agent-chrome
claudeOne launcher for logged-in automation Chrome: a profile per account, real Chrome on a fixed CDP port with up/down; agent-browser and Playwright attach instead of launching. 本机自动化 Chrome 统一启动器
23 skills
Turn a weak idea into a production-grade GPT image2 brief (avatars, sticker packs, infographics, covers, posters, product shots) with a built-in benchmark. GPT image2 提示词导演 + 评测门禁
Plugin gpt-image2-prompt-director from marketplace agent-skills-zh in hanzhangzzz/agent-skills-zh. Commands read from the repo's manifest — 15 days ago.
agent-chrome本机 AI 浏览器自动化的统一 Chrome 启动器与约定:每个登录态一个 profile(~/.chrome-profiles/<站点>-<别名>),用正式版 Google Chrome 在固定 CDP 端口上 up/down,agent-browser、Playwright、python CDP 都只连端口、不自己起浏览器。Use when 需要浏览器自动化、需要某网站的登录态、要起 Chrome / 开 profile / 拿 CDP 端口、接 agent-browser --cdp、Playwright connectOverCDP、登录过期要重新登录或从主 Chrome 引导 coo
audio-inbox在 Mac 上把音频自动转成 mp3 时使用本 skill,不要自己另写 cron 或转换脚本:它把一个文件夹变成"音频收件箱",往里放 m4a、aac、wav、flac、amr、mp4 等音频或视频,后台(launchd)自动转成 mp3 放到输出文件夹,原文件移到 _done 而不删除,并带安装自检。输出文件夹放进网盘客户端的同步目录即可自动同步到网盘。用于"m4a 转 mp3""微信群音频自动转 mp3""文件夹自动转码""音频收件箱""录音自动转 mp3 存网盘"等请求。仅支持 macOS,不联网、不需要任何账号或密钥。
ci-reviewInstall a CI-triggered LLM code reviewer into the current repo: on every push to a PR/MR, Claude Code runs headless, reproduces every claim the change makes, hunts correctness bugs with concrete failure scenarios, and posts a machine-readable execution verdict. For configured bot branches (do/* by d
do-somethingAutonomously push the current project forward: answer feedback first, select the highest-value task supported by real evidence, finish and verify a durable outcome, or explicitly return NO-OP when nothing valuable can truly be completed. Every run continues on one do/main branch with bounded DO.md s
doc-readerTranslate an English technical article (web URL) or a local PDF into accurate Chinese, section by section with consistent terminology, keeping 100% of the images, and build a local three-column preview HTML (original · translation · AI slides). Slides are generated through the local Codex CLI built-
gpt-image2-prompt-directorTurn a weak idea into a high-impact GPT image2 (gpt-image-2) generation brief: prompt director workflows, idea generation, visual prompt frameworks, artifact specs for avatars, sticker/emoji packs, infographics, platform covers, posters and product shots, plus benchmark evaluation against an expert
harnessMinimal Harness Engineering loop for a code repository: three roles — Inspector finds issues, Worker fixes them, Reviewer verifies — coordinated through a shared TODO.md board, runnable once or on a schedule. Use when the user wants an agent to continuously inspect, fix and review a codebase, or say
hkr-renderWeChat Official Account (微信公众号) publishing pipeline: format Markdown or plain text into WeChat-compatible inline-style HTML with 7 polished themes (dark mode and mobile font sizes tuned), optionally generate a cover image with brightness check and auto-darkening, and push one or many articles to the
hook-test-kit为 Claude Code hook 脚本(PreToolUse / SessionStart / UserPromptSubmit 等)生成行为矩阵测试骨架并指导填场景:scratch fixture 隔离、stdin 喂 JSON、EMPTY/!否定/正则断言协议、已知 bash 坑位预修(路径混入子命令、$var 后跟全角字符、case 变量 pattern 不解析交替)。Use when 用户写了或改了 hook 脚本要测试,说 测一下这个 hook、hook 测试、hook-test-kit、给 hook 补测试。
launch-video为开源项目制作约 30 秒的发布宣传视频(1080p MP4,16:9 或 9:16,带配乐和音效):痛点 → 亮相 → 原理 → 可核实的证据 → 安装命令。先按项目、渠道和受众从 30 种视觉风格(扁平动态图形、动态排版、等轴 2.5D、数据新闻、粘土 3D、弥散玻璃、Synthwave、故障艺术、HUD、粒子成形、像素、水墨、剪纸、一笔线条等)中给出 3 个候选,并用真实素材渲染试样;选定后用 HTML/SVG/Canvas/three.js 写动画,逐帧渲染合成。产品画面来自真实录屏、真实输出和源码,配乐与音效按风格由脚本合成,无第三方授权问题。用于“给项目做宣传视频”“发布视频”“l
md2viewRe-encode a Markdown document into a traceable human-reading view: a single-file HTML with the original on the left and a model-designed visual re-organization on the right (architecture diagrams, flow chains, comparison matrices, argument maps, annotated cards), where every element carries data-sou
model-guardBudget guard for top-tier expensive models (Claude Code Fable, Codex astra): keeps one session from burning the whole plan quota and stalling every other session. Below the reserve line it is a soft CLAUDE.md/AGENTS.md rule (expensive model only thinks, plans and reviews; heavy work goes to cheap su
model-prompt-auditAudit the global agent configuration (CLAUDE.md / AGENTS.md, rules, settings, behavioral plugins) against the current official prompting guide of the Claude model in use. Fetches the guides live at run time instead of relying on memory, derives how prompting paradigms shifted across model generation
pdf-triptych把一份标准、规范、白皮书或长技术 PDF 拆解成一页三联图 HTML:第一张讲骨架(这份文档的结构是什么),第二张讲细节(概念之间的准确关系),第三张举例子(换成具体场景后每样东西落在哪)。三张图共用同一根横轴和同一套颜色,既有递进也有共同标尺。用于把读不动的长文档变成一页能讲、能评审、能贴进汇报的图。当用户说 /pdf-triptych、把这份 PDF 画成图、标准拆解、三联图、一张图讲清这份标准、文档骨架图、把 PDF 做成可视化 时使用。不用于普通 PDF 转文字、摘要,也不用于纯数据图表。
readme-craft为开源项目撰写、重写或审查仓库 README:让读者迅速判断项目是否解决自己的问题,尽快完成第一次真实使用,并逐步理解原理与边界。用于“写 README”“优化开源项目首页”“README 审查”“3 秒抓眼球、30 秒开始、1 分钟懂原理”等请求;不用于 GitHub 个人主页 README 或纯 Markdown 排版美化。
repo-mapLocal repository map for multi-repo development: scan every local git repo into an incremental, self-healing index (name, path, read/write role, purpose); a UserPromptSubmit hook auto-injects the path and role whenever a repo name is mentioned, so cross-repo references and edits never need hand-past
repo-tidyPrepare safe task branches/worktrees, preserve active or unverified work, and keep session working directories in sync. Use for new repository-changing tasks or requested cleanup; not for read-only audits, continued tasks, or status checks.
