一键导入
coder-rules-debug-requirements
Debugging requirements protocol from reproducible issue to verified fix and regression protection.
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
Debugging requirements protocol from reproducible issue to verified fix and regression protection.
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
Mandatory baseline rules for any agent. Must be loaded before any work
Frontend design system practices: tokens, typography, color, layout, and component consistency.
Frontend UI/UX practices: flows, interaction states, accessibility-first UX, forms, and perceived performance.
Clean code execution rules for coding agents with verifiable quality gates.
Requirement quality rules for coding tasks with traceable MUST/SHOULD and verifiable acceptance criteria.
API design rules for stable, observable, backward-compatible HTTP APIs.
| name | coder-rules-debug-requirements |
| description | Debugging requirements protocol from reproducible issue to verified fix and regression protection. |
<when_to_use> Investigating functional bugs, crashes, regressions, or production incidents Need structured debug flow for coding agent execution Need explicit completion criteria for bug fixes </when_to_use>
<input_requirements> Symptom statement and impact Expected vs actual behavior Minimal reproducible example (steps/data) Environment fingerprint (version, config, flags) Evidence pack (errors, logs, traces, timestamps) </input_requirements>
<debug_workflow> Triage impact and confirm current reproducibility Build minimal reproducible case Localize failing layer and narrow search space State testable hypothesis and instrumentation plan Apply minimal root-cause fix Verify fix against acceptance criteria Add regression test/eval that fails before and passes after Record residual risks and follow-up actions </debug_workflow>
<quality_rules> No reproducible signal means no claim of confirmed fix Bugfix is incomplete without regression protection Fix must target root cause, not only symptom masking Verification must include evidence from commands or telemetry </quality_rules>
<required_signals> Repro rate before and after fix Error rate or failure count change Latency/perf guardrail impact when relevant Regression suite result for affected path </required_signals>
<do_not> Do not debug by guesswork without hypothesis Do not close issue without reproducible verification Do not skip regression test because fix "looks obvious" Do not merge broad refactor as hidden hotfix </do_not>
<output_requirements> Problem statement with expected vs actual Root cause summary and impacted components Fix summary with evidence of verification Regression artifact added and location </output_requirements>