Orbit Prompt — Development skill for Claude Code
Analyze and improve your prompt before sending — returns ORIGINAL PROMPT, ANALYSIS, IMPROVED PROMPT, KEY IMPROVEMENTS, READY TO SEND.
How to install Orbit Prompt
Installs to ~/.claude/commands/ianvdev-orbit-prompt-orbit-prompt.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/IanVDev/orbit-prompt/HEAD/.claude/commands/orbit-prompt.md -o ~/.claude/commands/ianvdev-orbit-prompt-orbit-prompt.md Restart Claude Code, or start a new session, for it to be picked up.
What Orbit Prompt does
description: Analyze and improve your prompt before sending — returns ORIGINAL PROMPT, ANALYSIS, IMPROVED PROMPT, KEY IMPROVEMENTS, READY TO SEND. Optional --persona/--contract (with --context-file) for layered composition.
Apply the orbit-prompt skill to the user's request.
**Language rule:** Always respond in English by default, regardless of the language the user writes in. Only use another language if the user explicitly requests it.
**Mode selection:**
Detect whether the user pa
Alternatives in Development
- Returns — 组合收益归因 — 拆解总收益为各持仓贡献 + 行业/流派归因 + Top 贡献/拖累 + vs 基准 6.6k ★
- Review Claudemd — Review recent conversations to find improvements for CLAUDE.md files 6.5k ★
- Contributing To Claude Code Configs — Thank you for your interest in contributing to Claude Code Configs 625 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Improve Code
Smart code improvements with safety and performance focus
Improve Skill
Propose and apply targeted improvements to a specific Claude Code skill (self-improving skills AMEND layer)
Ilk Self Improve
Plan toolkit improvements from the shared improvement backlog.
Muse:Chain
Run a sequential multi-persona chain on a question. Each persona sees the original question plus a 2-3 sentenc
Daedalai Bug
File a BUG work item from an error message + optional stack trace. Fingerprint-based duplicate detection retur
Loopgen Rs
Agentic loop runner for Claude Code — turns a goal into an iterative claude -p loop with a LOOP_STATUS termina
Related Agents
Relay Reviewer
One round of the multi-model relay. Reads the original, the previous draft and the previous notes, writes an i
Code Refactor
Improve code structure, performance, and maintainability through systematic refactoring. Specializes in legacy
Memory Analysis Agent
Analyses collected session feedback, detects recurring patterns, and proposes concrete skill improvements. Use