Refine Approach
mhmzdev/the-holy-quran-app
Sharpen an existing brainstorm or execution plan for The Holy Qur'an app — score it for clarity, completeness, specificity, YAGNI, and scope, then improve it in place.
选择实现策略（垂直切片、水平切片或混合方案）并进行风险评估。在规划功能实现时使用. An agent skill from shinpr/ai-coding-project-boilerplate.
MITAuto-check passed
Install Implementation Approach
$ npx skills add shinpr/ai-coding-project-boilerplate --skill implementation-approach -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate implementation-approach --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills-zh-CN/implementation-approach .claude/skills/implementation-approach && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "implementation-approach" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/implementation-approach into .claude/skills/implementation-approach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementation-approach", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/implementation-approachType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add shinpr/ai-coding-project-boilerplate --skill implementation-approach -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate implementation-approach --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills-zh-CN/implementation-approach .agents/skills/implementation-approach && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "implementation-approach" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/implementation-approach into .agents/skills/implementation-approach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementation-approach", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shinpr/ai-coding-project-boilerplate --skill implementation-approach -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate implementation-approach --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills-zh-CN/implementation-approach .cursor/skills/implementation-approach && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "implementation-approach" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/implementation-approach into .cursor/skills/implementation-approach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementation-approach", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/shinpr/ai-coding-project-boilerplate.git --path .claude/skills-zh-CN/implementation-approach--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add shinpr/ai-coding-project-boilerplate --skill implementation-approach -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate implementation-approach --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills-zh-CN/implementation-approach .gemini/skills/implementation-approach && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "implementation-approach" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/implementation-approach into .gemini/skills/implementation-approach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementation-approach", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install shinpr/ai-coding-project-boilerplate implementation-approachInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add shinpr/ai-coding-project-boilerplate --skill implementation-approach -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills-zh-CN/implementation-approach .github/skills/implementation-approach && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "implementation-approach" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/implementation-approach into .github/skills/implementation-approach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementation-approach", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shinpr/ai-coding-project-boilerplate --skill implementation-approach -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate implementation-approach --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills-zh-CN/implementation-approach .opencode/skills/implementation-approach && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "implementation-approach" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/implementation-approach into .opencode/skills/implementation-approach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implementation-approach", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
implementation-approach- GitHub stars
- 232
- Token cost
- ~1.2k tokens
- SKILL.md length
- 161 words
- Files
- 1
- Skills in repo
- 42
- Repo updated
- First seen
- Licence
- MIT
At a glance
选择实现策略（垂直切片、水平切片或混合方案）并进行风险评估。在规划功能实现时使用. An agent skill from shinpr/ai-coding-project-boilerplate.
- Works in 4 steps: 现有职责基线：通过现有职责，构建能交付当前结果的最简端到端路径。明确的需求和已接受… → 依据核验：用当前需求、已验证的约束、观察到的范围内问题以及有依据支撑的重大风险来检… → 有针对性的比较：针对每一项未满足条件，在增加设计增量之前，先测试复用、从现有数据派… → …
- SKILL.md covers 元认知策略选择流程, 验证等级定义, 集成点定义 and 决策检查清单, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Implementation Approach is an agent skill from shinpr/ai-coding-project-boilerplate. 选择实现策略（垂直切片、水平切片或混合方案）并进行风险评估。在规划功能实现时使用。
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Agentic coding TypeScript boilerplate for Claude Code: sub-agent workflows with built-in quality checks and context engineering. The licence is MIT.
