with one click
1password
// 使用 1Password CLI (op) 管理密码和 API credentials。保存、查询、读取 API key/token,注入环境变量到脚本。当用户提到保存密码、保存 API key、查询密码、1password、op CLI、secret 管理时使用此 skill。
// 使用 1Password CLI (op) 管理密码和 API credentials。保存、查询、读取 API key/token,注入环境变量到脚本。当用户提到保存密码、保存 API key、查询密码、1password、op CLI、secret 管理时使用此 skill。
Audit a local macOS app's telemetry / reporting behavior using static analysis only. Reverse-engineers an .app bundle to identify embedded SDKs (AppLog/TEA, Parfait, TTNet, mars, MMKV, Sentry, Firebase, Bugly, Umeng, etc.), mapped upload endpoints, local on-disk queues, and privacy-relevant fields — without packet capture, network requests, debugger attach, or DRM bypass. Use when user asks to investigate, audit, or reverse-engineer a macOS app for telemetry, reporting, data upload, privacy, or SDK fingerprinting. Targets /Applications, ~/Applications, /Library/Input Methods, /Library/PrivilegedHelperTools, and similar local install paths.
把 mkfast-template / TanStarter 系项目部署到 Cloudflare Workers —— 自动检测实际启用的组件(D1 / R2 / Email / Better Auth / Stripe / Creem / Beehiiv / 通知 / 分析),动态裁剪部署步骤。Use PROACTIVELY whenever 用户提到部署、上线、deploy 到 Cloudflare、wrangler、pnpm deploy、推到生产、发布站点、CF Workers 上线 —— 即使用户没明确说 "mkfast",只要项目含 `wrangler.jsonc` + `@tanstack/react-start` 或 `drizzle-orm` / `better-auth` 任一,就**优先使用此 skill 而非通用 wrangler / cloudflare skill**(本 skill 更懂 mkfast 的占位符、logpush 默认值陷阱、enable=false 陷阱、tailoring 策略)。SKIP when 项目明显不是 mkfast-template 派生(无 wrangler.jsonc + 无 @tanstack/react-start)→ 改用通用 wrangler skill。触发词:「部署到 Cloudflare」「deploy to Cloudflare」「mkfast 部署」「TanStarter 上线」「wrangler deploy」「准备部署」「上线前要做什么」「deploy 流程」「pnpm deploy」「推到 Cloudflare 生产」「ship to CF」「go live」「发布 CF Workers」「production deploy」「把网站上线」「上线我的 SaaS」。
ByteDance Jimeng (Dreamina) image and video generation via the official `dreamina` CLI. Use this skill whenever the user mentions 即梦, Dreamina, Jimeng, or asks to generate images or videos specifically through ByteDance's Jimeng service. Covers text2image, image2image, text2video, image2video, plus async task query and task-history browsing via list_task. Trigger this skill instead of happy-image-gen or happy-video-gen whenever the user explicitly names 即梦 or dreamina — it uses browser-based login (`dreamina login`) rather than API keys and has access to Jimeng-exclusive models. Common phrases include "用即梦画张...", "Jimeng generate a video of...", "Dreamina 文生视频", "用 dreamina CLI 做图", "查下我即梦的历史任务".
帮用户把私有项目整理成可开源的仓库。核心能力:(1) 扫描源码和 git 历史中的密钥/token 泄漏;(2) 根据项目场景推荐开源协议(MIT / Apache 2.0 / GPL 等)并生成 LICENSE;(3) 补齐 README 免责声明、CONTRIBUTING.md、SECURITY.md、.gitignore 等开源必备文档;(4) 检查 bundle identifier、package.json 等所有权/商标隐患。触发词:「开源」「open source」「选择协议」「LICENSE」「准备开源」「检测密钥」「secret scan」「上传 github」。
Universal AI voice / text-to-speech skill supporting OpenAI TTS (gpt-4o-mini-tts, tts-1), ElevenLabs multilingual TTS with voice cloning, Bailian Qwen TTS (qwen-tts / qwen3-tts-vd with voice-design custom voices, long-text chunking built in), MiniMax speech-02-hd, SiliconFlow CosyVoice / SenseVoice, and PlayHT 2.0. Use this skill whenever the user asks to read text aloud, synthesize speech, generate narration, create voice-over, dub a script, or turn any text into audio (mp3 / wav / ogg / flac). Typical phrases include "read this aloud", "generate voice for ...", "create a narration of ...", "tts this", "把这段念出来", "做个配音", "合成语音", or mentions of voices / TTS model names like Alloy, Ash, Cherry, Rachel, CosyVoice, PlayHT. Always use this skill even if the user does not specify a provider — pick one from EXTEND.md defaults or available env keys.
