Skip to main content

copilot-agent-patterns

GitHub Copilot custom agent design patterns, best practices, collaboration workflows, and agent orchestration

来源信息

仓库
Hack23/riksdagsmonitor
最近来源活动
2026年4月26日 17:53
检测到的 SKILL.md 语言
英语
星标
12
分支
4

安装方式

默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。

检查来源文件

决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。

正在显示 SKILL.md

SKILL.md
来源说明 · 只读预览
name
copilot-agent-patterns
description
GitHub Copilot custom agent design patterns, best practices, collaboration workflows, and agent orchestration
license
Apache-2.0
# Copilot Agent Patterns Skill ## 🔴 AI FIRST Quality Principle > **Apply the AI FIRST principle: never accept first-pass quality. Minimum 2 iterations. Read all output, improve every section. No shortcuts.** ## Purpose Provides proven patterns for designing, implementing, and orchestrating GitHub Copilot custom agents. ## Agent Design Patterns ### Specialist Agent Pattern - Focused on single domain expertise - Minimal tool set (`view`, `edit`, `create`, `shell`, `search_code`) - Clear scope boundaries (MUST/MUST NOT) - Skills integration references ### Orchestrator Agent Pattern - Broad tool access (`tools: ["*"]`) - Creates and assigns GitHub issues - Delegates to specialist agents - Tracks progress and quality ### YAML Frontmatter Standards ```yaml name: agent-name # Lowercase, hyphen-separated description: Brief expertise # Max 200 characters tools: ["tool1", "tool2"] # Minimal set for non-meta agents ``` ## Collaboration Patterns - **Sequential**: Task agent → creates issues → assigns specialists - **Parallel**: Multiple specialists work on different scopes simultaneously - **Stacked PRs**: Foundation PR → Implementation PR → Polish PR (using base_ref) ## Agent Boundaries - Each agent respects its expertise area - Delegates outside its scope - References skills library constantly - Follows ISMS policies automatically ## Copilot Coding Agent Tools - `assign_copilot_to_issue` — with base_ref and custom_instructions - `create_pull_request_with_copilot` — with base_ref and custom_agent - `get_copilot_job_status` — for tracking progress ## Best Practices - Focus on expertise area - Complete work autonomously when possible - Test changes thoroughly - Document decisions - Only ask when genuinely ambiguous ## Related Policies - [Secure Development Policy](https://github.com/Hack23/ISMS-PUBLIC/blob/main/Secure_Development_Policy.md) --- ## 🔗 Integration with agentic workflows & analysis artifacts This skill is consumed by the 11 agentic news workflows in `.github/workflows/news-*.md`. The authoritative contract lives in [`.github/prompts/README.md`](../../prompts/README.md); this skill supplies domain expertise on top of that contract. - **Analysis product** → [`ai-driven-analysis-guide.md`](../../../analysis/methodologies/ai-driven-analysis-guide.md) + every template in [`analysis/templates/`](../../../analysis/templates/). - **Required before any article**: 9 core artifacts (14 for Tier-C) in `analysis/daily/$ARTICLE_DATE/$SUBFOLDER/`; [`05-analysis-gate.md`](../../prompts/05-analysis-gate.md) is the single blocking gate. - **gh-aw v0.69.3** docs: [abridged](https://github.github.com/gh-aw/llms-small.txt) · [complete](https://github.github.com/gh-aw/llms-full.txt) · [blog series](https://github.github.com/gh-aw/_llms-txt/agentic-workflows.txt).
在 GitHub 查看