Example prompts
- “/implementation-approach”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 现有职责基线：通过现有职责，构建能交付当前结果的最简端到端路径。明确的需求和已接受的决策具有约束力；建议性的机制仍属候选项。
- 依据核验：用当前需求、已验证的约束、观察到的范围内问题以及有依据支撑的重大风险来检验该路径。只保留那些可能改变已选定设计的未满足条件。
- 有针对性的比较：针对每一项未满足条件，在增加设计增量之前，先测试复用、从现有数据派生、按需计算，或由当前调用方或边界承担职责等方案。按在用户决策、设置、模式、概念、输出、持久状态、实现路径、用户体验、运行时、实现、测试、文档和维护等存在实质差异的维度，比较各可行方案的总体复杂度…
- 削减检验：移除每一项提议的追加内容，并重新检验其所对应的条件。仅当被确认的结果、必要边界或必要证明因此无法满足时，才保留该追加内容。
What it can do on your machine
Read from SKILL.md and the folder at commit 56913a2. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Implementation Approach loads about 1.2k tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 161 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from shinpr/ai-coding-project-boilerplate at commit 56913a2, republished under its MIT licence (© shinpr). 161 words, ~1,157 tokens.
Download SKILL.mdSave it as
.claude/skills/implementation-approach/SKILL.md (or your agent's skills folder).- name
- implementation-approach
- description
- 选择实现策略（垂直切片、水平切片或混合方案）并进行风险评估。在规划功能实现时使用。
实现策略选择框架（元认知方法）
元认知策略选择流程
阶段 1：决策充分的现状分析
核心问题：“现有实现是什么样的？”
分析框架
架构分析: 职责划分、数据流、依赖关系、技术债务
实现质量评估: 代码质量、测试覆盖率、性能、安全性
历史背景理解: 现有形态的合理性、过去决策的有效性、约束变化、需求演变元认知问题清单
- 该实现的真正职责是什么？
- 哪些部分是业务本质，哪些源于技术约束？
- 从代码中看不出哪些依赖关系或隐含前提？
- 当前设计带来了哪些收益和约束？
当另一项现状事实无法改变职责、复用方式、方案有效性、总体复杂度、契约或验证结果时，停止分析。
完成依据：已检查的路径、观察到的架构/数据流事实、已知约束、标注为推断的历史合理性推断，以及可能改变策略选择的未知项。
转换条件：当每一项与策略相关的论断都已被观察到、附带证据明确推断，或记录为未知项时，进入下一阶段。
阶段 2：设计收敛
核心问题：“能交付当前所需结果的最小设计是什么？每一项超出该设计的追加内容，各由什么依据支撑？”
在探索实现策略之前，按顺序完成以下步骤：
- 现有职责基线：通过现有职责，构建能交付当前结果的最简端到端路径。明确的需求和已接受的决策具有约束力；建议性的机制仍属候选项。
- 依据核验：用当前需求、已验证的约束、观察到的范围内问题以及有依据支撑的重大风险来检验该路径。只保留那些可能改变已选定设计的未满足条件。
- 有针对性的比较：针对每一项未满足条件，在增加设计增量之前，先测试复用、从现有数据派生、按需计算，或由当前调用方或边界承担职责等方案。按在用户决策、设置、模式、概念、输出、持久状态、实现路径、用户体验、运行时、实现、测试、文档和维护等存在实质差异的维度，比较各可行方案的总体复杂度。选择满足该条件且总体复杂度最低的方案。
- 削减检验：移除每一项提议的追加内容，并重新检验其所对应的条件。仅当被确认的结果、必要边界或必要证明因此无法满足时，才保留该追加内容。
候选路径和被否决的追加内容仍属于当前分析。需长期保留的输出是已选定设计：完整的选定路径，加上每项设计增量的依据，以及移除该项后会失效的条件。只有已接受的 ADR 可以将备选方案作为决策历史保留。实现时使用同样的收敛检验方式，无需产出单独的产物。
完成依据：一份完整的已选定设计；每项设计增量均说明其当前依据、设计增量更小的方案为何不足，以及削减检验的结果。
