Implement comprehensive error handling for Python code paths to keep services resilient and user-friendly. Use when failures are currently silent or exceptions leak through.
中文简介正在准备中。当前显示原文说明。
Check if a pull request is too large and guide splitting it into focused PRs.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
I help you assess whether a PR is too large and guide you through splitting it if needed:
Oversized PRs slow review, increase risk of missed issues, and frustrate reviewers. This skill prevents that.
Use when you want to:
Stage: Scope sizing and split planning (usually before requesting review).
pr-self-review for a full author checklist beyond PR size/scope.pr-create to draft and open the PR once scope is settled.pr-review for reviewer-side feedback on an already-open PR."Is this PR too big?" "Help me split this PR into smaller ones" "Check my PR size and suggest a split strategy"
Here's how I guide you through PR size assessment and splitting:
I'll ask for your PR stats if not provided in context:
Alternatively, you can paste the PR diff or provide a link to an open PR.
I'll evaluate against the standard threshold:
Examples:
✅ Your PR is appropriately sized!
⚠️ Your PR is too large.
I'll help you split it:
Identify distinct concerns: Read the diff and group changes by concern
Order by dependency: Determine the sequence for splitting
Example order:
PR-1: Add auth validation (core)
PR-2: Update payment to use auth (depends on PR-1)
PR-3: Documentation and cleanup (independent)
Guide branch strategy: Create a plan for splitting
main or previous PR branch (if dependent)Walk through execution: Help you execute the split
🔒 Large but can't be split
Some changes are genuinely atomic and can't be split (e.g., auto-generated files, schema migrations, large renames). I'll help you handle this:
Document in PR description:
NOTES: This PR is larger than our standard threshold because:
[Explain why it cannot be split]
Guide review strategy:
Suggest alternatives:
Why 400 lines?
Why "concern-based" splitting?
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Implement comprehensive error handling for Python code paths to keep services resilient and user-friendly. Use when failures are currently silent or exceptions leak through.
中文简介正在准备中。当前显示原文说明。
Tabular and numerical data analysis with descriptive statistics and insights. Use when the user provides data, tables, CSVs, or numbers and wants analysis.
中文简介正在准备中。当前显示原文说明。
Financial factsheet analysis with key metrics extraction and investment rationale
中文简介正在准备中。当前显示原文说明。
Diagnose and fix CI failures without leaving your editor.
中文简介正在准备中。当前显示原文说明。
Reproduce ai-repo PR checks locally with Poe and CI scripts, including per-package typecheck and coverage behavior. Use when validating changes before push or when user asks which local commands match CI.
中文简介正在准备中。当前显示原文说明。
Ask clarifying questions before implementing to ensure Python requirements are understood. Use when a task lacks detail, dependencies are unclear, or multiple interpretations are possible.
中文简介正在准备中。当前显示原文说明。