AI development governance suite that splits work into four documented stages — requirement analysis, structure design, modification governance, and acceptance — so every AI task reads the docs first and stays consistent and traceable. Use this whenever the user plans a new project or feature, clarifies requirements, designs system architecture or a database, proposes any modification or new feature, or wants to verify whether results meet the bar; follow the staged flow and read the matching guide under references. Covers producing an AI Guideline, the four structures (directory/logical/design/data), change records with impact analysis, and acceptance reports with a re-fix loop. Important: as soon as the user proposes a modification or new feature, go through modification governance first rather than editing code directly.
EnglishGoverned autopilot execution layer on top of ai-sdlc: turns a confirmed requirement into an auto-completed change — plan (Global Constraints + per-task interfaces) → per-task TDD build with read-only task review → acceptance → commit → PR → merge — with halt points driven by ai-sdlc risk grading (low = full auto, medium = one confirm gate, high / irreversible = always halts for a human). Use when the user wants a change executed end-to-end automatically under governance, wants TDD / per-task-review discipline, or wants to run the autopilot runner. Requires the ai-sdlc skill (>= v1.17) as the governance layer — run its entry handshake first.
English情報分析方法論(從利益到行動的十步驟框架):問題定義→事實建立→行為者分析→手段篩選→ 歸因校準→決策偏好→連鎖推演→情境預測→觀測指標→缺口聲明,加上可信度評級、預測校準回測 與六個擴展模組(定量/敘事/制度/歷史類比/供應鏈/長期趨勢)。當使用者要做情報分析、地緣政治 研判、行為者意圖分析、情境預測與機率評估、觀測指標追蹤、預測回測(Brier)、輿論敘事分析 時使用。可單一 SKILL 呼叫、跑完整慢情報流程、或快情報精簡流程;預測一律登錄檔案化版本鏈 帳本(docs/intel/predictions/)。繁中版;23…
ChineseIncludes AI Sdlc Autopilot and other workflows.
Supported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
AI Sdlc
AI development governance suite that splits work into four documented stages — requirement analysis, structure design, modification governance, and acceptance — so every AI task reads the docs first and stays consistent and traceable. Use this whenever the user plans a new project or feature, clarifies requirements, designs system architecture or a database, proposes any modification or new feature, or wants to verify whether results meet the bar; follow the staged flow and read the matching guide under references. Covers producing an AI Guideline, the four structures (directory/logical/design/data), change records with impact analysis, and acceptance reports with a re-fix loop. Important: as soon as the user proposes a modification or new feature, go through modification governance first rather than editing code directly.
AI Sdlc Autopilot
Governed autopilot execution layer on top of ai-sdlc: turns a confirmed requirement into an auto-completed change — plan (Global Constraints + per-task interfaces) → per-task TDD build with read-only task review → acceptance → commit → PR → merge — with halt points driven by ai-sdlc risk grading (low = full auto, medium = one confirm gate, high / irreversible = always halts for a human). Use when the user wants a change executed end-to-end automatically under governance, wants TDD / per-task-review discipline, or wants to run the autopilot runner. Requires the ai-sdlc skill (>= v1.17) as the governance layer — run its entry handshake first.
Intel Analysis
情報分析方法論(從利益到行動的十步驟框架):問題定義→事實建立→行為者分析→手段篩選→ 歸因校準→決策偏好→連鎖推演→情境預測→觀測指標→缺口聲明,加上可信度評級、預測校準回測 與六個擴展模組(定量/敘事/制度/歷史類比/供應鏈/長期趨勢)。當使用者要做情報分析、地緣政治 研判、行為者意圖分析、情境預測與機率評估、觀測指標追蹤、預測回測(Brier)、輿論敘事分析 時使用。可單一 SKILL 呼叫、跑完整慢情報流程、或快情報精簡流程;預測一律登錄檔案化版本鏈 帳本(docs/intel/predictions/)。繁中版;23 條核心紀律必遵。
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the AI Sdlc skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.