Install the "hotclip" agent skill from https://github.com/xixihhhh/hotclip/tree/main/skills/hotclip into .claude/skills/hotclip/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hotclip", 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.
Type 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.
skills CLI
$ npx skills add xixihhhh/hotclip --skill hotclip -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "hotclip" agent skill from https://github.com/xixihhhh/hotclip/tree/main/skills/hotclip into .agents/skills/hotclip/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hotclip", 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.
skills CLI
$ npx skills add xixihhhh/hotclip --skill hotclip -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "hotclip" agent skill from https://github.com/xixihhhh/hotclip/tree/main/skills/hotclip into .cursor/skills/hotclip/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hotclip", 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.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add xixihhhh/hotclip --skill hotclip -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "hotclip" agent skill from https://github.com/xixihhhh/hotclip/tree/main/skills/hotclip into .gemini/skills/hotclip/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hotclip", 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.
GitHub CLI
$ gh skill install xixihhhh/hotclip hotclip
Installs 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).
skills CLI
$ npx skills add xixihhhh/hotclip --skill hotclip -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "hotclip" agent skill from https://github.com/xixihhhh/hotclip/tree/main/skills/hotclip into .github/skills/hotclip/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hotclip", 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.
skills CLI
$ npx skills add xixihhhh/hotclip --skill hotclip -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "hotclip" agent skill from https://github.com/xixihhhh/hotclip/tree/main/skills/hotclip into .opencode/skills/hotclip/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hotclip", 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.
Facts
Skill name
hotclip
GitHub stars
310
Token cost
~1.1k tokens
SKILL.md length
460 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
AGPL-3.0
At a glance
Turn long videos & livestream VODs into viral vertical shorts, 100% locally — on-device transcription, LLM highlight detection, 9:16 reframe with karaoke captions, and a per-clip render-QA report.
Works in 3 steps: Repo + deps (skip what already exists) → LLM config for highlight detection, via… → First transcribe/clip run auto-downloads…
The user asks to clip / cut / 切片 / 剪 a long video
SKILL.md covers Setup (once), Commands (run from the repo…, Recommended workflow and Hard rules, plus 1 more section
Calls pnpm and git; needs HOTCLIP_LLM_API_KEY
What it does
Hotclip is an agent skill from xixihhhh/hotclip. Turn long videos & livestream VODs into viral vertical shorts, 100% locally — on-device transcription, LLM highlight detection, 9:16 reframe with karaoke captions, and a per-clip render-QA report. Use when the user asks to clip / cut / 切片 / 剪 a long video, podcast or stream replay into short clips, find highlights / 爆点 in a video, or transcribe a media file. Footage never leaves the machine.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering Transcription and Video scripts and shorts. It works with Model Context Protocol, Bilibili, Douyin and TikTok. The repository describes itself as: 免费开源的 AI 剪辑 / 直播切片工具:长视频、直播回放、播客一键切成爆款竖屏短视频,直发抖音/快手/B站/小红书/视频号——AI 找高光金句、弹幕热度进爆点判断、自动加字幕、横屏转竖屏,本地运行无水印不上传 | Free open-source Opus Clip alternative, 100% local: AI clips long… The licence is AGPL-3.0.
When your agent uses it
The user asks to clip / cut / 切片 / 剪 a long video
Stream replay into short clips
Find highlights / 爆点 in a video
Transcribe a media file
Example prompts
“/hotclip”
Requirements
A credential in HOTCLIP_LLM_API_KEY
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
1Repo + deps (skip what already exists)
2LLM config for highlight detection, via env vars (any OpenAI-compatible endpoint)
3First transcribe/clip run auto-downloads the ASR model (~1GB, CN mirror first). Warn the user it may take a few minutes once.
What it can do on your machine
Read from SKILL.md and the folder at commit 4f4347d. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
pnpm
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
HOTCLIP_LLM_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Hotclip loads about 1.1k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 460 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~101
When it runs· the whole SKILL.md, loaded when a task matches
~1.1k
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.
Safety
Auto-check passed
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.
Download SKILL.mdSave it as .claude/skills/hotclip/SKILL.md (or your agent's skills folder).
name
hotclip
description
Turn long videos & livestream VODs into viral vertical shorts, 100% locally — on-device transcription, LLM highlight detection, 9:16 reframe with karaoke captions, and a per-clip render-QA report. Use when the user asks to clip / cut / 切片 / 剪 a long video, podcast or stream replay into short clips, find highlights / 爆点 in a video, or transcribe a media file. Footage never leaves the machine.
HotClip — local AI clipping pipeline
HotClip（AGPL-3.0 开源）把几小时的直播回放/播客/课程切成可直接发布的竖屏短视频,全程本地运行。You drive the same pipeline the desktop app uses, via a headless CLI (or the bundled MCP server). Everything — ASR, highlight detection, cutting, caption burn-in — runs on this machine; the footage is never uploaded.
Setup (once)
Repo + deps (skip what already exists):bash
git clone https://github.com/xixihhhh/hotclip.git && cd hotclip
pnpm install # ffmpeg/ffprobe are bundled npm binaries — nothing else to install
LLM config for highlight detection, via env vars (any OpenAI-compatible endpoint):bash
export HOTCLIP_LLM_BASE_URL=http://localhost:11434/v1 # local Ollama (no key needed)
export HOTCLIP_LLM_MODEL=qwen3:8b
# cloud endpoints additionally need: export HOTCLIP_LLM_API_KEY=sk-...
If these are missing, ask the user which LLM endpoint to use — do not guess keys.
