resolving-issue — for Claude Code resolving-issue, community, for Claude Code, ide skills, markdown, AGENTS.md, ## Type, feature, refactor, ## Step 3 — Implement Follow

v1.0.0

关于此技能

适用场景: Ideal for AI agents that need implementing issue. 本地化技能摘要: Markdown section numbers checker # Implementing Issue Read AGENTS.md for architecture conventions and docs/CONTRIBUTING.md for branch/commit/PR rules. It covers cli, markdown, rust workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

功能特性

Implementing Issue
Read AGENTS.md for architecture conventions and docs/CONTRIBUTING.md for branch/commit/PR rules.
Also read docs/PATTERNS.md, docs/TESTING.md, and docs/VALIDATION.md before implementing.
Step 0 — Read the Issue
Determine the issue number from the user's message or context. Fetch the Issue:

# 核心主题

23prime 23prime
[0]
[0]
更新于: 3/30/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
46
Canonical Locale
en
Detected Body Locale
en

适用场景: Ideal for AI agents that need implementing issue. 本地化技能摘要: Markdown section numbers checker # Implementing Issue Read AGENTS.md for architecture conventions and docs/CONTRIBUTING.md for branch/commit/PR rules. It covers cli, markdown, rust workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

核心价值

推荐说明: resolving-issue helps agents implementing issue. Markdown section numbers checker # Implementing Issue Read AGENTS.md for architecture conventions and docs/CONTRIBUTING.md for branch/commit/PR rules. This AI

适用 Agent 类型

适用场景: Ideal for AI agents that need implementing issue.

赋予的主要能力 · resolving-issue

适用任务: Applying Implementing Issue
适用任务: Applying Read AGENTS.md for architecture conventions and docs/CONTRIBUTING.md for branch/commit/PR rules
适用任务: Applying Also read docs/PATTERNS.md, docs/TESTING.md, and docs/VALIDATION.md before implementing

! 使用限制与门槛

  • 限制说明: Conventional Commits, English only
  • 限制说明: Create a PR following .github/PULL REQUEST TEMPLATE.md. PR body must be in English and include Closes #<N .
  • 限制说明: PR body must be in English and include Closes #<N

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

resolving-issue 是什么?

适用场景: Ideal for AI agents that need implementing issue. 本地化技能摘要: Markdown section numbers checker # Implementing Issue Read AGENTS.md for architecture conventions and docs/CONTRIBUTING.md for branch/commit/PR rules. It covers cli, markdown, rust workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

如何安装 resolving-issue?

运行命令:npx killer-skills add 23prime/mdsn/resolving-issue。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

resolving-issue 适用于哪些场景?

典型场景包括:适用任务: Applying Implementing Issue、适用任务: Applying Read AGENTS.md for architecture conventions and docs/CONTRIBUTING.md for branch/commit/PR rules、适用任务: Applying Also read docs/PATTERNS.md, docs/TESTING.md, and docs/VALIDATION.md before implementing。

resolving-issue 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

resolving-issue 有哪些限制?

限制说明: Conventional Commits, English only;限制说明: Create a PR following .github/PULL REQUEST TEMPLATE.md. PR body must be in English and include Closes #<N .;限制说明: PR body must be in English and include Closes #<N。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add 23prime/mdsn/resolving-issue。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    resolving-issue 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

resolving-issue

安装 resolving-issue,这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Implementing Issue

Read AGENTS.md for architecture conventions and docs/CONTRIBUTING.md for branch/commit/PR rules. Also read docs/PATTERNS.md, docs/TESTING.md, and docs/VALIDATION.md before implementing.

Step 0 — Read the Issue

Determine the issue number from the user's message or context. Fetch the Issue:

bash
1REPO=$(gh repo view --json nameWithOwner --jq .nameWithOwner) 2gh issue view <N> -R "$REPO"

Read the title, body, and comments to understand the task fully before proceeding.

The Issue body follows .github/ISSUE_TEMPLATE/default.md. Extract the Type field from the ## Type section if present.

Step 1 — Clarify task type

Use the Type extracted from the Issue body. If the ## Type section is missing or unclear, determine the type from context:

TypeBranch prefixCommit type
featfeature/feat
fixfeature/fix
refactorfeature/refactor
perffeature/perf
docsfeature/docs
aifeature/ai
chorefeature/chore

Confirm the task and type with the user before proceeding.

