Knowledge Ops
affaan-m/ECC
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos).
微信公众号全流程运营:选题→采集→写作→排版→发布→数据分析→评论管理. An agent skill from LeoYeAI/openclaw-master-skills.
$ npx skills add LeoYeAI/openclaw-master-skills --skill wemp-ops -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills wemp-ops --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/wemp-ops .claude/skills/wemp-ops && 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 "wemp-ops" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wemp-ops into .claude/skills/wemp-ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wemp-ops", 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/wemp-opsType 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 wemp-ops -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills wemp-ops --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/wemp-ops .agents/skills/wemp-ops && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "wemp-ops" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wemp-ops into .agents/skills/wemp-ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wemp-ops", 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 wemp-ops -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills wemp-ops --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/wemp-ops .cursor/skills/wemp-ops && 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 "wemp-ops" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wemp-ops into .cursor/skills/wemp-ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wemp-ops", 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/wemp-ops--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 wemp-ops -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills wemp-ops --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/wemp-ops .gemini/skills/wemp-ops && 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 "wemp-ops" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wemp-ops into .gemini/skills/wemp-ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wemp-ops", 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 wemp-opsInstalls 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 wemp-ops -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/wemp-ops .github/skills/wemp-ops && 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 "wemp-ops" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wemp-ops into .github/skills/wemp-ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wemp-ops", 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 wemp-ops -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 wemp-ops --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/wemp-ops .opencode/skills/wemp-ops && 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 "wemp-ops" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/wemp-ops into .opencode/skills/wemp-ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wemp-ops", 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.
wemp-ops微信公众号全流程运营:选题→采集→写作→排版→发布→数据分析→评论管理. An agent skill from LeoYeAI/openclaw-master-skills.
Wemp Ops is an agent skill from LeoYeAI/openclaw-master-skills. 微信公众号全流程运营:选题→采集→写作→排版→发布→数据分析→评论管理。 Use when: (1) 用户要写公众号文章或提供了选题方向, (2) 用户说"写一篇关于XXX的文章"/"帮我写篇推文"/"出一篇稿子", (3) 用户要求采集热点/素材/竞品分析, (4) 用户提到公众号日报/周报/数据分析/阅读量/粉丝, (5) 用户要求检查评论/回复评论/评论管理, (6) 用户说"发布"/"推送"/"推到公众号"/"发到草稿箱", (7) 用户讨论文章排版/封面图/标题优化。 即使用户没有明确说"公众号",只要涉及微信文章写作、内容发布、 公众号后台操作、文章数据查看、或读者互动管理,都应使用此技能。 当用户给出选题方向时,自动完成素材采集→内容写作→封面生图→排版美化→推送草稿箱全流程。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 36 other files, including scripts, reference files and assets (for example `README.md`, `_meta.json` and `assets/templates/business.json`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
11 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.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
nodepython3From 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.
Wemp Ops loads about 2.5k tokens when it runs, and up to ~21k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 698 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); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 698 words, ~2,458 tokens.