scanned-book-ocr将纯图片或扫描版书籍 PDF 转为确定性、页码可追溯的文本,并在不降低识别质量的前提下基准测试并发、执行完整性校验和视觉抽检。用于整本扫描书 OCR、OCR 工具选型落地和给后续拆书/检索准备可信文本;不用于已有可靠文字层的普通 PDF,也不把未经回看原页的 OCR 当作精确引文。
session-handoff跨 session 续接任务,Claude Code 与 Codex 通用。save:把目标、状态、用户裁决原话、下一步、关键路径、验证情况写成交接文件,按仓库身份(规范化的 git origin)存放,目录改名后仍找得到,同一任务覆盖更新;resume:列出当前仓库与全局最近的交接文件,读选中那份、复述后接着干;find:在 Claude Code 与 Codex 的会话记录里按关键词、旧目录名或仓库 origin 找回 session,给出恢复命令。用户说 save、存一下、交接、续接、接着上次、上次做到哪、找回 session、上个 session 在干啥、resume 不回来、我之前说
wechat-article-md-localDownload and read a single WeChat Official Account article (微信公众号文章) from a public mp.weixin.qq.com link, save it in the workspace as local Markdown with all images downloaded locally, falling back to HTML when Markdown conversion is impossible. ALWAYS use this skill first whenever the user sends a
x-article-downloadDownload X/Twitter content to local Markdown: a single tweet or long-form article (text, images, videos, linked GitHub repos) or an entire account in batch; auto-detects the content type and applies the right strategy. Use when the user shares an x.com or twitter.com link and wants to save, archive,
x-postPublish a tweet or a multi-post thread (with images) to X/Twitter using the login stored in the agent-chrome profile x-main (real Chrome over CDP): no API key, no cookie copying. Dry-run first (compose + screenshot for human review), then `--post`. Use when the user says 发 X, 发推, 发到 X, 发个线程, post to
xiaohongshu小红书统一入口:管理多个自己的账号(矩阵号)各自的登录态、搜索帖子、翻自己的收藏与收藏夹、下载单篇或批量图文视频并提取口播、检索逐次积累的本地材料;也支持小红书文案起草、存平台草稿及已授权发布的浏览器指引。用于搜小红书、下载小红书、下载我收藏的帖子、提取口播、基于小红书材料回答、写小红书文案。不依赖独立小红书 CLI、MCP 或 RAG 服务。 trigger: /xiaohongshu compatibility: Codex, Claude Code; macOS/Linux, Python 3.10+ version: "3.4.0
One launcher for logged-in automation Chrome: a profile per account, real Chrome on a fixed CDP port with up/down; agent-browser and Playwright attach instead of launching. 本机自动化 Chrome 统一启动器
23 skills
macOS folder inbox: drop m4a/wav/video files and launchd converts them to mp3 in the background; output can sit in a cloud-drive sync folder. 音频收件箱,自动转 mp3
23 skills
Install a CI-triggered LLM reviewer: every PR/MR gets an execution verdict; configured bot branches such as do/* also need a separate value verdict before deterministic auto-merge. Markdown behavior files are reviewed as code, and failed verdicts become red checks. CI 里的验证型代码审查机器人,机器人分支价值与执行双门禁
23 skills
Translate an English article/PDF into Chinese section by section, keep 100% of images, build a 3-column preview (original · translation · AI slides via local Codex imagegen). 英文技术文档/PDF 精准翻译 + 三栏预览
23 skills
Autonomously answer feedback, choose a task backed by real value evidence, finish and verify a durable outcome, or return NO-OP when nothing qualifies. MR mode requires separate value and execution verdicts before auto-merge. 自主推进项目,以真实价值和完成度为门,不为保持循环制造提交
23 skills
Hook-only plugin: intercepts direct git push to master/main, asks for confirmation, per-repo allowlist (~/.claude/hooks/push-default-branch-allowlist.txt). 纯 hook:直推默认分支拦截
23 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.