Every paid pack we publish, in one download: 30-Day Short-Video Kit, SaaS Competitor Pages, Amazon Listing Fix Kit, CSV to Board PPTX, and the full Postgres Release-Safety set (Migration Review, Lock Triage, EXPLAIN Reviewer). US$82.96 bought separately - US$29 here. Run locally in Claude, ChatGPT, Gemini, or any AI assistant. No subscription, no extra API key.
更少 Token，更精準的 AI 指令。以語意最佳化移除冗餘、合併重複要求，保留真正意圖、必要限制、輸出格式與重要上下文；提供 Token 估算，並可依要求比較優化前後差異。支援 MAX_COMPRESSION、BALANCED、MAX_PRECISION。
One agent takes a short video from brief to a publish-ready pack: hook variants scored by visible rules, a timed shot list, per-shot prompts that repeat the same character and style text, captions and a cut list. Then a pre-flight QA checks claims, sources, real-person likeness consent, asset licenses, AI labelling, pacing and platform limits. Offline deterministic script. It does not generate video or promise views.
Turn higher-AOV goals into a testable bundle, add-on, or tiered offer without random discounting. This skill maps buyer context, hero SKU, companion items, margin guardrails, inventory and return risk, pricing ladder, listing message, A/B test plan, and success metrics.
120 structured, copy-paste prompts across marketing, business writing, development, and data analysis. Every prompt uses role → context → output format → constraints — fill in the {variables} and it works on ChatGPT, Claude, or Gemini. Includes a customization guide.
This agent helps Python teams using the Anthropic or OpenAI SDK safely cut LLM spend without risking regressions. With zero code changes, it maps call sites and runs your test scenarios to rank token waste from missed prompt caching or heavy model tiers. It tests fixes in isolated git worktrees, enforcing a strict "do-no-harm" gate that reverts any patch failing to preserve behavior. It delivers a clear savings audit that converts into verified, behavior-preserving code patches upon opt-in.
A downloadable Product SNS Lite skill bundle for Codex-style agents. Turn a product, service, landing page, or source URL into a review-ready campaign pack: evidence summary, audience diagnosis, safe/risky claims, campaign angles, social post drafts, GPT Image 2 creative prompts, posting calendar, approval checklist, and automation handoff specs.
Compresses AI filler text — preambles, transitions, repetitions — at 3 intensity levels (Lite / Full / Ultra) while enforcing a protected scope (URLs, numbers, code, reasoning) that is never deleted, so "be concise" stops silently destroying what matters.
Boost smaller AI models with better planning, context management, validation, repair loops, tool use, and structured execution — without relying on a larger model.