First transcribe/clip run auto-downloads the ASR model (~1GB, CN mirror first). Warn the user it may take a few minutes once.
--reference <video>: hand in a viral clip to model after — its pacing (duration / speech rate / shot-cut frequency / hook shape) is measured locally and steers candidate selection as a preference (never a hard rule). Use when the user says "切得像这条" / "learn from this clip".
Input: MP4 / MKV / MOV / FLV / TS, or audio-only (podcasts get an auto-generated waveform video). Paths with spaces need quoting.
Recommended workflow
Review-first (default for interactive sessions): run highlights --json, show the user the candidates (title / score / hook / recommended), let them pick, then run clip — the pipeline re-detects from cache so this is cheap. For "just do it" requests, run clip directly.
Read the output receipt: the export folder contains one mp4 + cover JPG + .post.txt (publish copy) per clip, plus clips.json — per-clip evidence chain (render: what the pipeline did) and qa: render-QA report (status: pass|warn with issues like black frames, long silences, loudness deviation, duration mismatch, mid-word cuts, and platform-risk words in title/copy/captions via a local rule lint — qa.contentHits lists each term and where it appeared).
Self-repair is automatic: fixable warnings (leading/trailing silence or black frames → edge-trim; loudness deviation → second normalize pass) are repaired and re-checked in one pass; qa.repair records what was done (actions, applied). A repair is only kept when the re-check strictly improves.
Surface QA warnings: if any clip still has qa.status === "warn", tell the user which clip and why; content-lint hits mean the copy/captions may be throttled or rejected by 抖音/小红书/视频号 — suggest rewording before publishing. Never silently ship a warned clip.
Show full SKILL.md (104 more words)Show less
Hard rules
Never guess timestamps. Cut points come from word-aligned transcription (highlights output); do not invent start/end seconds or hand-roll ffmpeg cuts when the pipeline covers it.
Local-first: do not upload the footage or transcript to any service beyond the user-configured LLM endpoint (which only ever receives transcript text, never media).
Exports land next to the source video in <name>-hotclip/ unless --out is given; tell the user the absolute path when done.
MCP alternative
The same pipeline is exposed as a local stdio MCP server (pnpm mcp, tools: clip_video / detect_highlights / transcribe_video) — prefer it when the host supports MCP registration; the CLI is equivalent otherwise.
Hotclip 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.
A skill your agent uses when the user wants a video made, edited or finished: a launch or promo, product demo, explainer, trailer or teaser, tutorial or walkthrough, a screen recording turned into a…
A skill your agent uses when the user wants to plan or generate a social media cover image for a Xiaohongshu note, Douyin/TikTok photo post, Reels/Shorts cover, WeChat/Video Account post…
Transcribe and summarize a video or podcast from a URL (YouTube, TikTok, Bilibili, Apple Podcasts, SoundCloud, 30+ platforms) or from a local media/.txt file.
A skill your agent uses when user provides a short video platform URL or local video/audio file and wants subtitles/AI summary, or when user asks to list their own AI Douyin historical tasks.
Turn long videos & livestream VODs into viral vertical shorts, 100% locally — on-device transcription, LLM highlight detection, 9:16 reframe with karaoke captions, and a per-clip render-QA report. Hotclip is an agent skill from xixihhhh/hotclip. Turn long videos & livestream VODs into viral vertical shorts, 100% locally — on-device transcription, LLM highlight detection, 9:16 reframe with karaoke captions, and a per-clip render-QA report.
When should I use Hotclip?
Hotclip fits situations like: the user asks to clip / cut / 切片 / 剪 a long video; stream replay into short clips; find highlights / 爆点 in a video; transcribe a media file.
How do I install Hotclip in Claude Code?
Run `npx skills add xixihhhh/hotclip --skill hotclip -a claude-code`. Or copy the skill folder (skills/hotclip in xixihhhh/hotclip) into .claude/skills/hotclip in your project. Claude Code loads it when a task matches its description.
How do I install Hotclip in Codex?
Run `npx skills add xixihhhh/hotclip --skill hotclip -a codex`. Or copy the skill folder (skills/hotclip in xixihhhh/hotclip) into .agents/skills/hotclip in your project. Codex loads it when a task matches its description.
Can I use Hotclip in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xixihhhh/hotclip --skill hotclip -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hotclip, .gemini/skills/hotclip, .github/skills/hotclip and .opencode/skills/hotclip in your project.
What does Hotclip need to run?
Going by SKILL.md and its folder, Hotclip needs the command-line tools its instructions call (pnpm and git) and credentials named HOTCLIP_LLM_API_KEY. Our summary lists: A credential in HOTCLIP_LLM_API_KEY.
Does Hotclip access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Hotclip safe to install?
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.
What licence does Hotclip use?
Hotclip is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Hotclip use?
About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Hotclip?
Skills that share tags, products or a category with Hotclip: Showtime (FavioVazquez/showtime, 220 stars), Social Cover Director (Jamailar/Beav, 1.8k stars), Video Transcribe (wendy7756/AI-Video-Transcriber, 3.3k stars) and Shorts (AgriciDaniel/claude-shorts, 219 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Hotclip?
xixihhhh (a GitHub user) maintains it in xixihhhh/hotclip, which has 310 GitHub stars. The repository was last updated on October 8, 2026.
Source: xixihhhh/hotclip on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
