Official Lark/Feishu CLI tool with 200+ commands and 26 AI agent skills, designed for agent-native operation and easy integration with AI runtimes.

Create a structured post-earnings equity research update with key metrics, estimate changes, charts, and thesis review.

GitHub action to set up PHP with extensions, php.ini configuration, coverage drivers, and various tools.

Help your coding agents (Claude Code, Codex, Qoder, Cursor, and other coding agents) get better at getting better.

LLM-powered engine that compiles raw documents into structured, local-first wikis as a transparent alternative to RAG.

Qodo-Cover: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞

Curated collection of 14 domain-specific agent skills covering the CesiumJS API, installable as a Claude Code plugin or via the Agent Skills standard.

Admin / analytics dashboard in a single HTML file. Fixed left sidebar, top bar with user/search, main grid of KPI cards and one or two charts. Use when the brief asks for a "dashboard", "admin", "analytics", or "control panel" screen.

A CLI and local admin UI for previewing and publishing static HTML, Markdown, and mini apps to Cloudflare Pages, ideal for agent-generated reports.

A collection of 19 Claude Code skills for cybersecurity professionals covering offensive security, defensive operations, reverse engineering, threat hunting, and CSOC automation.

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

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.