.claude/skills/wemp-ops/SKILL.md (or your agent's skills folder). This skill also uses 30 other files; get the full folder from GitHub.首次使用前执行:
node scripts/setup.mjs检查 Node.js 版本、Python3、微信公众号 API 配置。
根据用户意图选择对应流程:
| 意图 | 流程 |
|---|---|
| "写一篇关于 X 的文章" | → 全流程(下方详述) |
| "采集 X 热点" | → 仅采集 |
| "公众号日报/周报" | → 数据分析 |
| "检查/回复评论" | → 互动管理 |
| "发布文章" | → 仅发布 |
| "选题/有什么可以写的" | → 选题管理(检查 topic-pool.md) |
当用户给出选题方向时,执行以下完整流程。先读 persona.md 确定写作人设。
如果老板没有指定具体选题,先检查选题池:
<WORKSPACE>/collections/topics/topic-pool.md如果老板已有明确选题,直接进入 Step 1。
读 references/article-templates.md 判断内容类型:
选题模糊时给 2-3 个具体方向让用户选(最多 1 轮澄清)。
2pre. 交接文件检查
先检查 <WORKSPACE>/temp/handoffs/collector-to-writing.md 是否存在:
2a. 收藏库检索(优先) 先从个人收藏库中检索相关素材——这是让文章有"人味"的关键(详见 writing-techniques.md §五):
grep -i "关键词" <WORKSPACE>/collections/tags.mdgrep -ril "关键词" <WORKSPACE>/collections/2b. 外部采集(补充) 收藏库素材不足时,从外部补充:
web_search 搜索 2-3 轮(官方信息→深度分析→对比评测)web_fetch 抓取 2-4 篇高质量参考文章node scripts/smart_collect.mjs 从 20+ 数据源采集相关热点⚠️ 中间存盘规则:每 2-3 轮 web_search/web_fetch 后,立刻把已获得的关键发现写到 <WORKSPACE>/temp/wemp-findings-{slug}.md(选题 slug),防止连续采集时前面的信息在 context 中被挤掉。采集完成后此文件可删除。
2c. 素材整理 合并收藏库 + 外部素材,按相关度排序,标注来源
读 references/writing-sop.md、references/style-guide.md 和 references/writing-techniques.md,按以下流程写作:
3a. 创意排水(正式动笔前必做) 花 2-3 分钟快速列出这个选题的"废水"——套路想法、陈词滥调、第一反应。标记为禁用列表,正式写作中刻意避开。(详见 writing-techniques.md §一)
3b. 正式写作
persona.md 人设(AI 产品经理第一人称)references/article-templates.md 对应类型的结构模板draft-v1.md,放在当前文章的工作目录下,如 wemp-article-NN/draft-v1.md)写作中运用五大技巧(详见 writing-techniques.md §二):
3c. 标题生成(双轨制) 按 writing-techniques.md §四 生成标题候选:
3d. 三遍审校 按 writing-techniques.md §三 结构化审校:
设计指南见 references/cover-image-guide.md。两种方案:
方案 A(优先):Seedream 5.0 Lite 生成
<WORKSPACE>/scripts/seedream-generate.sh "prompt" output.jpg "2560x1080" 12560x1440(16:9) 生成,再 sips -c 1090 2560 裁剪为 2.35:12880x1280 生成后裁剪方案 B(备选):nano-banana-pro 生成
方案 C(兜底):HTML 渲染 + 浏览器截图
python3 -m http.server 本地启动完整指南见 references/illustration-prompts.md(Type×Style 矩阵、Prompt 规范、风格锚点)。
4.5a 配图规划(先规划再生图)
扫描文章结构,按以下规则标注潜在配图位置:
## 标题后的第一段 → 潜在配图点内容信号自动匹配,根据段落关键词推荐 Type:
framework | 步骤/流程 → flowchart | vs/对比 → comparisoninfographic | 叙事/经历 → scene | 代码/界面 → screenshot锁定全文 Style(一篇文章只用一种 AI 生图风格):
notion-sketch(默认)| 数据/架构文 → tech-flat | 故事/教育文 → warm-doodle输出配图计划表(保存到 illustration-plan.md),让老板确认后再生图。
密度参考:2000 字 3 张、3000 字 4-5 张,正文配图硬上限 5 张。
4.5b 生图执行
配图有两条渲染路径,在配图计划表中按每张图标注:
路径 A:AI 生图(视觉美感优先,适合大部分场景)
<WORKSPACE>/scripts/seedream-generate.sh "prompt" output.jpg "2560x1440"2560x1440prompts/style-anchor.md,后续图片引用保持一致prompts/NN-{type}-{slug}.md,便于回溯修改路径 B:Mermaid 渲染截图(信息精确性优先,技术文章的流程/架构/对比图)
mermaid-render 的插图references/illustration-prompts.md 中的 Mermaid 规范)<WORKSPACE>/scripts/mermaid-render.html(临时 HTML 模板)images/prompts/NN-{type}-{slug}.md,记录 Mermaid 源码通用规则:
<WORKSPACE>/scripts/beautify-screenshot.sh <input> [output] --shadow --bg "#f5f5f5"<WORKSPACE>/scripts/remove-watermark.sh <input> [output](nano-banana-pro 需去水印)文章涉及线上产品(AI 工具、SaaS 产品等)时,截取真实产品界面作为配图。
公开页面(无需登录):
# 1. 打开产品页面
browser action:open url:"https://example.com/product"
# 2. 等待加载完成后截图
browser action:screenshot fullPage:false type:png
# 3. 裁剪/缩放(macOS sips 工具)
sips -z <高度> <宽度> screenshot.png # 缩放
sips -c <高度> <宽度> screenshot.png # 裁剪居中
sips --resampleWidth 800 screenshot.png # 按宽度等比缩放
# 4. 上传到微信素材库
node scripts/publisher.mjs # 通过 --markdown 自动上传
# 或手动:在 utils.mjs 中调用 uploadArticleImage()需登录页面(付费产品/内部系统):
browser action:screenshot profile:chrome 截图截图规范:
# 基础排版
python3 scripts/markdown_to_html.py --input article.md --theme tech --output article.html
# 带图片自动上传(本地图片自动上传到微信素材库并替换 URL)
python3 scripts/markdown_to_html.py --input article.md --theme tech --output article.html --upload主题选择:tech(科技风,默认)、minimal(简约风)、business(商务风)。
排版约束详见 references/weixin-constraints.md。
如果有额外配图需要手动插入(非 Markdown 内嵌图片),先上传再手动插入 HTML。
# 一键从 Markdown 到草稿(推荐,自动转 HTML + 上传图片 + 清理旧同名草稿)
node scripts/publisher.mjs --markdown article.md --title "文章标题" --cover cover.png
# 或手动分步:先转 HTML 再推送
python3 scripts/markdown_to_html.py --input article.md --theme tech --output article.html --upload
node scripts/publisher.mjs --title "文章标题" --content article.html --cover cover.png
# 跳过自动清理旧草稿
node scripts/publisher.mjs --markdown article.md --title "标题" --cover cover.png --no-cleanup
