Search

Fit chat history into any model's context window: token estimation, sliding-window packing with a running summary, and overflow detection. Zero dependencies, no AI inside.

��# Storage Use: ``` import { Storage } from '@cardsjd/storage'; this.storage = new Storage(AppConfig); ```

OpenAI-compatible proxy that adds functionality to models through tricks

Opinionated & Autonomous AI Code Assist PR review loop for Claude Code & Codex. Support Codex and Gemini Code Assistance; Thread-state-aware, Framework-aware for acceptance tests, severity-filtered, cycle cap, sticky-receipt visibility.

A Claude skill for the safe, gated review & update of Android (Kotlin/Gradle) dependencies in a version catalog — detects updates, analyzes risk, and applies only after your confirmation.

Diagnose Chrome Manifest V3 extension pitfalls — and teach AI coding agents to avoid them.

Always-current official Claude docs inside Claude Code. A 3 MB metadata plugin: live on-demand fetching from Anthropic's servers, zero content redistributed. Auto-discovery skill, instant search, interactive HTML courses, and doc changelog reports.

Agent-native skill for publishing local projects to GitHub with zero-config proxy detection

Executive business analysis skill for Claude — Big Four-grade consulting from any Excel/CSV file (Arabic RTL)

Instagram marketing skills for Claude Code and Codex: captions, carousels, hooks, hashtag strategy, and a weekly plan. Draft, humanize, and publish via Publora. MIT.

Typography skill for AI agents - audit and produce publication-grade text. Butterick's Practical Typography for your coding agent.

Companion OpenClaw skill for the Unity plugin — teaches AI agents the tool surface and editor workflows so they can drive Unity remotely.

Companion OpenClaw skill for the Godot plugin — teaches AI agents the tool surface and editor workflows so they can drive Godot remotely.

Companion OpenClaw skill for the Unreal plugin — teaches AI agents the tool surface and editor workflows so they can drive Unreal Engine remotely.

An agent composition framework that builds stacks and compiles specialized subagents for Claude Code

Learn TypeScript with Handbook-aligned exercises, a local progress tracker, and AI mentor rules that give hints — not spoilers.

Ruleshub is a comprehensive collection of AI-optimized rules and guidelines for popular APIs and platforms.

Standalone Nostr agent on the Pi SDK (autogent-nostr), with a Buzz Desktop backend provider that deploys it.

Seven reliability primitives for any LLM API: Chain-of-Verification, self-consistency, best-of-N, reflexion, debate, drift detection, hedged execution.

OMP plugin for manual graph construction and LLM context synthesis from source code.