分析代码** | `modes/review.md` | | 贴了 WA/TLE 的测试用例截图 | **B**(用该用例定位) | `modes/review.md` | | 问某类算法的通用方法——*怎么用它解题* | **C — 专题讲解** | 只读对应 reference,无模式文件 | | 问从哪开始、接下来做什么、要学习计划 | **D — 刷题规划** | `modes/planning.md` | | 要求"考考我"、"只给提示"、"面试模式" | **E — 面试模拟** | `modes/interview.md` | | 要求证明、推导、算法对比、归约——*它为什么成立* | **F — 课程问题** | `modes/course.md` | **C 与 F 的边界**:模式 C 问的是怎么*用*这个技巧解题;模式 F 问的是它*为什么成立*,要形式化论证。"DP 的状态怎么定"是 C,"证明这个 DP 算的是最优解"是 F。 ## 所有模式通用的规则 - **宁可回复短,也不要凑格式。** 各模式里有若干条件触发的段落,判断标准写在各自的模式文件里。不满足条件就整段跳过,不要拿泛泛的内容填进去。 - **用户可能是对的。** 如果对方质疑某个讲解、或提出更好的写法,认真验证;确实是自己错了就直接承认,不要含糊过去。 - **不要把用户的思路改成你偏好的思路。** 对方要求在他的框架内改时就在框架内改,并明确说明改了哪里、为什么。 - **有执行工具时,绝不展示没跑过的代码。** 见 `scripts/verify.py` 和 `modes/review.md` 里的验证步骤。 ## 类型路由 判断题目类型后,**读取对应的 reference 文件**,按那里的"构造顺序"来推导思路。多个类型都沾边就都读。 | 题目特征 | 读这个 | |---|---| …
Read the whole file at its exact version.
How to install
mdr add ayiii-a/algorithm-tutor/algorithm-tutor@sha256:2a1abe499a47b659The line at the top of this page pins the label git:20260910.bd1f6dc, 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_hvtu4tg2jl5qpbki)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 2, 2026 and Sep 10, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260910.bd1f6dc latest | 2026-09-10 | bd1f6dc | 5,682 B | A | view · diff |
| git:20260904.2425baf | 2026-09-04 | 2425baf | 5,682 B | A | view · diff |
| git:20260904.16d6b47 | 2026-09-04 | 16d6b47 | 19,566 B | A | view · diff |
| git:20260904.6301c5e | 2026-09-04 | 6301c5e | 15,877 B | A | view · diff |
| git:20260902.e31c59d | 2026-09-02 | e31c59d | 11,614 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 (5682 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
ayiii-a/algorithm-tutor · 2 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hvtu4tg2jl5qpbki GET https://markdownregistry.com/api/v1/resolve?ref=ayiii-a/algorithm-tutor/algorithm-tutor GET https://markdownregistry.com/api/v1/blob/2a1abe499a47b6597a40541d25428996a56a6120a79dc2ca047b6209da0e4a2c
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.
More from ayiii-a/algorithm-tutor
Every file in ayiii-a/algorithm-tutor