Search

Tessera SDK — drop-in LLM cost optimization. One line patches OpenAI, Anthropic, Mistral, Groq, Cohere clients to route through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free tier: 60M tokens/mo. Production: 20% of measured savings, $0 if none.

Official scaffolder for the Agentic Dev ecosystem — bootstraps a project from agentic-dev-boilerplate and runs its interactive installer.

Convert handwritten documents into structured JSON with vision LLMs.

Claude Code tmux watchdog — auto-unblock permission dialogs

AST-aware llms.txt generator for Python and JavaScript/TypeScript codebases

Intelligent interrupt layer for Claude — learns when to ask, when to proceed

Predict protein subcellular localization using protein language model embeddings.

Pre-ingestion PII de-identification for Australian government data, using zero-shot LLM detection with checksum validation.

Shell-GPT 自动安装和配置工具：对接 SiliconFlow API，全程国内镜像，专为教学场景设计

AI-assisted web data extractor — paste a URL + plain-English instruction, get structured JSON or CSV. Resilient to DOM changes via semantic LLM extraction.

Protocol converter supporting OpenAI Chat, OpenAI Responses, and Anthropic protocols

A Claude Skill for rigorous source-criticism of Chinese classical texts.

Drop-in Claude Code skill bundle for AI-resistant SEO article generation — research → write → E-E-A-T audit, configurable for any site or language.

Claude Code skill — design visuals for technical course materials using Dan Roam, Mayer, C4, cognitive load theory, and Gestalt/CRAP

A Claude skill that scans drafts for AI writing tells and rewrites them out without flattening your voice

Claude Code skill that audits a shipped repo for the production-readiness gaps ~70% of AI-coded projects miss · companion to in-session security skills, scans the deployed product not the editor buffer

Claude Code skill that raises any website's SiteDex AI-readiness score in a single PR. Distilled from 3 PRs and 3 re-audits on agentroot.io.

Partner-grade LLM agent evaluation framework. Verbatim BCG rubric, adversarial Skeptic Agent for sycophancy/ambiguity detection, 10-signal Novelty Stack. Anthropic skill, Claude-native — no API keys.

基于微信读书官方 Agent Skill 的二创项目精选 · Curated projects built on WeRead's official Agent Skill (released 2026-05-17)

Local CLI tool for GitHub RAG, Call Graphs, and Codebase querying.