Step 2 — Create branch

Include the Issue number in the branch name:

bash
1git switch -c feature/<N>-<short-description>

Step 3 — Implement

Follow AGENTS.md conventions. Consult the docs before writing code:

  • docs/PATTERNS.md — source layout, how to add a rule, clap and output patterns
  • docs/TESTING.md — test structure, helper patterns, DirGuard
  • docs/VALIDATION.md — layer boundaries and what each layer validates

Step 4 — Update docs/SPEC.md if needed

If the implementation changes user-visible behavior (new flags, new error codes, output format changes, new validation rules), update docs/SPEC.md accordingly.

Step 5 — Test against real files

bash
1mise run rs-run -- -- 'examples/*.md'

Step 6 — Auto-fix and check

bash
1mise run fix

If any errors remain that cannot be auto-fixed, resolve them manually, then verify:

bash
1mise run check

Repeat until clean.

Step 7 — CodeRabbit review

Invoke the coderabbit skill. Fix each actionable finding and re-review until clean.

Step 8 — Commit

Follow docs/CONTRIBUTING.md:

  • Conventional Commits, English only
  • No Co-Authored-By: line
bash
1git add <files> 2git commit -m "<type>: <description>"

Step 9 — Push and open PR

bash
1git push -u origin feature/<N>-<short-description>

Create a PR following .github/PULL_REQUEST_TEMPLATE.md. PR body must be in English and include Closes #<N>.

bash
1gh pr create --title "<type>: ..." --body "$(cat <<'EOF' 2## Checklist 3 4- [ ] Target branch is `main` 5- [ ] Status checks are passing 6 7## Summary 8 9## Reason for change 10 11## Changes 12 13## Notes 14 15Closes #<N> 16EOF 17)"

Step 10 — Address PR review comments

After opening the PR, GitHub Copilot and CodeRabbit will post review comments automatically. Check whether reviews have arrived:

bash
1gh pr view <PR_NUMBER> --json reviews | jq '[.reviews[].author.login]'
  • If the array is empty, reviews have not arrived yet. Wait ~2–3 minutes and check again.
  • If still empty after ~5 minutes, automated reviews are likely disabled — skip this step.
  • If copilot-pull-request-reviewer or coderabbitai appear, invoke the implementing-pr-review skill to evaluate and apply valid suggestions.

Step 11 — Reflect learnings into docs/

After the PR is merged, review what was encountered during implementation and PR review. If anything is generalizable — useful for future implementations in this project — add it to the appropriate file under docs/.

Sources to review:

  • Accepted review comments: patterns or pitfalls that reviewers pointed out
  • User corrections: when the user said "no, not that — do X instead", consider whether X is a project-wide rule worth documenting
  • Compilation/check failures: if mise run check failed for a non-obvious reason, note the fix

Choose the target file based on the nature of the learning:

Learning typeTarget file
Code patterns, clap/serde conventions, output formattingdocs/PATTERNS.md
Test structure, helper patterns, working directory gotchasdocs/TESTING.md
Validation boundary decisions, try_new vs newdocs/VALIDATION.md

Criteria for adding:

  • Would a future implementer likely make the same mistake?
  • Is it specific to this codebase (not just "read the Rust docs")?
  • Is it concrete enough to be actionable?

If any of the above apply, open a separate PR for the docs updates:

bash
1git switch main && git pull 2git switch -c docs/patterns-from-issue-<N> 3git add docs/ 4git commit -m "docs: add patterns from issue-<N> implementation" 5git push -u origin docs/patterns-from-issue-<N> 6gh pr create --title "docs: add patterns from issue-<N> implementation" --body "$(cat <<'EOF' 7## Checklist 8 9- [ ] Target branch is `main` 10- [ ] Status checks are passing 11 12## Summary 13 14Add generalizable patterns learned during issue-<N> implementation. 15 16## Notes 17 18Related: #<PR_NUMBER> 19EOF 20)"

If nothing generalizable was found, skip this step.

相关技能

寻找 resolving-issue 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具