zhmxiaowo

zhmxiaowo/opencode-simple

Command

Recommend the best model tier for the current task by complexity and budget.

zhmxiaowo/opencode-simple

Command

Sequential agent workflow for complex tasks. Coordinates multiple agents in defined patterns.

zhmxiaowo/opencode-simple

Command

Spec-First research + implementation plan. Outputs SPEC (API/types/deps) AND step-by-step phases with dependency graph. WAIT for user CONFIRM before touching any code.

zhmxiaowo/opencode-simple

Command

List known projects and their instinct statistics from the continuous learning system.

zhmxiaowo/opencode-simple

Command

Promote project-scoped instincts to global scope when confidence threshold is met.

zhmxiaowo/opencode-simple

Command

Run the quality pipeline on demand for a file or project scope. Supports --fix and --strict modes.

zhmxiaowo/opencode-simple

Command

Safely identify and remove dead code with CDD compile verification at every step.

zhmxiaowo/opencode-simple

Command

Load the most recent session file from /.claude/sessions/ and resume work with full context from where the last session ended.

zhmxiaowo/opencode-simple

Command

Save current session state to a dated file in /.claude/sessions/ so work can be resumed in a future session with full context.

zhmxiaowo/opencode-simple

Command

Manage session history - list, load, alias, and edit sessions.

zhmxiaowo/opencode-simple

Command

Configure your preferred package manager (npm/pnpm/yarn/bun) for the project.

zhmxiaowo/opencode-simple

Command

Analyze local git history to extract coding patterns and generate SKILL.md files.

zhmxiaowo/opencode-simple

Command

A shortcut that creates a technical specification for a proposed feature without creating the full implementation plan.

zhmxiaowo/opencode-simple

Command

Analyze the codebase structure and generate token-lean architecture documentation (codemaps).

zhmxiaowo/opencode-simple

Command

Sync documentation with the codebase, generating from source-of-truth files.

zhmxiaowo/opencode-simple

Command

Run CDD verification on current codebase. Checks compile, types, LSP, lint, secrets, debug logs, and AI slop. No tests.

zhmxiaowo/opencode-simple

Skill Claude CodeCodex

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

zhmxiaowo/opencode-simple

Skill Claude CodeCodex

Engineering operating model for teams where AI agents generate a large share of implementation output.

zhmxiaowo/opencode-simple

Skill Claude CodeCodex

REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.

zhmxiaowo/opencode-simple

Skill Claude CodeCodex

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

zhmxiaowo/opencode-simple

Skill Claude CodeCodex

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

zhmxiaowo/opencode-simple

Skill Claude CodeCodex

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation…

zhmxiaowo/opencode-simple

Skill Claude CodeCodex

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

zhmxiaowo/opencode-simple

Skill Claude CodeCodex

Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.