gulfclamatores7360/llmception
Explore LLM prompts by building parallel implementation paths in git worktrees to resolve decision points through user input.
Explore LLM prompts by building parallel implementation paths in git worktrees to resolve decision points through user input.
npx add-skill gulfclamatores7360/llmceptionExplore LLM prompts by building parallel implementation paths in git worktrees to resolve decision points through user input.
Use when a task is complex, ambiguous, architectural, debugging-oriented, refactoring-heavy, strategic, causal, performance-sensitive, security-sensitive, multi-file, high-impact, or likely to suffer from hallucinated verification. Builds a disk-backed causal workspace before answering, planning, or modifying files; avoid for trivial edits, simple formatting, and direct factual answers.
Local control tower for orchestrating tmux-based AI agent workflows
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
Battle-tested AI agent skills for WorkBuddy — built by a student who got tired of doing things manually
BenchClaw is a Codex/OpenCode skill workflow for benchmark construction, evaluation, and maintenance. It standardizes the full pipeline—from idea drafting and data generation to evaluation, reporting, failure diagnosis, and skill refinement—so agents can build reproducible, auditable benchmarks with clear quality gates, lineage, and rollback.
Agent-first document ingestion layer on Docling with Markdown, image sidecars, manifests, OCR, and quality gating.