Back to search
huangshu
SkillGitHub
黄叔开源的Skill集合
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/backtthefuture--huangshu)HTML
<a href="/listings/backtthefuture--huangshu"><img src="/api/listings/backtthefuture--huangshu/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 78 lines · 1 finding marked
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # 黄叔开源 Skill 集合
- > 为 [Claude Code](https://docs.anthropic.com/en/docs/claude-code) 打造的实用 Skill,开箱即用。
- ## Skill 目录
- | Skill | 它能干什么 | 适合什么时候用 |
- |-------|------------|----------------|
- | [私董会(advisory-board)](skills/advisory-board/) | 请 12 位顶级思想家从不同角度帮你拆问题 | 面临重大商业决策,需要多视角碰撞 |
- | [Social-SBTI(social-sbti)](skills/social-sbti/) | 根据公开社交动态生成娱乐向人格画像卡 | 给自己或公开公众人物做娱乐向人格画像 |
- | [视频逐字稿(video-transcript)](skills/video-transcript/) | 把 B 站/抖音/小红书/YouTube 视频转成可搜索、可引用的逐字稿 | 做笔记、做素材、做总结 |
- | [BOSS 求职助手(boss-zhipin-scraper)](skills/boss-zhipin-scraper/) | 校准真实 JD,按确认的数量和档位持续筛选并触达岗位 | 在 BOSS 直聘搜索、分析和联系适合自己的岗位 |
- 点击 Skill 名称可以看完整说明。新手只需要看下面这段安装命令。
- ## 小白安装
- 先打开 macOS 的「终端」,复制对应的一行命令,粘贴进去回车。安装完后,完全退出 Claude Code 再重新打开。
- ### 私董会
- ```bash
- npx skills add Backtthefuture/huangshu --skill advisory-board -a claude-code -g -y
- ```
- ### Social-SBTI
- ```bash
- npx skills add Backtthefuture/huangshu --skill social-sbti -a claude-code -g -y
- ```
- ### 视频逐字稿
- ```bash
- bash <(curl -fsSL https://raw.githubusercontent.com/Backtthefuture/huangshu/main/skills/video-transcript/bootstrap.sh)
- Note: Runs a downloaded script through process substitution (bash <(curl …))
- Line 35 on GitHub
- ```
- ### BOSS 求职助手
- 在 Codex 中直接粘贴下面这句话:
- ```text
- 请使用 skill-installer 安装这个 Skill:https://github.com/Backtthefuture/huangshu/tree/main/skills/boss-zhipin-scraper
- ```
- 也可以在终端执行:
- ```bash
- python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py --url https://github.com/Backtthefuture/huangshu/tree/main/skills/boss-zhipin-scraper
- ```
- ## 这些命令是什么意思
- 普通 Skill 用 `npx skills add ...` 安装:它的作用就是把指定 Skill 下载到 Claude Code 能看见的位置。
- 需要额外配置的 Skill 用 `bootstrap.sh` 安装:它像一个安装向导,会先下载 Skill,再检查依赖、补配置。比如 `video-transcript` 需要视频处理工具、浏览器引擎和豆包 API Key。
- 命令里的 `-a claude-code` 不能省。省掉后可能会装到别的目录,Claude Code 看不见。
- ## 🛠️ 工具(Tools)
- 除了 Skill 本体,这里还收录黄叔自用的 Skill 周边工具。
- | 工具 | 说明 | 首次安装 | 再次启动 |
- |-----|------|---------|---------|
- | [Skill Hub](tools/skill-hub/) | 本地 Web UI,扫描全机器所有 Claude Skills,可视化编辑、去重、相似检测、版本快照、7 天回收站 | `npm install -g https://github.com/Backtthefuture/huangshu/raw/main/tools/skill-hub/release/claude-skill-hub.tgz && skill-hub` | `skill-hub` |
- > 装的是 `tools/skill-hub/release/claude-skill-hub.tgz` 这个预构建 tarball(绕开 `npm install -g github:...` 在 npm 11 + node 24 上的悬空软链 bug)。每次 skill-hub 源码变更后 tarball 会同步重打。
- >
- > 首次装完会自动启动并打开浏览器;之后任何时候只要在终端敲 `skill-hub` 就能重新启动,或者直接访问 `http://localhost:3456`(如果服务还在跑)。更新到最新版本:再跑一次首次安装的那条命令即可。
- ## 贡献
- 欢迎提交 Issue 和 PR。如果你基于这些 Skill 做了有趣的改造,也欢迎分享。
- ## 许可
- MIT License
skills/video-transcript/bootstrap.sh · Bundled script · 140 lines · 1 finding marked
- #!/usr/bin/env bash
- # video-transcript skill 一行命令安装入口
- #
- # 用法:
- # bash <(curl -fsSL https://raw.githubusercontent.com/Backtthefuture/huangshu/main/skills/video-transcript/bootstrap.sh)
- Note: Runs a downloaded script through process substitution (bash <(curl …))
- Line 5 on GitHub
- #
- # 流程: 拉 skill 文件 → 跑 install.sh(装系统依赖 + 配 API Key)
- #
- # 兜底顺序: npx skills add → git sparse-checkout → tarball
- set -e
- REPO="Backtthefuture/huangshu"
- SKILL="video-transcript"
- TARGET="$HOME/.claude/skills/$SKILL"
- C_BOLD='\033[1m'; C_GREEN='\033[32m'; C_YELLOW='\033[33m'; C_RED='\033[31m'; C_BLUE='\033[34m'; C_GRAY='\033[90m'; C_RESET='\033[0m'
- say() { printf "${C_BLUE}▸${C_RESET} %s\n" "$1"; }
- ok() { printf " ${C_GREEN}✓${C_RESET} %s\n" "$1"; }
- warn() { printf " ${C_YELLOW}⚠${C_RESET} %s\n" "$1"; }
- err() { printf " ${C_RED}✗${C_RESET} %s\n" "$1"; }
- bar() { printf "${C_GRAY}═══════════════════════════════════════════════════════${C_RESET}\n"; }
- # ── Codex 集成:检测到 ~/.codex/ 就注册 /video-transcript ──
- register_codex() {
- local codex_home="${CODEX_HOME:-$HOME/.codex}"
- if [ ! -d "$codex_home" ]; then
- printf " ${C_GRAY}ℹ${C_RESET} 未检测到 ~/.codex/,跳过 Codex 集成(只 Claude Code 可用)\n"
- return 0
- fi
- mkdir -p "$codex_home/prompts"
- cat > "$codex_home/prompts/video-transcript.md" <<'PROMPT_EOF'
- You are a video transcript extractor. The user provides a video URL
- (B站 / 抖音 / 小红书 / YouTube) or a local file path as $ARGUMENTS.
