KimYx0207

KimYx0207/Meta_Kim

Agent Claude Code

Match the right skills, tools, and capability packages for a MetaKim agent or workflow.

KimYx0207/Meta_Kim

Agent Claude Code

Orchestrate evolution writeback for MetaKim — aggregate signals, coordinate writeback through Warden's gate, and prevent recursive self-evolution.

KimYx0207/Meta_Kim

Agent Claude Code

Design workflow orchestration, business-flow blueprints, stage sequencing, and rhythm control for MetaKim systems.

KimYx0207/Meta_Kim

Agent Claude Code

Design SOUL.md and the core prompt architecture for new MetaKim agents.

KimYx0207/Meta_Kim

Agent Claude Code

Design memory, knowledge persistence, and continuity strategy for MetaKim agents.

KimYx0207/Meta_Kim

Agent Claude Code

Review MetaKim outputs for quality drift, AI slop, and evolution signals.

KimYx0207/Meta_Kim

Agent Claude Code

Discover external tools and skills to close MetaKim capability gaps.

KimYx0207/Meta_Kim

Agent Claude Code

Design security boundaries, hooks, permissions, and rollback rules for MetaKim agents.

KimYx0207/Meta_Kim

Agent Claude Code

Coordinate the MetaKim agent team, quality gates, and final synthesis across the other meta agents.

KimYx0207/Meta_Kim

Command Claude Code

Reopen a MetaKim governed run report.

KimYx0207/Meta_Kim

Command Claude Code

Run the appropriate MetaKim verification path.

KimYx0207/Meta_Kim

Command Claude Code

Run the MetaKim meta-theory governance dispatcher.

KimYx0207/Meta_Kim

Skill Claude Code

Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…

KimYx0207/Meta_Kim

Cursor rule Cursor

MetaKim choice-surface fallback — stable Cursor trigger for blocking user decisions.

KimYx0207/Meta_Kim

Cursor rule Claude CodeCursor

Meta-agent execution boundary enforcement — meta- agents must not perform direct execution work in Cursor.

KimYx0207/Meta_Kim

Cursor rule Cursor

Meta-theory dispatch entry and deep Fetch requirement for Cursor.

KimYx0207/Meta_Kim

Skill Claude Code

MetaKim executable governance dispatcher. It classifies the run, loads only needed references, preserves foundational capabilities and runtime-native abilities, routes owner + weapon + dependency + runtime + OS + verification, and closes only with evidence, intent acceptance, and writeback decision.

KimYx0207/Meta_Kim

Skill Claude Code

Reusable MetaKim file inventory classification flow. It helps separate durable sources, generated evidence, runtime mirrors, temporary state, and risky unknowns before cleanup or commit.

KimYx0207/Kim_Service

Hook Claude Code

One of 2 in settings.json

Runs when you submit a prompt, before the agent sees it, running node. From KimYx0207/Kim_Service.

KimYx0207/Kim_Service

Skill Claude CodeCodex

A playbook for coordinating several independent coding agents across Claude Code, Codex, OpenClaw, and Cursor. Each agent handles a separate part of a task, and the main agent combines the results.

KimYx0207/Kim_Service

Skill Claude CodeCodex

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill. Also triggers…

KimYx0207/Kim_Service

Skill Claude CodeCodex

A prompt-writing guide for turning vague or complex goals into instructions an agent can execute and check. It produces a Goal Prompt for starting work and a Loop Prompt for reviewing results and continuing later.

KimYx0207/Kim_Service

Skill Claude CodeCodex

A structured decision-review workflow for product, business, engineering, content, and planning questions.

KimYx0207/Kim_Service

Skill Claude CodeCodex

A Chinese-language reference skill describing a structured way to reason from intent and evidence to a decision and next action. It distinguishes quick, standard, and higher-risk workflows.