rexleimo
@rexleimo
Public Skills
review-loop
by rexleimo
Automated two-phase code review loop: the coding agent implements a task, then an independent CLI agent (Codex, Claude, Gemini, OpenCode, Aider, or custom) reviews the changes, and the coding agent addresses the feedback. Use when the user requests a review loop, code review cycle, or says "review-loop".
spec-kit-parallel-orchestrator
by rexleimo
Parallel orchestration skill for Spec Kit workflows. When users mention spec kit, enter /speckit. or /prompts:speckit. commands, request spec kit workflow prompt, or need multi-agent collaboration, this skill must be triggered. It validates stages and dependencies first, then splits tasks into 3-6 parallel subtasks, aggregates results, and recursively proceeds to the next round.
openspec-long-running-harness
by rexleimo
Use when implementing long-running agent workflows that need cross-session state persistence, incremental progress tracking, and gate enforcement. Combines OpenSpec spec-driven development with Anthropic's effective harnesses pattern for multi-context-window projects.
superpowers-parallel-agents
by rexleimo
Use when superpowers tasks can be split into two or more independent domains with non-overlapping edit scopes for concurrent subagent execution.
openspec-parallel-agents
by rexleimo
Use when OpenSpec workflows need dependency-aware parallel subagents across OPSX commands, legacy openspec commands, and Codex CLI prompt aliases.
anthropic-1p-prompt-optimizer
by rexleimo
Optimize, rewrite, and evaluate prompts using the Anthropic 1P interactive prompt-engineering tutorial patterns (clear/direct instructions, role prompting, XML-tag separation, output formatting + prefilling, step-by-step “precognition”, few-shot examples, hallucination reduction, complex prompt templates, prompt chaining, and tool-use XML formats). Use for 提示词优化/Prompt优化/Prompt engineering, rewriting system+user prompts, enforcing structured outputs (XML/JSON), reducing hallucinations, building multi-step prompt templates, adding few-shot examples, or designing prompt-chaining/tool-calling scaffolds.
hybrid-executor
by rexleimo
当需要利用 Claude 的代码重构能力或 Gemini 的超长上下文分析时使用。
code-review
by rexleimo
Automated code review for pull requests and code changes using multi-agent architecture with confidence-based scoring. Use when reviewing PRs, auditing code changes, checking guideline compliance, or detecting bugs in diffs. Works with GitHub, GitLab, and local git repositories. Compatible with Claude Code, Codex, Cursor, Windsurf, and other AI coding tools.