By IvanLutsenko
Automated vertical clip creator for talks and presentations. Whisper transcription + Claude analysis (moments + smart crop) + ffmpeg processing. Full pipeline: video → transcribe → find moments → crop analysis → cut clips → subtitles → social media copy.
Create vertical clips from a video. Full pipeline: transcribe → find moments → crop → cut → subtitles → copy
Transcribe a video using whisper (local or API)
Find interesting moments in a transcript or video
Analyzes whisper transcript to find the most engaging moments for vertical clips. Looks for strong quotes, complete thoughts, practical advice, and provocative statements.
Analyzes video frames to determine optimal crop position for vertical (9:16) clips. Uses vision to locate the speaker and calculate crop coordinates.
Generates platform-specific social media descriptions for video clips. Creates copy for YouTube Shorts, Instagram Reels, and TikTok.
Create vertical clips from a video. Full pipeline: transcribe → find moments → crop → cut → subtitles → copy. Use when the user invokes /clip-maker.
Find interesting moments in a transcript or video. Use when the user invokes /find-moments.
Transcribe a video using whisper (local or API). Use when the user invokes /transcribe.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Custom AI agent plugins by Ivan Lutsenko
Add the marketplace once, then install plugins as needed:
/plugin marketplace add https://github.com/IvanLutsenko/awac-ai-agent-plugins
Compatibility: the previous repository slug,
awac-claude-code-plugins, is kept as a supported fallback for existing
Claude Code marketplace installations.
Automated unit test generation for Kotlin/Android business logic with corporate standards.
Installation:
/plugin install bereke-business-test-gen
Quick Start:
/test-class src/main/java/.../YourClass.kt # Single class (2-15 min)
/test-module feature/auth # Full module coverage (30-90 min)
/test-diff [--branch origin/master] # PR workflow (tests only for changed files)
/test-fix [--all] feature/auth # Auto-fix existing tests to standards
/validate-tests feature/auth # Validate tests against standards
Status: ✅ Production Ready | Version: 2.7.2
What's New in 2.7.2:
awac-ai-agent-plugins and fall back
to the legacy awac-claude-code-plugins install path.Key Features:
Multi-platform crash analysis for Android & iOS with git blame forensics, code-level fixes, and a deterministic quality gate.
Installation:
/plugin install crashlytics
/crashlytics:install-permissions # one-time: add read-only git/MCP to allowlist
Quick Start:
/crash-report ca8f7f21e3... # Unified (auto-detects platform from config)
/crash-report-android # Explicit Android
/crash-report-ios # Explicit iOS
/crash-config # Configure plugin settings
/crashlytics:install-permissions # Add read-only allowlist to settings.json
Status: ✅ Production Ready | Version: 4.4.3
What's New in 4.4.3:
SECTION_ALIASES для en/ru/es/de/fr/pt/it (фикс false 6/14 на не-английских отчётах). Forensics-агенты пишут headers всегда на английском, body — на target language.BRANCH_REF (= origin/<default_branch>) вместо хардкода master + обязательный git fetch origin --quiet перед blame/log/show. STEP 4.0 sanity-check «is the fix already merged in BRANCH_REF»./crashlytics:install-permissions — мерджит read-only allowlist в settings.json (user или project уровень на выбор).scripts/tests/.Features:
origin/<default_branch>crashlytics_get_issue + crashlytics_batch_get_events), REST v1alpha fallback, Manual mode for offline useProject tracking, task management with kanban boards, bug logging, decision records (ADR), and session management via Obsidian. Auto-tracks sessions, actions, bugs, and commits via hooks.
Installation:
/plugin install obsidian-tracker
cd plugins/obsidian-tracker/mcp && npm install && npm run build
Quick Start:
/track-start my-project # Start auto-tracking session
/projects # List all projects
/project-new # Create new project
/task my-project "Fix bug" # Create task on kanban board
/done my-project 1 # Mark task as done
/project-archive archive old-project # Archive a project
/track-stop # Save session to Obsidian
Status: ✅ Production Ready | Version: 4.3.2
What's New in 4.3.2:
awac-ai-agent-plugins project slug.Features:
Multi-agent code review with CodeRabbit CLI integration. 4 specialized agents + optional CodeRabbit for comprehensive review.
Automated unit test generation for Kotlin/Android business logic with corporate standards
macOS notifications in your system language. Auto-translates via Google Translate with local caching. Supports custom messages.
Project tracking, task management with kanban boards, bug logging, decision records (ADR), session management, and engineering traceability via Obsidian. Auto-tracks sessions, actions, bugs, and commits via hooks.
Automatically syncs Claude Code theme with macOS system appearance (dark/light mode). Checks on every user message via UserPromptSubmit hook.
Multi-platform crash analysis for Android & iOS with git blame forensics, code-level fixes, and deterministic quality gate. MCP-primary fetch with REST API fallback. Language-aware validator and origin/<branch> forensics.
npx claudepluginhub ivanlutsenko/awac-ai-agent-plugins --plugin clip-makerEdit CapCut and JianYing projects from Claude Code — subtitles, timing, speed, volume, templates, cut long-form to shorts.
Full video production pipeline for Remotion — gives Claude eyes (video analysis), voice (TTS/voiceover), ears (music/SFX), stock footage, AI image/video generation, TikTok captions, 3D content, and more. By Dojo Coding Labs.
Content extraction and processing utilities for developers
Complete YouTube content production workflow: research competitors, generate video ideas, build briefs, craft titles and thumbnails, and create detailed video outlines with demo prep checklists.
Generate Korean podcast episodes from any source (URLs, tweets, articles, PDFs) with OpenAI TTS and auto-upload to YouTube
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.