Not in the top 1,000 by GitHub stars
hwl668/Scientific-learning-skills-
Diagnosis-first Agent Skills that turn AI from answer machine into learning tutor.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
deploy/socialistic/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 241f348abc61
No earlier version was observed for comparison.
skills/code-learning/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 241f348abc61
No earlier version was observed for comparison.
skills/deepening-learning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
50a007ae4c80 → 241f348abc61
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 50a007ae4c80
No earlier version was observed for comparison.
skills/fuzzy-understanding/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
50a007ae4c80 → 241f348abc61
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 50a007ae4c80
No earlier version was observed for comparison.
skills/mistake-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
50a007ae4c80 → 241f348abc61
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 50a007ae4c80
No earlier version was observed for comparison.
skills/problem-solving/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
50a007ae4c80 → 241f348abc61
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 50a007ae4c80
No earlier version was observed for comparison.
skills/scientific-learning/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
50a007ae4c80 → 241f348abc61
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 50a007ae4c80
No earlier version was observed for comparison.
skills/study-plan-builder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
50a007ae4c80 → 241f348abc61
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 50a007ae4c80
No earlier version was observed for comparison.
skills/text-memorizer/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
50a007ae4c80 → 241f348abc61
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 50a007ae4c80
No earlier version was observed for comparison.
skills/word-deep-dive/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
50a007ae4c80 → 241f348abc61
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 50a007ae4c80
No earlier version was observed for comparison.
skills/zero-base-learning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Instructions only
50a007ae4c80 → 241f348abc61
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 50a007ae4c80
No earlier version was observed for comparison.
Verified commit 241f348abc611b8ac2b80baff08ff0b6070e0a94
git clone --filter=blob:none --no-checkout https://github.com/hwl668/Scientific-learning-skills-.git .hotskills/hwl668-scientific-learning-skills- && git -C .hotskills/hwl668-scientific-learning-skills- checkout --detach 241f348abc611b8ac2b80baff08ff0b6070e0a94
# Copy each selected skill directory from .hotskills/hwl668-scientific-learning-skills- into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/hwl668/Scientific-learning-skills-.git .hotskills/hwl668-scientific-learning-skills- && git -C .hotskills/hwl668-scientific-learning-skills- checkout --detach 241f348abc611b8ac2b80baff08ff0b6070e0a94
# Copy each selected skill directory from .hotskills/hwl668-scientific-learning-skills- into .agents/skills/<skill-name>/Heat
1.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- scientific-learning-agent
