laitszkin/develop-new-features
skills/develop-new-features/SKILL.md
從零開始打造新專案。將產品需求轉化為可批准的 spec，再實作為可驗證的交付成果。
$ install --global
skillsauthnpx skillsauth add laitszkin/apollo-toolkit develop-new-featuresInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 29, 2026, 7:41 AM383.9s3 files scanned
SKILL.md
- name:
- develop-new-features
- description:
- 從零開始打造新專案。將產品需求轉化為可批准的 spec，再實作為可驗證的交付成果。
技能目標
將新的產品需求轉化為可批准、可實作、可驗證的交付流程。 避免在需求未定稿前直接撰寫產品程式碼。 確保最終功能、測試與規劃文件彼此一致。
驗收條件
- 產出完全符合用戶需求的 spec，將其精確定義為可實作的工程指導文檔
- 遵照 spec 完成用戶需求的實作
工作流程
1. 建立 spec
分析用戶需求，並使用 spec 技能建立 SPEC.md（純業務規格）。
2. 技術設計
在明確獲取用戶對 SPEC.md 的同意之後，使用 design 技能進行技術方案設計。
design 會進行網路調研（可行性、現有實現、兼容技術棧），然後產出 DESIGN.md、CHECKLIST.md 與 Architecture Diff。
3. 生成實作計畫
使用 plan 技能將 SPEC.md + DESIGN.md + CHECKLIST.md 轉化為 PROMPT.md。
plan 會自動識別單 spec 或 batch spec，進行任務分解，並生成對應的執行計畫與智能體路由策略。
4. 實作 spec
使用 implement 技能讀取 PROMPT.md，嚴格按照計畫執行實作。
使用範例
- "現有repo完全不存在任何的CSV解析、讀取、會出功能。用戶要求替 dashboard 新增 CSV 匯出功能。-> "建立spec並等待用戶批准，再實作匯出流程，並用 property tests 驗證欄位順序、編碼與內容不變量"
- "原repo不存在任何cli功能。用戶要求同時新增 CLI、後端與基礎設施的新能力" → "拆成多份 spec。使用
design為每份 spec 進行技術設計，再使用plan生成 PROMPT.md 定義協同策略與 subagent 路由，最後使用implement按計畫執行。"
Related Skills
laitszkin/create-skill
development
VerifiedTrustedCommunity
Guides the agent through creating a new Agent Skill from scratch. Use when the user wants to build a skill, create a new skill, scaffold a skill directory, or author a SKILL.md. Do NOT use for optimising or rewriting existing skills — use 'optimise-skill' for that. Do NOT use for editing files that are already part of a skill. Do NOT use for creating non-skill content like documentation, scripts, or project files.
5SKILL.mdUpdated Jul 13, 2026
laitszkin/create-skill
development
VerifiedTrustedCommunity
Guides the agent through creating a new Agent Skill from scratch. Use when the user wants to build a skill, create a new skill, scaffold a skill directory, or author a SKILL.md. Do NOT use for optimising or rewriting existing skills — use 'optimise-skill' for that. Do NOT use for editing files that are already part of a skill. Do NOT use for creating non-skill content like documentation, scripts, or project files.
5SKILL.mdUpdated Jul 11, 2026
laitszkin/review-pr
development
VerifiedTrustedCommunity
Review a pull request — interactive PR selection via `gh`, 4-dimension code review (hallucinated code, architecture, performance, test validity), then post severity-graded comments with fix suggestions on the PR. Not for spec-based review — use `review` instead.
5SKILL.mdUpdated Jun 11, 2026
laitszkin/version-release
tools
VerifiedTrustedCommunity
協助完成自動化版本發佈。同步文檔、更新版本號、推送 tag 並建立 GitHub Release。
5SKILL.mdUpdated May 29, 2026