Designing, evaluating, and shipping autonomous AI agents.
9607 posts
Turn goals and existing Agent tools into readable, reviewable, reusable workflow Skills.
Fluent argument validation for fluent software development.
Local, revision-safe Blender VSE control for AI agents: typed timeline edits, four MCP tools, bounded context, and fresh-process persistence...
A Claude skill that turns brainstorming into an interactive mind map of inverted assumptions — no answers, no ranking, just provocations.
Hyperliquid endpoints on Dwellir: HyperEVM JSON-RPC, Info API, gRPC streaming, order book WebSocket
Stop your coding agent from stalling real work on self-invented bookkeeping - receipts, hashes, locks, certification rituals. Ship first, th...
TÜBİTAK TEYDEB/ARDEB çağrı takibi, proje önerisi ön değerlendirme, patent ön araştırma ve 5746 mevzuat uyumu için Claude Code eklentisi. Uno...
A Claude Code skill pack for working on Webflow through the Webflow MCP: hand-routing, hook-enforced publish and delete guards, and a verifi...
Unofficial, safety-first QQ Mail CLI for scripts and AI agents. Read/search/triage/backup/gated-cleanup/allowlisted-send over a stable JSON...
Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential imp...
Battle-tested agent skills mapping the footguns of Kotlin, Compose Multiplatform and the desktop JVM — mined from a production music app, no...
Agent workflow for deadline-bound execution with evidence gates
