Search

Regression-safe OSS contribution pipeline as a Claude Code skill — dedupe, reproduce, attest, throttle, follow-up. Encodes 10 rules so AI-drafted PRs land instead of getting filed as noise.

A set of 8 global skills for Claude Code that enforce disciplined, test-driven agentic development. Install once, use in any project.

Understanding CLAUDE.md, MEMORY.md, SKILLS.md, SOUL.md, and Related Prompting Mechanisms

Self-learning scrum workflow for Claude Code

fraQtl runtime — drop-in loader for fraQtl-compressed Hugging Face checkpoints. Production LLM inference with calibration-aware compression.

11 个面向中文科研写作的 Claude Code 纪律 Skill。

No description available

AI Agent Architecture Evaluation Tool — Benchmarked against SOTA Standards// AI Agent 项目架构评价工具 - 对标SOTA 标准

JSON conversion pipelines via LLM-generated JSONata rules with caching.

Cross-session memory system for AI coding assistants. Persists conversation context, task progress, and reusable experiences across sessions via Markdown files. Features Hook-powered auto-recall, interactive knowledge graph visualization, chronological timeline, and global experience library. Supports Claude Code, Cursor, and OpenCode.

Parallel unit test runner with coverage support

LLM + evolutionary algorithms to optimize programs in multiple languages and domains

PDF RAG-as-a-Service SDK — ingest, query and summarize PDFs in 3 lines

Conformal coverage guarantees for any reward function — wrap a Python callable with provable (1-α) coverage in 5 lines.

None

Install doc-writer AI skill into your project

AI hypothesis-verification loop for existing apps.

Scoped npm package foundation for HagiCode internationalization tooling.

> [!WARNING] > NocoBase Skills is still in draft status. The content is for reference and may change at any time.

Agent-native LLM Wiki — AI-maintained knowledge base with Obsidian compatibility