转换条件：当每一项支撑性论断都已被观察到、附带证据明确推断，或记录为未知项时，进入下一阶段；将阻塞下一步的未知项转化为继续所需的具体、可验证依据要求。仅当未知项要求变更已确认的成果、目标状态需求或非目标，或需要不可逆操作授权时，才与用户交互。
阶段 3：策略探索与创建
核心问题：“在确定 before -> after 时，应参考哪些实现模式或策略？”
策略发现流程
调研与探索: 优先参考仓库中的既有模式；其次是与已解析依赖版本匹配的官方文档；再次是维护良好的开源实现；文献/博客仅用作补充性备选方案，并标注为非权威来源
创造性思考: 策略组合、基于约束的设计、阶段划分、扩展点设计参考策略模式（鼓励创造性组合）
遗留系统处理策略：
- Strangler 模式：通过分阶段替换实现渐进式迁移
- Facade 模式：通过统一接口隐藏复杂性
- Adapter 模式：与现有系统之间的桥接
新开发策略：
- 功能驱动开发：优先交付用户价值的垂直实现
- 基础驱动开发：优先保证稳定性的自底向上构建
- 风险驱动开发：优先处理风险最大的要素
集成/迁移策略：
- Proxy 模式：透明的功能扩展
- Decorator 模式：对现有功能的分阶段增强
- Bridge 模式：通过抽象获得灵活性
完成依据：当决策并非显而易见时，至少提出两个可行的候选方案，每个候选方案都需对应到其所满足的观察到的约束，以及未解决的约束。
转换条件：当各候选方案都针对同一约束集合具备可比性时，进入下一阶段。
阶段 4：风险评估与控制
核心问题：“将其应用于现有实现会产生哪些风险？哪种控制措施能在保留验证与回滚能力的同时，可衡量地降低发生概率或影响程度？”
风险分析矩阵
技术风险: 系统影响、数据一致性、性能下降、集成复杂度
运营风险: 服务可用性、部署停机、流程变更、回滚流程
项目风险: 进度延迟、学习成本、质量达成度、团队协作风险控制策略
预防措施: 分阶段迁移、并行运行验证、集成/回归测试、监控设置
事件响应: 回滚流程、日志/指标准备、沟通机制、服务持续运行流程完成依据：每项重大风险都具备发生概率/影响程度的依据、一项预防或遏制控制措施，以及一个验证点。
转换条件：当每项高影响风险都已有控制措施或阻塞性上报时，进入下一阶段。
阶段 5：约束兼容性验证
核心问题：“该项目的约束条件是什么？”
约束清单
技术约束: 库兼容性、资源容量、强制性要求、数值目标
时间约束: 截止日期/优先级、依赖关系、里程碑、学习周期
资源约束: 团队/技能、工时/系统、预算、外部合约
业务约束: 上市时机、客户影响、法规合规完成依据：每项约束都已被观察到、推断出，或标记为未知；每一项可能使某候选方案失效的未知项，都需明确指出继续所需的具体、可验证依据。
转换条件：当剩余的未知项不会改变有效候选方案集合，或由用户予以解决时，进入下一阶段。
阶段 6：实现方案决策
在满足所有硬性约束和当前需求的前提下，选择过渡风险最低、验证延迟最小的方案。仅在需求覆盖度、兼容性和风险控制三者相当时，才将生命周期成本和实现工作量用作决胜因素。
垂直切片（功能驱动）
特征：按功能单元跨所有层进行垂直实现 适用条件：功能间依赖度低、输出为用户可用形式、需要跨所有架构层进行变更 验证方式：每个功能完成时交付终端用户价值
水平切片（基础驱动）
特征：按架构层分阶段构建 适用条件：基础系统稳定性重要、多个功能依赖共同基础、逐层验证有效 验证方式：所有基础层完成后进行集成运行验证
混合方案（创造性组合）
特征：根据项目特点灵活组合 适用条件：需求不明确、需要按阶段变更方案、从原型验证过渡到完整实现 验证方式：当该阶段产出终端用户可操作的行为时分配 L1；当该阶段产出可测试的内部行为或契约时分配 L2；仅当该阶段产出构建期结构、尚无可运行行为时才分配 L3
对于混合方案，为每个阶段分配一个明确的 L1/L2/L3 验证等级和可观测的完成结果。
完成依据：一个已选定的方案，其阶段边界、集成点，以及每个阶段的验证结果。
转换条件：当所选方案覆盖全部硬性约束、其风险均已配备控制措施时，进入文档记录阶段。否则返回候选探索（阶段 3）；若阶段 4-5 的结果改变了已选定设计或其依据，则返回设计收敛（阶段 2）。
阶段 7：决策依据文档化
在设计文档或规划交接文档中返回以下结构：
implementationApproachDecision:
observedConstraints: [<约束 + 依据>]
inferredConstraints: [<约束 + 依据与推断>]
unknowns: [<未知项 + 所需依据或决策>]
selectedApproach: <vertical | horizontal | hybrid 方案说明>
selectionRationale: <硬性约束覆盖度、兼容性、风险控制及总体复杂度依据>
addedDesignSurface: [<设计增量 + 当前依据 + 设计增量更小的方案为何不足 + 削减检验结果>]
