Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
书/长文/研报/论文的深度消化,产出结构笔记+原子笔记+知识网络连接。关键词:深度阅读、深度学习、结构笔记、deep learning。
$ npx skills add LeoYeAI/openclaw-master-skills --skill deep-reading -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills deep-reading --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mikonos-deep-reading .claude/skills/deep-reading && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "deep-reading" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mikonos-deep-reading into .claude/skills/deep-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-reading", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mikonos-deep-readingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill deep-reading -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills deep-reading --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mikonos-deep-reading .agents/skills/deep-reading && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "deep-reading" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mikonos-deep-reading into .agents/skills/deep-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-reading", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill deep-reading -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills deep-reading --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mikonos-deep-reading .cursor/skills/deep-reading && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "deep-reading" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mikonos-deep-reading into .cursor/skills/deep-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-reading", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/mikonos-deep-reading--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill deep-reading -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills deep-reading --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mikonos-deep-reading .gemini/skills/deep-reading && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "deep-reading" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mikonos-deep-reading into .gemini/skills/deep-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-reading", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills deep-readingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill deep-reading -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mikonos-deep-reading .github/skills/deep-reading && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "deep-reading" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mikonos-deep-reading into .github/skills/deep-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-reading", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill deep-reading -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills deep-reading --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mikonos-deep-reading .opencode/skills/deep-reading && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "deep-reading" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/mikonos-deep-reading into .opencode/skills/deep-reading/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-reading", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
deep-reading书/长文/研报/论文的深度消化,产出结构笔记+原子笔记+知识网络连接。关键词:深度阅读、深度学习、结构笔记、deep learning。
Deep Reading is an agent skill from LeoYeAI/openclaw-master-skills. 书/长文/研报/论文的深度消化,产出结构笔记+原子笔记+知识网络连接。关键词:深度阅读、深度学习、结构笔记、deep learning。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `README.md`, `_meta.json` and `references/expert_personas.md`).
It sits in AI & LLM Engineering, covering Deep learning. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
10 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Deep Reading loads about 2.5k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 20 tokens; SKILL.md has 733 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 733 words, ~2,524 tokens.