deploy/socialistic - code-learning
skills/code-learning - deepening-learning
skills/deepening-learning - fuzzy-understanding
skills/fuzzy-understanding - mistake-review
skills/mistake-review - problem-solving
skills/problem-solving - scientific-learning
skills/scientific-learning - study-plan-builder
skills/study-plan-builder - text-memorizer
skills/text-memorizer - word-deep-dive
skills/word-deep-dive - zero-base-learning
skills/zero-base-learning
How it works
scientific-learning-agent
When your agent uses it
诊断式学习总入口。用于处理学习、解题、错题复盘、概念理解、深入讲透、英语查词、背诵抽背、学习计划等请求。先判断用户真正卡在哪，再选择合适的学习模式回答。适用于 socialistic.ai 等只支持单个 SKILL.md 的平台；本文件已内置所有子能力，不依赖外部子 skill 文件。
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
4,899 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 总原则
- 非学习请求处理
- 输入不完整时
- 路由表
- Router Engine
- 冲突处理
- 输出开头
- 输入判断
- 执行流程
- 输出结构
- 诊断框架
- 执行流程
- 输出结构
- 输入判断
- 七个深化维度
- 输出结构
- 输入判断
- 执行流程
- 输出结构
- 输入判断
- 错因分类
- 执行流程
- 输出结构
- 解析规则
- 执行流程
- 输出结构
- 输入判断
- 执行流程
- 输出结构
- 输入判断
- 执行流程
- 输出结构
Files
../../.claude-plugin/marketplace.jsonasset391 bytes../../.claude-plugin/plugin.jsonasset579 bytesSKILL.mdcore17,355 bytes
Read SKILL.md
# Scientific Learning Agent
你是一个诊断式学习 agent。核心原则是：先诊断，再讲解；先判断用户真正需要什么，再选择回答模式。不要把自己当成答案机器，也不要一上来长篇输出。
本文件是单文件部署版，已经内置原项目的父路由和所有子 skill 核心流程。不要尝试调用、加载或引用外部子 skill 文件；直接在本文件内完成路由和执行。
## 总原则
1. 先判断请求类型，再回答。
2. 学习问题要诊断卡点；非学习问题直接回答，不要强行路由。
3. 解释要服务于用户当前状态：零基础、学过但模糊、想深入、做题卡住、错题复盘、背诵、查词、制定计划。
4. 不要为了显得完整而堆内容。只讲当前最有帮助的部分。
5. 每次输出尽量包含一个验证环节：自测题、变式题、复述要求、检查清单或下一步行动。
6. 如果用户明确要求“直接回答”，可以压缩诊断，但仍保留一句最小判断。code-learning
When your agent uses it
带用户学习真实 Python 代码仓库，讲解架构与执行路径，关键代码带练、考核反馈和跨会话续学。用于看不懂源码、理解开源深度学习项目、学习 AI 生成代码。教学 agent 的宿主入口，不代替普通功能开发或故障修复。
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,506 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 建立目标与材料
- 工具驱动教学
- 常见误区
Files
SKILL.mdcore5,892 bytesSKILL.mdcore5,892 bytes
Read SKILL.md
# 代码学习 agent 的宿主入口
主体是 `learning_agent.code_learning` 的持久化会话和工具接口；本 Skill 让现有 Codex/Claude Code 宿主调用它。也可独立运行 CLI 的 `chat`，接支持工具调用的模型。
## 建立目标与材料
利用用户已给的基础和目标，最多补问一个影响路线的问题。识别四种模式：快速看懂 overview、系统学 systematic、动手带练 practice、考核 assess。用户要求直接解释时直接解释。
在本项目可用的 Python 环境中执行：
```bash
python -m learning_agent.code_learning start --repo /path/to/repo --goal "追踪一次训练的数据流" --mode systematic
# 无外部仓库时可用离线案例：start --demo micrograd 或 start --demo nanogpt
python -m learning_agent.code_learning resume SESSION_IDdeepening-learning
When your agent uses it
适用于已经有基础后想讲透、深入理解、本质解释、多角度理解、证明/推导、反例、跨知识联系、实际应用和高阶迁移的问题。用户问"为什么真正成立/还能怎么看/和什么有关/本质是什么"时使用。不是讲更难，而是讲更透。
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,265 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 七大深化维度
Files
SKILL.mdcore4,514 bytes
Read SKILL.md
# 目标
在已有基础上，从多个维度深化对一个知识点的理解，建立更丰富的认知结构。
# 适用场景
- 已经理解基本概念，能做常规题目
- 想知道"这个知识还能怎么看"
- 想知道这个知识和其它知识的关联
- 想知道这个知识在实际中怎么用
- 想看到这个知识的证明/推导
# Memory 系统
fuzzy-understanding
When your agent uses it
适用于学过、听过或做过但不清楚的学习问题。用户说看不懂、分不清、不会用、感觉懂了但做不出、公式会套但不知道为什么、符号/定义/概念混乱，或普通问"这是什么意思/为什么这样"且上下文显示不是零基础时使用。核心任务是诊断卡点并修复。
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,368 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. 快速诊断
- 2. 指出卡点
- 3. 针对性修复
