KakkoiDev/icm-runtime
Interpretable Context Methodology (ICM) — bash runtime + reusable coding agent skills for structured multi-stage AI workflows
Interpretable Context Methodology (ICM) — bash runtime + reusable coding agent skills for structured multi-stage AI workflows
npx add-skill KakkoiDev/icm-runtimeInterpretable Context Methodology (ICM) — bash runtime + reusable coding agent skills for structured multi-stage AI workflows
Mac-native intake stack for agent-heavy work
Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models.
Multi-author novel writing pipeline as Claude Code skills — no API keys
Agent skill that studies any codebase and produces structured knowledge artifacts. Works with Claude Code, Cursor, OpenCode, and any agentskills-compatible agent.
Knowledge Base-centric research skill set for Claude — 16 skills across paper-pipeline, kb-core, and writing-pipeline
An AI-powered product copy reviewer built for Elementor. This skill checks text or screenshots against Elementor’s brand glossary and voice & tone guidelines, identifies misalignments, explains why, and suggests improved, on-brand alternatives. Works with Claude, Codex, Cursor, and other compatible tools.