← All skill packs

AI Agent Workflow Collection

Skill pack
29 skills0 selected
zeniththSkills in this pack

Use when writing descriptions for [Donation] timestamps in an anibon-timestamper stream, to select the correct donation sub-type and tone (Serious, Joke, Q&A, Weird) before writing the description.

English

Use when processing a live stream or specific video chunk covering a newly released game event or update (Game Event Launch).

English

Use when processing a live stream or specific video chunk where the speaker is playing a single game with sparse verbal reactions (Dedicated gaming).

English

Download, parse, chunk, and analyze YouTube LiveChat replays for live streams. Extracts SuperChats/Donations, Hype/Meme peaks, viewer Q&As, and applies Thai internet subculture psychology.

English

Transcribe YouTube audio locally using whisper.cpp when YouTube has no subtitles or auto-captions. Alternative path loaded by anibon-timestamper.

English

Use when generating timestamps for any ANIBON stream and the output feels too long, has too many sections, or each 5-minute chunk produces its own timestamp. Load alongside anibon-timestamper to enforce macro-level density rules that keep output short while preserving all major context.

English

Use when processing a live stream or specific video chunk where the speaker switches between multiple games in one session (Multi-game marathon).

English

Advanced video editing skill using FFmpeg, emphasizing perfect audio/video sync, frame-accurate waveform cutting, and narrative flow without jump-cutting.

English

Use when processing a live stream or specific video chunk where the speaker is primarily talking, chatting with viewers, or discussing news/updates (Talk-heavy stream).

English

Use when generating detailed timestamps or topic summaries for long-form live streams and videos featuring speaker "Boat" (Pu Boat) from Anibon Official. This is the orchestrator skill.

English

Save or load the progress state of a local timestamper session to prevent token context window exhaustion.

English

Use when generating timestamps for Anibon streams on a LOCAL model (Ollama, gemma4, qwen). Focuses on step-by-step sequential looping, minimal context, and goldfish brain rules.

English

Use when processing a live stream or specific video chunk where the speaker is discussing tokusatsu (Kamen Rider, Super Sentai, Ultraman, etc.) with guests/co-hosts, or hosting a watch party for a tokusatsu episode.

English

Verify game world, character, and location names against local references before writing story timestamps. Loaded by anibon-timestamper when the stream covers post-cutoff games.

English

Use when the current agent cannot directly view or analyze images, but frame inspection is needed for video analysis or visual context.

English

Use when spawning multiple parallel subagents to process large datasets, transcript chunks, or batch workloads without hitting API rate limits or falling back to…

English

Use when writing data processing scripts, analysis utilities, or multi-step automation tools in Python to ensure they are modular, configurable, testable, and reusable.

English

Use when processing auto-generated YouTube transcripts that contain transcription errors, misspellings, or phonetic pronunciation anomalies.

English

Master orchestrator skill that triggers automatically when a user wants to make a highlight video from a link. Coordinates the planner, cutter, and verifier skills automatically.

English

Use when cutting, concatenating, or fixing audio-video synchronization and frame freeze issues in downloaded video…

English

Use when selecting timestamps for a highlight reel from a livestream or talk-show, to ensure no jarring jump cuts appear and the narrative flows smoothly between scenes.

English

Quality-checks a highlight MP4 for duration, tracks, and pixel format against the JSON cut plan.

English

Use when selecting, filtering, or marking timelines from a livestream to create a summary, highlight reel, or send instructions to a video…

English

Use when processing, summarizing, or timestamping content that references the Thai royal family, succession, or sensitive political issues, requiring strict metaphor-based masking to ensure publisher safety.

English

Includes Anibon Donation Classifier, Anibon Event Stream, Anibon Gaming Stream, and other workflows.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Pack stats

Skills29CategorygeneralStars0

What’s included

Anibon Donation Classifier

Use when writing descriptions for [Donation] timestamps in an anibon-timestamper stream, to select the correct donation sub-type and tone (Serious, Joke, Q&A, Weird) before writing the description.

Anibon Event Stream

Use when processing a live stream or specific video chunk covering a newly released game event or update (Game Event Launch).

Anibon Gaming Stream

Use when processing a live stream or specific video chunk where the speaker is playing a single game with sparse verbal reactions (Dedicated gaming).