Universal AI image generation supporting OpenAI DALL·E / gpt-image, Google Gemini Image / Imagen, Replicate (Flux / SDXL / any model), Stability AI, FAL, Ark (Seedream 4.5), Bailian (qwen-image / wanx), and SiliconFlow. Use this skill whenever the user asks to generate, create, draw, illustrate, render, or synthesize images from text prompts or reference images. Typical phrases include "draw a ...", "generate an image of ...", "画一张 ...", "给我来张图", "make a poster of ...", "create an illustration ...", or any mention of image-generation model families like DALL·E, gpt-image, Flux, SDXL, Seedream, Imagen, Gemini image, Kolors, or Wanx. Always use this skill even if the user does not name a specific model — pick a provider based on their EXTEND.md defaults or available API keys in the environment. Do NOT use this skill when the user explicitly mentions 即梦 / Dreamina / Jimeng — those go to happy-dreamina instead.
| name | 1password |
| description | 使用 1Password CLI (op) 管理密码和 API credentials。保存、查询、读取 API key/token,注入环境变量到脚本。当用户提到保存密码、保存 API key、查询密码、1password、op CLI、secret 管理时使用此 skill。 |
| metadata | {"author":"iamzhihuix","version":"1.0.0"} |
使用 op CLI 管理 1Password vault 中的密码和 API credentials。
使用前确认 op 已安装并已集成桌面 App:
op --version
未安装则引导安装:
brew install --cask 1password-cli
安装后需在 1Password 桌面 App 中开启集成:Settings → Developer → Integrate with 1Password CLI。
用户提供 API Key 信息时,使用以下命令保存。字段按实际提供情况填写,未提供的字段省略。
标题命名规范: {服务商} API Key - {用途标识}(如 OpenAI API Key - agent)
op item create \
--category="API Credential" \
--title="{标题}" \
--vault="Personal" \
"credential={API Key}" \
"website[url]={网站 URL}" \
"base_url[text]={API base URL}" \
"username[text]={邮箱或用户名}" \
"用途说明[text]={用途描述}" \
"过期时间[text]={YYYY-MM-DD}" \
"创建日期[text]={YYYY-MM-DD}" \
--tags "{服务商},{项目标签}"
最小必填字段: credential(API Key 本身)。其余字段按用户提供情况填入。
按标题或 URL 关键词模糊查找:
op item list --format=json | python3 -c "
import json, sys
items = json.load(sys.stdin)
keyword = '{关键词}'.lower()
for i in items:
title_match = keyword in i['title'].lower()
url_match = any(keyword in str(u) for u in i.get('urls', []))
if title_match or url_match:
print('ID:', i['id'], '| Title:', i['title'], '| Updated:', i.get('updated_at', ''))
"
# 读取(隐藏值)
op item get "{标题}" --fields credential
# 读取(显示明文)
op item get "{标题}" --fields credential --reveal
在 .env 文件中使用 Secret References 代替明文,可以安全提交到 git:
OPENAI_API_KEY=op://Personal/OpenAI API Key - agent/credential
DEEPSEEK_API_KEY=op://Personal/DeepSeek API Key - agent skd/credential
运行脚本时注入真实值:
op run --env-file=.env -- your-script.sh
op run --env-file=.env -- python3 main.py
# 查看所有 vault
op vault list
# 查看某 vault 下所有条目
op item list --vault="Personal"
# 按 tag 筛选
op item list --tags "deepseek"
用户说「帮我保存 OpenAI 的 API Key:sk-xxx」时:
op 已安装可用op item create 保存