.claude/skills/deep-reading/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.核心理念:不仅要理解世界(Understand),还要改变世界(Act)。 适用范围:Book, Long-form Article, Research Report, Academic Paper.
来源: 本书/摘要,未核对原文;保留能确定的专有名词与结论,禁止编造细节;Feynman 验收时标「案例保真:部分(无原文)」。CLAUDE.md / core-entry「笔记元数据规范」一致;键名一律英文,便于 Obsidian 标签系统识别 tags 等):type: ...
tags: [english-tag-one, english-tag-two] # 或 YAML 多行列表;取值一律英文
links: [...]
description: ... # 费曼式洞察,100字内
date: YYYYMMDD
source_skill: deep-reading
epistemic_status: borrowed # 书/文默认 borrowed;自推分析可改为 working / speculativetags(取值):YAML 键名必须是 tags;数组内每条标签为英文(建议小写 kebab-case,或 Obsidian 嵌套 parent/child)。禁止用中文、空格或未规范化的中文短语作标签字面量;中文主题名写在正文与 [[链接]],不塞进 tags。
description 回答:这张笔记最值得告诉别人的一个洞察是什么?费曼会怎么介绍;供 index-note 归网时快速定性。本 skill 的产出归位与入网规则与 file-organize 一致:物理按天落 05_每日记录,MOC 在 03_索引 用链接拉取;入网步骤与 file-organize 共用同一套定义。
| 事项 | 规则 | 详见 |
|---|---|---|
| 归位 | 在 05_每日记录/YYYY/MM/YYYYMMDD/ 下新建本次任务文件夹(若日期目录不存在则先创建),本次任务笔记默认落在该文件夹内。索引笔记例外:物理位置在 03_索引/,创建后从 05 任务目录移动到 03 下(与 file-organize 类型表一致) | Phase 2.5 步骤 2 |
| 入网 | 索引笔记:在已存在索引中添加入口(挂载),本索引笔记底部链回父索引。结构/原子/方法笔记:在 03_索引/ 的 MOC 里按关键词添加入口 + 笔记底部反链(与 file-organize 入网步骤一致) | 索引笔记入网见 Phase 2.5 步骤 1;结构/原子/方法入网见 file-organize references/03索引实现MOC流程.md,Phase 6 执行 |
结构笔记命名:YYYYMMDD_00_[标题]_结构笔记.md。日期文件夹不存在则创建。
执行顺序:Phase 0 → 1 → 2 → 2.5 → 2.75 → 3 → 4 → 5 → 6 → 6.5(流程执行审查,强制),不可跳步;Phase 2.5 须在 Phase 2 完成后立即执行;Phase 2.75 须在 Phase 3 开始前完成;Phase 6.5 须在 Phase 6 完成后立即执行。
在开始 Phase 1 前产出执行计划;落盘为 YYYYMMDD_01_[书名]_执行计划.md(与结构笔记同目录),并在 task.md 的 Preparation 下链接该文件。
确保包含:
Agent: Mortimer Adler
templates/structure_note_template.md,含核心命题、逻辑支撑链与阅读顺序 (Reading Sequence)(每序列列出笔记顺序;该顺序将作为 Phase 3「阅读顺序链」的权威来源)。逻辑树与阅读顺序中的 [[链接]] 须为真实暂定标题(非模板占位),否则 Phase 2.75 无法通过。structure-note skillAgent: Niklas Luhmann
"不要问它属于哪个分类,问它和谁对话。"
templates/index_note_template.md,含关键词与多入口。references/03索引实现MOC流程.md 的「索引层级与命名约定」一致:索引_<主题>_<领域>.md 中的 <领域>。index-note skill;调用前先完成「领域名」决策。Agent: Niklas Luhmann
索引笔记创建完成后立即执行:入网(在已存在索引中挂载)→ 归位(物理移动到 03_索引)。
03_索引/ 下选定一个(或多个)与本书主题相关的已存在索引,在其中添加入口指向本索引笔记(如子专题表追加 - [[本索引笔记名]] — 领域简述,YYYYMMDD;说明用领域简述,不用书名/来源)。本索引笔记底部链回该父索引。05_每日记录/.../)移动到 03_索引/ 下合适位置(根目录或某主题子文件夹)。移动后父索引中的 [[本索引笔记名]] 仍有效(仅文件名,不依赖路径)。Agent: Mortimer Adler + Niklas Luhmann
脆弱步骤低自由度:未通过本节不得开始 Phase 3 的 Sweep 2+(血肉/边缘);仅允许在通过后执行「扩展型」建卡。详见 skill-creator 工作流模式。
显式链接全集(Round-1 清单) 的权威定义:
[[wikilink]]:逻辑树 (Logic Tree) 与 所有 Reading Sequence 小节中出现的链接并集,去重。[[概念笔记A]]、[[笔记A]] 等未替换为真实概念名)不得计入「已通过」的全集;须返回 Phase 1,将链接改为可建卡的暂定标题后再重做本节。task.md 对齐(强制):在 task.md 增加 # 显式链接全集(Phase 2.75) 区块,将上款全集逐条复制为 - [ ] [[概念名]],与结构笔记双向一致(结构里有的每条 task 里必有;task 里有的结构里必有)。
门禁判定:
task.md 中「显式链接全集」与结构笔记并集一致; Agent: Luhmann & Feynman
核心创新:边创建边发现 (Luhmann Scan)。
术语(避免混淆):
| 用语 | 含义 |
|---|---|
| 显式链接全集 | Phase 2.75 锁定;即本轮必须先落地的概念卡清单(骨架)。 |
| Phase 3 Sweep 1 / 2 / 3+ | 工作波次:骨架 → 血肉 → 边缘;见下列流程。 |
| Scan-R2 / Scan-R3(记录标签) | 仅用于 task.md 中 Luhmann Scan 行内格式,指「由 Scan 发现的后续待建链接批次」,与 Sweep 编号不同;完整定义见 references/luhmann_scan.md「Scan 产出轮次」。 |
保真 vs 扩展:本书/材料主论证链上的原子笔记优先满足 Case Fidelity(案例保真)。Scan 产生的外围概念:若超出本书范围或仅需占位,允许 stub(短定义 + 链)或仅记链接待以后扩展;止损条件见 luhmann_scan.md「何时停止?」。
流程:
references/luhmann_scan.md)。前置 → Scan-R2: [[A]]. 连接 → Scan-R3: [[B]]. 方法论 → [[方法名]] (Phase 4).(Scan-R2/R3 为 Scan 记录标签,勿与 Sweep 编号混用。)luhmann_scan.md 止损条款)。Atomic Note 规范:
templates/atomic_note_template.md阅读顺序链 (Reading-Order Chain)(强制):
← [[上一张]] | [[下一张]] →。Agent: The Pragmatist
将 Phase 3 发现的方法论创建为 Method Note。
Method Note 规范 (高优先级):
templates/method_note_template.md| 步骤 | What(做什么) | How(怎么做) | Why(为什么) | 表格;禁止只用纯段落描述步骤。Agent: Richard Feynman
用 Feynman 标准审视整个知识网络:
Agent: Niklas Luhmann
03_索引/ 相关 MOC 中完成接入。按 file-organize 的入网步骤执行(与 file-organize 共用同一套定义):提取关键词 → 索引候选发现 → 在选中索引中添加入口(Inbox 或关键词条目)→ 笔记底部加反链。详见 file-organize 的 references/03索引实现MOC流程.md;无需调用其他 skill。03_索引/ 下其他索引;若某笔记也是其他主题的优质入口,则在对应索引中添加入口。输出简要清单:[[笔记A]] → 已入 索引_X;建议补充入 索引_Y(理由)。Phase 6 完成后必须执行。调用 workflow-audit skill,以德明+葛文德视角对本流程执行完成度逐项核对与系统闭环检查:
YYYYMMDD_[任务名]_流程审查报告_德明与葛文德视角.md),含逐项清单、系统闭环、DoD 勾选、多索引挂载清单;对审查中标为 ❌ 的项必须补执行,直至 DoD 全部通过。.cursor/skills/workflow-audit/SKILL.md;报告模板:workflow-audit/references/audit_report_template.md。不可跳过。未通过流程执行审查并补全漏项,则本流程视为未完成。
在 task.md 中维护进度:
# Preparation
- [ ] Pre-game Plan Created (≥6 项 TODO + Context;对话内区块或落盘文件)
# Structure & Index
- [ ] Structure Note Created (Adler)
- [ ] Index Note Created (Luhmann)
- [ ] Index Note Onboarding (Phase 2.5): 挂载到已存在索引 + 归位到 03_索引
# 显式链接全集(Phase 2.75;与结构笔记逻辑树 ∪ Reading Sequence 并集一致)
- [ ] [[概念一]]
- [ ] [[概念二]]
# Extraction Loop (Phase 3)
- [ ] [[笔记A (Concept)]] + Luhmann Scan
- [ ] [[笔记B (Concept)]] + Luhmann Scan
# Methodology (Phase 4)
- [ ] [[工具A (Method)]] (SOP/Checklist/MVE)
# Review (Phase 5 & 6)
- [ ] Feynman Check (De-jargon check)
- [ ] Network Check (2+ Links per note;入网按 file-organize 的 03索引实现MOC流程;多索引挂载检查)
# Workflow Audit (Phase 6.5,强制)
- [ ] 调用 **workflow-audit** 做流程执行审查(德明+葛文德视角),产出审查报告并对 ❌ 项补执行,直至 DoD 全部通过task.md 双向一致;无占位链接;门禁通过后才进行 Sweep 2+。© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 8 other files (references) in skills/mikonos-deep-reading of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Deep Reading next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Deep Reading this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.5k | Automated safety check: Pass | MIT | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Add Oponnx/onnx | 22k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| CLIP Image-Text MatchingOrchestra-Research/AI-Research-SKILLs | 13k | 7 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Add Function Bodyonnx/onnx | 22k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 |
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
onnx/onnx
Add a new ONNX operator or update an existing operator to a new opset version.
Orchestra-Research/AI-Research-SKILLs
Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.
onnx/onnx
Add a function body definition to an ONNX operator, defining how it decomposes into simpler ops.
PaddlePaddle/Paddle
A skill your agent uses when working with Paddle's distributed training system: understanding parallelism strategies (DP, ZeRO, TP, PP, SP), semi-automatic parallel with ProcessMesh + shardtensor…
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Categories
书/长文/研报/论文的深度消化,产出结构笔记+原子笔记+知识网络连接。关键词:深度阅读、深度学习、结构笔记、deep learning。. Deep Reading is an agent skill from LeoYeAI/openclaw-master-skills.
Deep Reading fits situations like: tasks that involve Deep learning.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill deep-reading -a claude-code`. Or copy the skill folder (skills/mikonos-deep-reading in LeoYeAI/openclaw-master-skills) into .claude/skills/deep-reading in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill deep-reading -a codex`. Or copy the skill folder (skills/mikonos-deep-reading in LeoYeAI/openclaw-master-skills) into .agents/skills/deep-reading in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill deep-reading -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-reading, .gemini/skills/deep-reading, .github/skills/deep-reading and .opencode/skills/deep-reading in your project.
SKILL.md names no scripts, command-line tools or credentials: Deep Reading is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Deep Reading is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Deep Reading: Add Uint Support (pytorch/pytorch, 104k stars), Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars), Add Op (onnx/onnx, 22k stars) and CLIP Image-Text Matching (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,160 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.