Anibon Livechat Analysis

Download, parse, chunk, and analyze YouTube LiveChat replays for live streams. Extracts SuperChats/Donations, Hype/Meme peaks, viewer Q&As, and applies Thai internet subculture psychology.

Anibon Local Transcription

Transcribe YouTube audio locally using whisper.cpp when YouTube has no subtitles or auto-captions. Alternative path loaded by anibon-timestamper.

Anibon Macro Density

Use when generating timestamps for any ANIBON stream and the output feels too long, has too many sections, or each 5-minute chunk produces its own timestamp. Load alongside anibon-timestamper to enforce macro-level density rules that keep output short while preserving all major context.

Anibon Marathon Stream

Use when processing a live stream or specific video chunk where the speaker switches between multiple games in one session (Multi-game marathon).

Anibon Stream Synthesis FFmpeg

Advanced video editing skill using FFmpeg, emphasizing perfect audio/video sync, frame-accurate waveform cutting, and narrative flow without jump-cutting.

Anibon Talk Stream

Use when processing a live stream or specific video chunk where the speaker is primarily talking, chatting with viewers, or discussing news/updates (Talk-heavy stream).

Anibon Timestamper

Use when generating detailed timestamps or topic summaries for long-form live streams and videos featuring speaker "Boat" (Pu Boat) from Anibon Official. This is the orchestrator skill.

Anibon Timestamper Handoff

Save or load the progress state of a local timestamper session to prevent token context window exhaustion.

Anibon Timestamper Local

Use when generating timestamps for Anibon streams on a LOCAL model (Ollama, gemma4, qwen). Focuses on step-by-step sequential looping, minimal context, and goldfish brain rules.

Anibon Tokusatsu Stream

Use when processing a live stream or specific video chunk where the speaker is discussing tokusatsu (Kamen Rider, Super Sentai, Ultraman, etc.) with guests/co-hosts, or hosting a watch party for a tokusatsu episode.

Anibon World Identity

Verify game world, character, and location names against local references before writing story timestamps. Loaded by anibon-timestamper when the stream covers post-cutoff games.

Antigravity Vision Proxy

Use when the current agent cannot directly view or analyze images, but frame inspection is needed for video analysis or visual context.

Batching Subagents Concurrency

Use when spawning multiple parallel subagents to process large datasets, transcript chunks, or batch workloads without hitting API rate limits or falling back to heuristics

Building Reusable CLI Tools

Use when writing data processing scripts, analysis utilities, or multi-step automation tools in Python to ensure they are modular, configurable, testable, and reusable.

Cleaning Auto Transcripts

Use when processing auto-generated YouTube transcripts that contain transcription errors, misspellings, or phonetic pronunciation anomalies.

Creating Highlight Video

Master orchestrator skill that triggers automatically when a user wants to make a highlight video from a link. Coordinates the planner, cutter, and verifier skills automatically.

Edit Cut Video FFmpeg

Use when cutting, concatenating, or fixing audio-video synchronization and frame freeze issues in downloaded video streams

Highlight No Jumpcut Rules

Use when selecting timestamps for a highlight reel from a livestream or talk-show, to ensure no jarring jump cuts appear and the narrative flows smoothly between scenes.

Highlight Verifier

Quality-checks a highlight MP4 for duration, tracks, and pixel format against the JSON cut plan.

Livestream Scene Selection

Use when selecting, filtering, or marking timelines from a livestream to create a summary, highlight reel, or send instructions to a video editor

Masking Royal News

Use when processing, summarizing, or timestamping content that references the Thai royal family, succession, or sensitive political issues, requiring strict metaphor-based masking to ensure publisher safety.

Showing 24 of 29 skills. Use the list’s page controls above to explore the rest.

Quick start

  1. Choose your skills. Select individual skills above, or choose the entire pack.
  2. Copy the install prompt. Use Copy install prompt above the list.
  3. Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.

Try it with your agent

After installation, start with a request like:

Example request
Use the Anibon Donation Classifier skill to help with my task.
Ask me for the context you need before getting started.

Requirements & license

  • A coding agent that can access your project files and install skills.
  • Your agent checks each skill’s instructions, dependencies, and permissions during setup.
  • License details are not provided in these listings. Check the author’s terms before using the skills.
AI Agent Workflow Collection | Agent Skills Atlas