gaoguobin/codex-eide-rebuild / skills/eide-rebuild
eide-rebuild
VerifiedEIDE rebuild and compile Agent Skill for Embedded IDE for VS Code workspaces. Runs a Python unify_builder runner and returns compact or full JSON build results.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.3 KB |
| agents/openai.yaml | config | 921 B |
| scripts/eide_rebuild.py | script | 147 B |
| scripts/eide_rebuild/__init__.py | script | 7.8 KB |
| scripts/eide_rebuild/builder_params.py | script | 12.8 KB |
| scripts/eide_rebuild/eide_model.py | script | 1.0 KB |
| scripts/eide_rebuild/executor.py | script | 17.5 KB |
| scripts/eide_rebuild/platform.py | script | 536 B |
| scripts/eide_rebuild/project.py | script | 1.5 KB |
| scripts/eide_rebuild/result_model.py | script | 9.2 KB |
| scripts/eide_rebuild/tools.py | script | 19.2 KB |
agents/openai.yaml
View on GitHubinterface:
display_name: "EIDE Rebuild"
short_description: "Rebuild EIDE workspaces and return compact or full JSON build results"
default_prompt: "Use this Agent Skill when the user asks to compile, rebuild, or verify an EIDE / Embedded IDE for VS Code workspace. It supports natural language prompts such as '你自己编译验证下对不对' and explicit forms such as 'EIDE rebuild C:\\work\\demo\\project.code-workspace'. For normal single-project requests, run `python scripts/eide_rebuild.py rebuild <workspace-or-project-path> --stdout minimal` directly. When the user explicitly asks for subagent/delegated/background rebuild work, prefer the `eide-rebuild` custom agent if available. Never run multiple workers against the same project/build directory concurrently. Report a low-noise summary from stdout, keep resultPath available for follow-up, and read full logs only on failure or explicit request."
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |