Project context for AI coding agents — lazy-loaded per project, with an agent-native Kanban, idea canvas, and spec-driven task creation. For OpenClaw and external agents.

Sync one reviewed context source into native AI-agent files, with privacy-safe evidence receipts that never confuse generation with runtime load.

Bundle of skills to supercharge your coding agents.

Generate and safely maintain AGENTS.md, the cross-tool standard for AI coding agents. Non-destructive re-runs, never fabricates, three-tier boundaries.

Canonical frontend stack blueprint for AI coding agents: TypeScript, React, Vite, Vitest, Tailwind, TanStack, and shadcn/ui, with strict architecture rules, versioned docs, and a machine-readable manifest for bootstrapping modern web, Electron, Tauri, and PWA projects.

15 frontend craft skills for AI coding agents. Interviews or audits you into a real design system, then verifies typography, OKLCH color, states, forms, charts, a11y, and anti-slop.

Local-first governance for AI coding agents: the external, files-only record that verifies what your agents did, so no agent is the sole witness to its own work. One agent per lane, approvals, gates, a tamper-evident record you own. Nothing leaves your machine.

Claude Code plugin marketplace for Angular + .NET + SQL Server + Azure - governance skills, agents, and audit/fix pipelines for full-stack Microsoft shops.

Offline Markdown mirror of the ElevenLabs Agents (ElevenAgents) docs, 407 pages: agent platform, customization, telephony, SDKs, guides, and the full Conversational AI API reference. Drop next to your project so AI coding agents (Claude Code, Cursor, Aider) grep real docs instead of hallucinating endpoints.

Verified code examples and artifacts for TimTalks articles.

Original Claude skills, Codex skills, Cursor rules, Gemini instructions, and prompts for OpenAI-compatible base_url setup.

Hermes/OpenClaw provider-agnostic coding dispatch skill for approval-gated AI coding from any channel.

My son's 1st-birthday RSVP site: a festa-junina invitation shipped end-to-end with Claude Code as a platform. Cloudflare Pages + D1 + Pages Functions + R3F WebGL, $0/mo on the free tier. CLAUDE.md captures the project memory and skill-invocation conventions.

Integration-first operating protocol for AI coding agents — coordinate Codex, OpenCode, Augment, OpenClaw, Hermes through repo-native files

Hands-on git coaching skills for AI coding agents: real commands, plain-English why, undo-first recovery, and safe practice drills.

This repository demonstrates that the benchmark framework generalizes to codebases of any size. It serves as a Config C test target for the external orchestrator configuration described in the paper "Context-Augmented Code Generation".

Autonomous software delivery for AI agents. 18 skills that turn the lifecycle into bounded, self-correcting, checkpoint-resumable phases with deterministic enforcement hooks and a self-improving learn/map loop. For Claude Code and Codex.