一键导入
godmode-debug
Systematic debugging for Rust. Use before proposing any fix — establish root cause first, then write a failing test, then fix.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Systematic debugging for Rust. Use before proposing any fix — establish root cause first, then write a failing test, then fix.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Write an implementation plan as a markdown file, then immediately serialize it to a timestamped YAML task file in .ctx/tasks/. Use before touching any code when given a spec or approved design.
Design-first workflow for new features, components, or architecture decisions. Use before writing any code — get explicit approval on a design first.
Commit-and-push workflow with validation. Use when asked to "cap", "commit and push", or "ship it".
Dispatch parallel subagents for independent tasks. Use when 2+ tasks have no shared state or sequential dependencies.
Task graph management for a session. Use to create tasks, track progress, execute the next unblocked task, or manage dependencies between work items.
Test-driven development workflow for Rust. Use before writing any implementation code — write a failing test first, then implement, then refactor.
| name | godmode-debug |
| description | Systematic debugging for Rust. Use before proposing any fix — establish root cause first, then write a failing test, then fix. |
Rule zero: No fix without a root cause. Symptom patches that mask underlying problems are not fixes.
Before touching any code:
Parse the error exactly. Read the full message, stack trace, and context. Do not skim.
Reproduce it consistently:
RUST_BACKTRACE=1 cargo nextest run -p <crate> -- <test_name>
Check environment first. Missing env vars and unresolved op:// refs are the most
common root cause. Verify before investigating code.
Check recent changes.
git diff HEAD~1
git log --oneline -10
For multi-component failures: add diagnostic output at each boundary. Trace data flow backward from the symptom.
Only after root cause is confirmed:
cargo nextest run -p <crate>
cargo clippy -p <crate> -- -D warnings
RUST_BACKTRACE=full for panics; RUST_LOG=debug for tracingcargo check before cargo nextest — catch compile errors cheaplyIf 3 sequential fix attempts all fail, stop. Surface the deeper problem to the user.
unwrap() to "fix" an error — propagate it properly