- 4. 验证理解
- 5. 变式测试
Files
SKILL.mdcore4,582 bytes
Read SKILL.md
# 目标
诊断学习者在某个知识点上的具体卡点，针对性修复，而不是重新讲一遍。
# 适用场景
- 学过概念但说不清是什么
- 会背定义但不会用
- 做题时感觉"好像懂了又好像没懂"
- 公式会用但不知道为什么
# Memory 系统
**类型**：分析记忆（不参与间隔复习）。mistake-review
When your agent uses it
适用于错题复盘和错误诊断。用户说做错了、答案不一样、为什么我错、粗心、同样错误反复出现，或提供原题/自己的解答/标准答案时使用。归类错因，提炼避免再错的方法，并用变式训练巩固。
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,411 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. 重现错误
- 2. 定位错因
- 3. 分析误区
- 4. 正确思路
- 5. 同类识别方法
- 6. 检查清单
- 7. 变式训练
Files
SKILL.mdcore4,468 bytes
Read SKILL.md
# 目标
把错题变成学习资源。不只看"正确答案是什么"，而是搞清楚"为什么我会错"和"怎么不再错"。
# 适用场景
- 考试/作业中做错的题
- 感觉会但做错了的题
- 同样的错误反复出现
- 粗心做错的题（往往不是"粗心"那么简单）
# Memory 系统
**类型**：分析记忆（不参与间隔复习）。problem-solving
When your agent uses it
适用于理工科、数学、物理、计算机等题目求解。用户说这题怎么做、求解、证明、不会做、卡住了、帮我看看思路，或贴出题目但没有错误解答时使用。重思路推演，不重答案展示。教方法而不是给答案。
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
1,220 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. 识别题型
- 2. 找关键条件
- 3. 建立模型
- 4. 分步求解
- 5. 总结方法
- 6. 变式训练
Files
SKILL.mdcore4,181 bytes
Read SKILL.md
# 目标
引导学习者建立解题思路，理解"为什么这样做"，最终能独立解决同类和变式题目。
# 适用场景
- 被一道题卡住了，不会做
- 会做题但不知道为什么这样做
- 会做这道但不会做类似的
- 想知道一道题有没有更好的解法
# Memory 系统
**类型**：分析记忆（不参与间隔复习）。scientific-learning
When your agent uses it
学习请求的兜底路由入口。仅在用户显式要求使用 scientific-learning/统一学习入口，或请求意图确实模糊、有多个子 skill 同时合理而需要先分流时使用。不要用于已能直接匹配 code-learning、zero-base-learning、fuzzy-understanding、deepening-learning、problem-solving、mistake-review、word-deep-dive、text-memorizer 或 study-plan-builder 的普通学习请求；这类请求应直接使用对应子 skill。
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
2,081 tokensWhen the skill is activated
Reference documents
15,554 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. 识别意图
- 2. 调用/模拟子 skill
Files
../code-learning/SKILL.mddoc5,892 bytes../deepening-learning/SKILL.mddoc4,514 bytes../fuzzy-understanding/SKILL.mddoc4,582 bytes../mistake-review/SKILL.mddoc4,468 bytes../problem-solving/SKILL.mddoc4,181 bytesSKILL.mdcore7,052 bytes../study-plan-builder/SKILL.mddoc4,666 bytes../text-memorizer/SKILL.mddoc7,420 bytes../word-deep-dive/SKILL.mddoc9,949 bytes../zero-base-learning/SKILL.mddoc6,975 bytes
Read SKILL.md
# 目标
作为 Scientific Learning Skills 的轻量兜底入口，仅在显式调用或无法直接确定子 skill 时分流。不要把它当成所有学习请求的前置层，也不要在父 skill 里抢先长篇讲解。
# 路由原则
1. 用户显式点名子 skill 时，直接使用该子 skill，不经过本入口。
2. 请求已能直接匹配某个子 skill 时，直接使用子 skill，不要额外加载本 skill。
3. 只有在用户显式调用本入口，或多个意图无法靠已有上下文区分时，才用下面的路由表。
4. 如果平台支持显式 Skill 调用，调用对应子 skill。
5. 如果没有显式 Skill 调用但能访问本地 skill 文件，打开并遵循对应 sibling skill 的 `SKILL.md`：
- `../zero-base-learning/SKILL.md`
- `../fuzzy-understanding/SKILL.md`
- `../deepening-learning/SKILL.md`study-plan-builder
When your agent uses it
适用于制定学习计划、复习安排、备考路线、自学路径和时间规划。用户问怎么学、多久学完、如何备考、每天学什么、短期补弱、考试冲刺或项目学习路线时使用。根据目标、时间、当前基础，生成现实可执行的学习计划。
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
1,368 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. 目标拆解
- 2. 阶段划分
- 3. 每日任务
- 4. 资源匹配
- 5. 检测标准
- 6. 复盘机制
Files
SKILL.mdcore4,666 bytes
Read SKILL.md
# 目标
根据学习者的具体约束（目标、时间、基础），生成一个现实、具体、可执行的学习计划。
# 适用场景
- 准备某门课的期末考试
- 自学一门新的编程语言/数学分支
- 考研/高考复习规划
- 短期内需要补齐某个知识短板
# Memory 系统
**类型**：分析记忆（不参与间隔复习）。text-memorizer
When your agent uses it
适用于背诵、抽背、默写、文科知识点记忆和文本复习。用户粘贴一段文字，或说帮我背、帮我记、出题、抽背、复习薄弱点、政治/历史/思政大题时使用。输出重点拆分、思维导图、随机抽背题目，并按反馈追踪间隔复习。
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
2,300 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 类型
- 存储位置
- 复习引擎
- 读写方式：CLI 优先
- 管理命令
- 1. 内容分类
- 2. 结构化拆分
- 3. 思维导图
- 4. 关键词压缩
- 5. 生成题库
- 6. 常见误区提示（P0 强制）
- 7. 抽背与追踪
- 新文本输入时
- 抽背时
Files
SKILL.mdcore7,420 bytes
Read SKILL.md
# 目标
把一段需要背诵的文本转化为结构化记忆材料，通过主动提取练习和薄弱点追踪，让背诵不再靠机械重复。
# 适用场景
- 思政类课程（马原、毛概、思修、近代史）知识点背诵
- 政治/历史大题的要点记忆
- 任何需要结构化记忆的文本段落
- 期末考试前需要快速过一遍的知识点清单
# Memory 系统
## 类型word-deep-dive
When your agent uses it
适用于英语单词查询、背单词、词义辨析、近义词/形近词区分、考试词汇分析和单词复习。用户输入单个英文词、!word、查词、这个词什么意思、某考试词汇、复习单词时使用。输出针对考试的全息词典卡片，支持选择性存入记忆和间隔复习。
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
3,077 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 类型
- 存储位置
- 复习引擎
- 读写方式：CLI 优先
- 两种记忆模式
- 模式切换
- 标记语法
- 复习功能
- 管理命令
- 解析规则
- 上下文判断
- 1. 多义项展开
- 2. 用法搭配
- 3. 词根词缀派生
- 4. 形近词辨析
- 5. 近义词梯度
- 6. 反义词
- 7. 针对性考法
- 8. 备考建议
- 9. 常见误区（P0 强制）
- 10. 记忆锚点
- 查词卡片
- 复习卡片
Files
SKILL.mdcore9,949 bytes
Read SKILL.md
# 目标
把一个英语单词讲透，并根据目标考试给出针对性的备考建议。同时支持选择性单词记忆系统——间隔复习、薄弱追踪，不在无价值的词上浪费复习时间。
# 适用场景
- 阅读/做题中遇到一个词，想彻底搞懂
- 背单词时想知道"这个词和那个词到底有什么区别"
- 写作时想知道该用哪个词更准确
- 备考阶段想知道这个词会不会考、怎么考、为此我该做什么
- 希望建立自己的"主动词汇记忆库"，按间隔复习而不是一次查完就忘
# Memory 系统
zero-base-learning
When your agent uses it
适用于从零学习、入门解释和普通"是什么/请讲一下/我第一次接触/完全不懂"类问题。用户想认识一个新概念、新公式、新学科、新工具，或没有提供已学背景时使用。从直觉出发，逐步建立正式理解。
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
2,039 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 第一层：区分"真零基础"和"隐藏的前置缺失"
- 第二层：校准回答起点
- 第三层：校准知识版本
- 1. 输入判断
- 2. 问题背景
- 3. 直觉解释
- 4. 最小概念
- 5. 正式定义
- 6. 最小例题
- 7. 常见误区
- 8. 自测问题
Files
SKILL.mdcore6,975 bytes
Read SKILL.md
# 目标
让零基础学习者在最短时间内建立对一个知识点的直觉理解和基本应用能力。
# 适用场景
- 第一次接触某个概念（如极限、矩阵、导数、熵）
- 没有相关前置知识
- 之前看了教材但完全读不懂
- 能说出名词但完全不知道是什么意思
# Memory 系统
**类型**：分析记忆（不参与间隔复习）。Skills included
- scientific-learning-agent
- code-learning
- deepening-learning
- fuzzy-understanding
- mistake-review
- problem-solving
- scientific-learning
- study-plan-builder
- text-memorizer
- word-deep-dive
- zero-base-learning
Repository facts
- License
- MIT
- Created
- May 31, 2026
- Last pushed
- Oct 30, 2026
- Forks
- 1
- Open issues
- 1
- Project activity
- Active
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
skills/code-learning/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 8 network referencesin 2 files: .claude-plugin/plugin.json:5 .claude-plugin/marketplace.json:3
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 8 signals by file
.claude-plugin/marketplace.json
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "hwl668", "url": "https://github.com/hwl668" - Network accessline 6
"name": "hwl668", "url": "https://github.com/hwl668" }, - Network accessline 7
"url": "https://github.com/hwl668" - Network accessline 8
}, "homepage": "https://github.com/hwl668/Scientific-learning-skills-", "license": "MIT", - Network accessline 9
"homepage": "https://github.com/hwl668/Scientific-learning-skills-",
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md deploy/socialistic/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md deploy/socialistic/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md deploy/socialistic/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md deploy/socialistic/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
