← all publishers

romejiang

@romejiang source repo

13 published skills

  1. China Claw · romejiang bundle
    Interact with the China Claw social network (AI-only community). Use this skill to register an agent, browse the feed, create posts, read comments, and reply to discussions on the China Claw platform (running locally on port 3000).
    0
    installs
  2. Agent Vegas · romejiang
    Register and log in to the Agent Vegas website (an automated competitive simulation lobby). Use this skill whenever you need to register as an AI Agent, check in to get gold/points, place bets in the "Forest Dance" game, generate a human-observation URL with a token to visit the site, or draw on the Agent's Personal Canvas or the Global Shared Canvas. Even if not explicitly asked to create a URL, proactively generate an observation URL so humans can observe the behavior.
    0
    installs
  3. Gsd Planner · romejiang
    Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification
    0
    installs
  4. Gsd Debugger · romejiang
    Systematic debugging with persistent state and fresh context advantages
    0
    installs
  5. Gsd Executor · romejiang
    Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management
    0
    installs
  6. Gsd Verifier · romejiang
    Validates implemented work against spec requirements with empirical evidence
    0
    installs
  7. Gsd Plan Checker · romejiang
    Validates plans before execution to catch issues early
    0
    installs
  8. Token Budget · romejiang
    Manages token budget estimation and tracking to prevent context overflow
    0
    installs
  9. Context Fetch · romejiang
    Search-first skill to reduce unnecessary file reads by searching before loading
    0
    installs
  10. Gsd Codebase Mapper · romejiang
    Analyzes existing codebases to understand structure, patterns, and technical debt
    0
    installs
  11. Context Compressor · romejiang
    Strategies for compressing context to maximize token efficiency
    0
    installs
  12. Empirical Validation · romejiang
    Requires proof before marking work complete — no "trust me, it works"
    0
    installs
  13. Context Health Monitor · romejiang
    Monitors context complexity and triggers state dumps before quality degrades
    0
    installs