phaseVerification: [<阶段 + L1/L2/L3 + 可观测的完成依据>]候选方案及否决理由仍属于当前分析，除非已被接受的 ADR 将其作为决策历史予以保留。
完成依据：所选方案及每项设计增量，均可追溯至一项观察到的约束、已接受的推断，或已解决的价值边界决策。
验证等级定义
各任务完成验证的优先级：
- L1：功能运行验证 - 作为终端用户功能可运行（例如：用户可以执行搜索并获得结果）
- L2：测试运行验证 - 已新增测试并通过（例如：类型定义测试）
- L3：构建成功验证 - 无编译错误（例如：接口定义）
优先级：按可验证性重要程度排序，L1 > L2 > L3
集成点定义
根据所选策略定义集成点：
- 基于 Strangler：每个功能在新旧系统之间切换时
- 功能驱动：用户实际可以使用该功能时
- 基础驱动：所有架构层就绪且 E2E 测试通过时
- 混合方案：每个阶段所定义的独立目标达成时
决策检查清单
- 在策略选择之前存在阶段 1 的依据
- 阶段 2 产出一份完整的已选定设计，且每项设计增量都对应到当前依据、设计增量更小的方案为何不足，以及削减检验下失效的条件
- 当所列策略均无法满足全部硬性约束时，候选方案生成包含组合方案
- 每项重大风险都配有控制措施和验证点
- 每项硬性约束都对应到所选方案
- 阶段 7 的输出记录了选择结果、总体复杂度依据及设计增量；备选方案仅出现在已被接受的 ADR 中
当某个已勾选项所需的依据未知时，在该阶段停止，并明确指出继续所需的具体、可验证仓库依据要求。仅当未知项要求变更已确认的成果、目标状态需求或非目标，或需要不可逆操作授权时，才与用户交互。
元认知执行指南
- 善用已知模式：将其作为起点，探索创造性组合
- 依据优先级排序的调研：依次使用仓库依据、与版本匹配的官方文档、维护良好的开源示例，最后是补充性的次要来源
- 运用 5 个为什么：追溯根本原因以把握本质
- 多视角评估：完成阶段 1-5 的依据核验与转换检验
- 策略组合：当单一策略无法满足全部硬性约束时，组合多种策略
- 决策可追溯性：将每个选择理由都映射到阶段 7 输出中的依据
© shinpr, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills-zh-CN/implementation-approach of shinpr/ai-coding-project-boilerplate.
Open the folder on GitHubat commit 56913a2
Compare with similar skills
Implementation Approach next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Implementation Approach this skillshinpr/ai-coding-project-boilerplate | 232 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Refine Approachmhmzdev/the-holy-quran-app | 889 | — | ~600 | Automated safety check: Pass | MIT | |
| Implementation Approachshinpr/claude-code-workflows | 691 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Advise Project ApproachAaravKashyap12/advise-project-approach | 318 | 2 repos | ~9.2k | Automated safety check: Warn | MIT | |
| Approach Evaluationdigipulse-engineering/GAAI-framework | 163 | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| Tool Foundation Sprint Approach Optionsproduct-on-purpose/pm-skills | 715 | — | ~2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Implementation Approach
shinpr/claude-code-workflows
Implementation strategy selection framework. An agent skill from shinpr/claude-code-workflows.
