Describe what you need — a presentation, lesson, or story — and let the AI build clean, beautiful HTML slides for you. Local-first. Works offline. Works for you.

A two-spread digital e-guide preview — page 1 is a cover (display title, author, "What's inside" stats, table of contents teaser); page 2 is a spread (lesson body with pull-quote and a step list). Lifestyle / creator brand tone. Use when the brief asks for an "e-guide", "digital guide", "lookbook", "lead magnet", "creator guide", "playbook", "PDF guide", or "电子指南".

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

Turn creator performance data into a documented retrospective, grounded hypotheses, and reusable content learnings.

Learn from your vibe coding instead of just clicking Accept. AhaDiff turns each AI diff into a code-verified lesson, quiz, and review. · 别再无脑 vibe coding 啦！让你从 vibe coding 中学到真东西。每次改动都变成能查证的课程、测验和复习。

A collection of minimalistic, project-agnostic skills and rules for AI coding agents to improve documentation, context hygiene, and self-improvement.

AI tutor skill for Claude Code using spaced repetition and personalized project examples with a progress dashboard.

Raise real concurrency in asyncio LLM batch scorers built on the OpenAI SDK (AsyncOpenAI, including OpenAI-compatible providers like DeepSeek). Use when: (1) raising an asyncio.Semaphore above ~100 produces no throughput gain, (2) a batch pipeline saturates near 100 in-flight requests despite a larger semaphore, (3) planning a high-concurrency campaign against a provider with no hard rate limit (DeepSeek v4-flash tolerates 2000+ in flight). Root cause: AsyncOpenAI's default httpx pool caps max_connections at 100, silently bottlenecking any larger semaphore — you must pass a custom http_client with httpx.Limits sized to the semaphore.

Documentation maintenance rules — which docs map to which code areas, the thin-pointer/no-drift rule, and the graphify-update step. Owned by project-steward. Load for /update-docs and the docs-sync step of the implement-workflow.

Smart update for SDLC wizard — shows changelog, compares files, lets you selectively adopt changes while preserving customizations.

Machine learning fundamentals lesson in interactive notebooks

Lesson material on data science and machine learning topics/concepts