Make a rule the assistant actually follows by moving it out of the prompt and into a hook that runs every time. When you have said the same thing three times and the behaviour still drifts, this is the fix. Covers which hook events carry the value, the exit-code rule that wedges sessions, how to test a hook with temporary settings so nothing is left behind, a skeleton that cannot crash your turn, and the escape hatch for when one does.
Helps users turn rough prompts into clear, specific, reusable prompts in different LLMs through concise critique.
Turn any topic into ready-to-post vertical micro-Shorts. Get finished 9:16 images with exact on-image text, safe mobile placement, calls to action, loop-focused pacing, and complete YouTube titles, descriptions, hashtags, and tags.
LLMエージェントがセッションをまたいで記憶を保持するための永続メモリ層。抽象基底クラス MemoryStore ＋ LocalJSONStore 実装で、保存・取得・検索を再利用可能に。Karpathy の「LLM OS（記憶＝ディスク層）」着想。バックエンド差し替え可・Python標準ライブラリのみ・LLM呼び出しゼロ・ユニットテスト同梱。
Predict second-by-second viewer retention for the first six seconds of a short-form video hook, then provide concrete opening fixes.
Turn openings that get scrolled past in 3 seconds into hooks that stop the scroll. Pin down the content's real payoff and the scrolling context the audience meets it in; diagnose the old opening against five common hook-killers; then mass-produce 10 variants from an eight-pattern hook matrix (curiosity gap, counterintuitive, specific number, and more), adapt them per platform, and finish with a payoff check and an A/B plan.
Diagnose why your TikTok, Reels, or Shorts video loses viewers in the first 3 seconds. Get 3 high-retention replacement hooks with visual cues, spoken lines, text badges, and a shot-by-shot edit table ready to film.
HyperFrames from NousResearch’s Hermes project, created by HeyGen. Use it to turn text, scripts, websites, or HTML/CSS/JS compositions into polished MP4/WebM videos. Build motion graphics, product tours, captioned videos, social overlays, TTS narration, audio-reactive visuals, and scene transitions, with frame-by-frame rendering and built-in quality checks.
Wraps each phase of a long AI task in a start-check / work / end-check bracket — and re-anchors the original instructions at every phase boundary so the agent cannot drift from its rules or skip verification as the session grows longer.