Advise Project Approach
AaravKashyap12/advise-project-approach
Research and advise on the best way to approach a software project, including architecture, tech stack, implementation strategy, pricing/operating-cost tradeoffs, benchmark research, and comparisons…
Approach Evaluation
digipulse-engineering/GAAI-framework
Research industry standards and best practices, identify viable approaches for a given technical or architectural problem, and produce a structured factual comparison against project-specific…
Tool Foundation Sprint Approach Options
product-on-purpose/pm-skills
Day 2 morning move of a Foundation Sprint. An agent skill from product-on-purpose/pm-skills.
Dev Approach
FHIR/fhir-codegen
Explores three competing solution shapes for one request in the roles of three isolated staff-level Engineering Leads, then has a fourth skeptical judge sub-agent select one on the record.
More from shinpr/ai-coding-project-boilerplate
All 42 skills in this repoIntegration E2E Testing
shinpr/ai-coding-project-boilerplate
Selects and designs the smallest integration/E2E test set that proves accepted behavior at an observable boundary.
Skill Optimization
shinpr/ai-coding-project-boilerplate
Evaluates and optimizes skill file quality using 9 content patterns and 10 editing principles.
Frontend Technical Spec
shinpr/ai-coding-project-boilerplate
Defines React environment, component architecture, state/data flow, build verification, and frontend non-functional criteria from repository evidence.
Frontend Typescript Rules
shinpr/ai-coding-project-boilerplate
Applies React/TypeScript type safety, component design, and state management rules.
Implementation Approach
shinpr/ai-coding-project-boilerplate
Selects implementation strategy (vertical slice, horizontal, or hybrid) with risk assessment.
Subagents Orchestration Guide
shinpr/ai-coding-project-boilerplate
Coordinates subagents through scale-based planning, approval, implementation, verification, and escalation flows.
Questions about Implementation Approach
What does Implementation Approach do?
选择实现策略（垂直切片、水平切片或混合方案）并进行风险评估。在规划功能实现时使用. An agent skill from shinpr/ai-coding-project-boilerplate. Implementation Approach is an agent skill from shinpr/ai-coding-project-boilerplate.
How do I install Implementation Approach in Claude Code?
Run `npx skills add shinpr/ai-coding-project-boilerplate --skill implementation-approach -a claude-code`. Or copy the skill folder (.claude/skills-zh-CN/implementation-approach in shinpr/ai-coding-project-boilerplate) into .claude/skills/implementation-approach in your project. Claude Code loads it when a task matches its description.
How do I install Implementation Approach in Codex?
Run `npx skills add shinpr/ai-coding-project-boilerplate --skill implementation-approach -a codex`. Or copy the skill folder (.claude/skills-zh-CN/implementation-approach in shinpr/ai-coding-project-boilerplate) into .agents/skills/implementation-approach in your project. Codex loads it when a task matches its description.
Can I use Implementation Approach in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shinpr/ai-coding-project-boilerplate --skill implementation-approach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/implementation-approach, .gemini/skills/implementation-approach, .github/skills/implementation-approach and .opencode/skills/implementation-approach in your project.
What does Implementation Approach need to run?
SKILL.md names no scripts, command-line tools or credentials: Implementation Approach is instructions for the agent only.
Does Implementation Approach access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Implementation Approach safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Implementation Approach use?
Implementation Approach is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Implementation Approach use?
About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Implementation Approach?
Skills that share tags, products or a category with Implementation Approach: Refine Approach (mhmzdev/the-holy-quran-app, 889 stars), Implementation Approach (shinpr/claude-code-workflows, 691 stars), Advise Project Approach (AaravKashyap12/advise-project-approach, 318 stars) and Approach Evaluation (digipulse-engineering/GAAI-framework, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Implementation Approach?
shinpr (a GitHub user) maintains it in shinpr/ai-coding-project-boilerplate, which has 232 GitHub stars. The repository holds 42 skills in this directory. The repository was last updated on October 4, 2026.
Source: shinpr/ai-coding-project-boilerplate on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.