# 列出草稿
node scripts/publisher.mjs --list
# 删除草稿
node scripts/publisher.mjs --delete --media-id <id>
# 发布草稿(用户确认后)
node scripts/publisher.mjs --publish --media-id <草稿media_id>默认停在草稿箱,不自动发布。 告知用户草稿已创建,确认后再发布。
推送新版本时自动清理同标题旧草稿(--no-cleanup 跳过)。
交付前,用一个无上下文的子 Agent 阅读文章全文,检查:
向用户汇报:文章标题、字数、草稿状态、封面预览、建议发布时间。
node scripts/smart_collect.mjs --query "用户需求" --keywords "AI扩展的关键词" --sources "hackernews,v2ex,36kr" [--deep]数据源分类:
tech: hackernews, github, v2ex, sspai, juejin, ithome, producthuntchina: weibo, zhihu, baidu, douyin, bilibili, toutiao, tencent, thepaper, hupufinance: 36kr, wallstreetcn, cls采集后整理为选题候选清单,每条含:标题、来源、热度、链接、与用户需求的相关度。
# 日报(默认昨天)
node scripts/daily_report.mjs [--date YYYY-MM-DD]
# 周报
node scripts/weekly_report.mjs输出包含:用户增长、阅读数据、热门文章、互动数据、AI 洞察。
# 检查新评论
node scripts/check_comments.mjs
# 回复评论
node scripts/reply_comment.mjs --comment-id <id> --content "回复内容"AI 生成回复建议时遵循 persona.md 的语气规范,用户确认后再执行回复。
公众号凭证配置在 skill 自己的 config/default.json:
{
"weixin": {
"appId": "你的AppID",
"appSecret": "你的AppSecret"
}
}⚠️ 不要写到 openclaw.json 的 channels 里! channels 只接受 OpenClaw 内置渠道类型(dingtalk/telegram/discord 等),写入未知类型会导致 gateway 校验失败并不断重启。
其他配置(数据源偏好、报告时间等)同样在 config/default.json 中调整。
公众号文章完成后,可一键生成其他平台版本。
从公众号草稿箱/已发布文章中提取:标题、正文、核心观点、配图
自动调用 xiaohongshu-ops 技能:
在公众号文章对应的 memory 记录中标注已分发平台和链接
© 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 30 other files (scripts, references, assets) in skills/wemp-ops of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Wemp Ops 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 |
|---|---|---|---|---|---|---|
| Wemp Ops this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.5k | Automated safety check: Pass | MIT | |
| Knowledge Opsaffaan-m/ECC | 276k | 2 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Research Opsaffaan-m/ECC | 276k | 2 repos | ~902 | Automated safety check: Pass | MIT | |
| Terminal Opsaffaan-m/ECC | 276k | 2 repos | ~750 | Automated safety check: Pass | MIT | |
| Messages Opsaffaan-m/ECC | 276k | 1 repos | ~724 | Automated safety check: Pass | MIT | |
| Email Opsaffaan-m/ECC | 276k | 1 repos | ~1.1k | Automated safety check: Pass | MIT |
affaan-m/ECC
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos).
affaan-m/ECC
Evidence-first current-state research workflow for ECC. An agent skill from affaan-m/ECC.
affaan-m/ECC
Evidence-first repo execution workflow for ECC. An agent skill from affaan-m/ECC.
affaan-m/ECC
Evidence-first live messaging workflow for ECC. An agent skill from affaan-m/ECC.
affaan-m/ECC
Evidence-first mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow for ECC.
affaan-m/ECC
GitHub repository operations, automation, and management. An agent skill from affaan-m/ECC.
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.
微信公众号全流程运营:选题→采集→写作→排版→发布→数据分析→评论管理. An agent skill from LeoYeAI/openclaw-master-skills. Wemp Ops is an agent skill from LeoYeAI/openclaw-master-skills.
Wemp Ops fits situations like: 用户要写公众号文章或提供了选题方向; 用户说写一篇关于XXX的文章/帮我写篇推文/出一篇稿子; 用户要求采集热点/素材/竞品分析; 用户提到公众号日报/周报/数据分析/阅读量/粉丝.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill wemp-ops -a claude-code`. Or copy the skill folder (skills/wemp-ops in LeoYeAI/openclaw-master-skills) into .claude/skills/wemp-ops in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill wemp-ops -a codex`. Or copy the skill folder (skills/wemp-ops in LeoYeAI/openclaw-master-skills) into .agents/skills/wemp-ops 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 wemp-ops -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wemp-ops, .gemini/skills/wemp-ops, .github/skills/wemp-ops and .opencode/skills/wemp-ops in your project.
Going by SKILL.md and its folder, Wemp Ops needs the command-line tools its instructions call (node and python3). Our summary lists: Python 3; Node.js.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Wemp Ops 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 9.8k 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 19k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Wemp Ops: Knowledge Ops (affaan-m/ECC, 276k stars), Research Ops (affaan-m/ECC, 276k stars), Terminal Ops (affaan-m/ECC, 276k stars) and Messages Ops (affaan-m/ECC, 276k 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.