- Run this command, streaming both stderr and stdout:
- python3 ~/.claude/skills/video-transcript/scripts/transcript.py "$ARGUMENTS"
- Behavior contract:
- 1. The script prints a 📊 评估表 to stderr early on. As soon as you see it,
- tell the user the title, duration, segment count, and 预估耗时 — so they
- know how long to wait.
- 2. When the script finishes, the FULL markdown transcript is on stdout,
- starting with a `# <title>` heading. You MUST display the entire transcript
- verbatim — every section with its `[MM:SS - MM:SS]` header. Do NOT summarize.
- Do NOT only say "saved to xxx.md".
- 3. End your reply with one short line noting the saved .md path.
- If the script fails with missing dependencies, suggest the user run:
- bash ~/.claude/skills/video-transcript/install.sh
- PROMPT_EOF
- ok "已注册 Codex 命令 → $codex_home/prompts/video-transcript.md"
- printf " ${C_GRAY} 在 Codex 里可用 /video-transcript <URL> 触发${C_RESET}\n"
- }
- bar
- printf "${C_BOLD} 🎬 video-transcript skill 安装引导${C_RESET}\n"
- bar
- echo ""
- # ── 已安装则提示 ─────────────────────────────────────────
- if [ -d "$TARGET" ]; then
- warn "已检测到 $TARGET 存在"
- printf " 覆盖重装? [y/N]: "
- read -r yn < /dev/tty || yn=""
- case "$yn" in
- [Yy]*) say "覆盖中,删除旧目录..."; rm -rf "$TARGET" ;;
- *) say "保留现有 skill,只跑 install.sh 重新配置"
- bash "$TARGET/install.sh"
- echo ""
- register_codex
- exit 0 ;;
- esac
- fi
- mkdir -p "$HOME/.claude/skills"
- # ── 三档兜底拉 skill 文件 ────────────────────────────────
- fetched=""
- # 档 1: npx skills add(huangshu 推荐方式,需要 node/npx)
- if [ -z "$fetched" ] && command -v npx >/dev/null 2>&1; then
- say "用 npx skills add 拉 skill..."
- if npx -y skills add "$REPO" --skill "$SKILL" -a claude-code -g -y 2>&1; then
- if [ -d "$TARGET" ] && [ -f "$TARGET/SKILL.md" ]; then
- fetched="npx"
- ok "通过 npx skills 拉到 $TARGET"
- fi
- fi
- [ -z "$fetched" ] && warn "npx skills 失败,尝试下一档..."
- fi
- # 档 2: git sparse-checkout(只拉这个 skill 子目录,省流量)
- if [ -z "$fetched" ] && command -v git >/dev/null 2>&1; then
- say "用 git sparse-checkout 拉 skill..."
- TMP=$(mktemp -d)
- if git clone --depth=1 --filter=blob:none --sparse "https://github.com/$REPO.git" "$TMP/repo" 2>&1; then
- (cd "$TMP/repo" && git sparse-checkout set "skills/$SKILL")
- if [ -d "$TMP/repo/skills/$SKILL" ]; then
- mv "$TMP/repo/skills/$SKILL" "$TARGET"
- rm -rf "$TMP"
- fetched="git"
- ok "通过 git sparse-checkout 拉到 $TARGET"
- fi
- fi
- [ -z "$fetched" ] && { rm -rf "$TMP"; warn "git 失败,尝试下一档..."; }
- fi
- # 档 3: tarball(终极兜底,无需 git/node)
- if [ -z "$fetched" ]; then
- say "用 tarball 下载..."
- TMP=$(mktemp -d)
- if curl -fsSL "https://github.com/$REPO/archive/refs/heads/main.tar.gz" | tar xz -C "$TMP" 2>&1; then
- SUBDIR=$(find "$TMP" -maxdepth 2 -type d -name "$SKILL" | head -1)
- if [ -n "$SUBDIR" ] && [ -d "$SUBDIR" ]; then
- mv "$SUBDIR" "$TARGET"
- rm -rf "$TMP"
- fetched="tarball"
- ok "通过 tarball 拉到 $TARGET"
- fi
- fi
- fi
- if [ -z "$fetched" ]; then
- err "三种方式都失败了!"
- err "请手动 git clone 后跑: bash <skill-dir>/install.sh"
- err " git clone https://github.com/$REPO ~/Downloads/huangshu"
- err " cp -r ~/Downloads/huangshu/skills/$SKILL $TARGET"
- err " bash $TARGET/install.sh"
- exit 1
- fi
- echo ""
- say "进入安装向导(装系统依赖 + 配豆包 API Key)..."
- echo ""
- bash "$TARGET/install.sh"
- echo ""
- register_codex
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.