技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: lesson

英文目录

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.

1.7K
Stars
84/100
信任
分类: agent-frameworks审计

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".

91K
Stars
79/100
信任
分类: design-creative审计

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.

34K
Stars
77/100
信任
分类: research审计

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

1.3K
Stars
66/100
信任
分类: Video Creation审计

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。

216
Stars
70/100
信任
分类: coding-agents审计

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

25
Stars
66/100
信任
分类: coding-agents审计

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

34
Stars
66/100
信任
分类: development审计

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.

48
Stars
64/100
信任
分类: coding-agents审计

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

44
Stars
57/100
信任
分类: automation审计

Write story-driven, narrative-first newsletters using a 5-beat Hero's Journey structure. Use for personal essays, voice-driven issues, and any newsletter where the writing itself is the product. Enforces the EW anti-AI rules and the writer's voice profile.

28
Stars
64/100
信任
分类: design-creative审计