github-copilot-fc

Build and customize .NET 8+ Blazor UIs with BlazorBlueprint. Use when choosing between BlazorBlueprint.Components and BlazorBlueprint.Primitives, wiring setup and providers, using ToastService/DialogService/localization, selecting icon packs, applying shadcn-ui-style theming, or copying and adapting BlazorBlueprint blueprints.

Configure and switch between BYOK (Bring Your Own Key) LLM providers for both GitHub Copilot CLI and VS Code Chat. Use when setting up OpenAI, Azure OpenAI, Anthropic, Ollama, Moonshot, OpenCode Go, or other OpenAI-compatible endpoints; creating or switching reusable provider profiles for CLI; configuring chatLanguageModels.json for VS Code; calculating max prompt or output token overrides; configuring wire API and reasoning effort; or troubleshooting COPILOT_PROVIDER_BASE_URL, COPILOT_PROVIDER_TYPE, COPILOT_PROVIDER_API_KEY, COPILOT_MODEL, COPILOT_PROVIDER_WIRE_API, COPILOT_PROVIDER_MAX_PROMPT_TOKENS, COPILOT_PROVIDER_MAX_OUTPUT_TOKENS, COPILOT_OFFLINE, and VS Code language model settings.

Spawn a new isolated Copilot CLI sub-session from a main Copilot CLI or VS Code session. Use when you need to programmatically create, resume, or chain Copilot CLI sessions with explicit control over session ID, custom agent, model, BYOK provider profile, permissions, and working directory. Triggers: "invoke copilot", "spawn copilot", "copilot sub-session", "programmatic copilot cli", "copilot cli session id", "resume copilot session", "chain copilot sessions", "copilot byok profile script", "subagent copilot cli", "task copilot cli".

Apply the Postrboard design language — a refined, airy, code-native aesthetic used across postrboard.com and burkeholland.github.io — when designing or building any website, landing page, UI component, or web app. Use this skill whenever the user asks to design, style, or build a site and wants it to feel polished, modern, and developer-native. Trigger on phrases like "build me a site", "design a landing page", "make it look like postrboard", "use my design language", "create a new site", etc.

Manage GitHub Copilot CLI MCP server configuration, including ~/.copilot/mcp-config.json, COPILOT_HOME or --config-dir, project-level .mcp.json/.github/mcp.json/.vscode/mcp.json, /mcp commands, --additional-mcp-config, and VS Code mcp.json migration.

Create, update, maintain, and evolve GitHub Copilot agent plugins for CLI, VS Code, or both. Use when scaffolding or refining plugin.json, reconciling manifest drift, choosing runtime-specific component fields, wiring plugin components, or governing shared versions across multi-runtime plugins.

Create and draft markdown-based issue documents (bug reports, feature plans, RFCs, ADRs, tasks, retrospectives) in the top-level `.issues/` folder. Use this skill whenever you need to document software issues, feature proposals, architectural decisions, work items, or post-mortems. Includes templates, metadata indexing, and structured YAML frontmatter. Different from issue tracker systems — this is for archival, decision-making, and knowledge base documents.

Slash command to evaluate whether an issue or pull request is still relevant, actionable, and worth keeping open

Programmatically create tldraw whiteboards and visualize them with a self-hosted tldraw instance. Create boards with shapes, text, and connectors, then deploy to a self-hosted server for collaborative editing and gallery management.

Write and run C# programs without a .csproj or solution file using .NET 10+ file-based apps, including multi-file apps with `#:include` (.NET 11+). Use when the user wants to execute C# code quickly — scripts, utilities, prototyping, quick experiments, data processing, teaching examples, or tool authoring. Triggers on phrases like "run this C# file", "C# script", "no project file needed", "single file C# app", "dotnet run file.cs", "quick C# utility", "split script across files", "#:include directive", or any request to write and immediately execute a small self-contained C# program.

Execute Google Cloud Platform operations using the gcloud CLI (and gsutil/bq where applicable). Use when the user wants to: authenticate with GCP, manage GCP resources, deploy applications, configure projects or IAM, view logs, run SQL/BigQuery, or interact with any GCP service from the command line. Triggers on phrases like "gcloud", "Google Cloud CLI", "deploy to GCP", "create a VM", "Cloud Run", "GKE cluster", "Cloud Storage bucket", "set GCP project", "service account", "Cloud Functions", "App Engine deploy", or any request to manage Google Cloud resources via command line.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Session-scoped git commit orchestrator that commits only current-session changes and leaves unrelated dirty worktree edits untouched. Inherits git-atomic-commit for atomic grouping and commit message execution, and git-commit-scope-constitution for scope governance and validation. Use when asked to commit this session only or isolate commits from mixed worktree state.

Compact the current conversation into a handoff document for another agent to pick up.

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.

Multi-iteration parallel subagent orchestrator for Kimi Code CLI

Multi-iteration parallel subagent orchestrator for Kimi Code CLI with streamlined observability, automated documentation, and atomic commits. Use when orchestrating complex work across multiple subagents, enabling parallel execution, or when explicitly requesting fleet mode with '/flow:fleet'. Integrates diataxis documentation and git-atomic-commit workflow.

Manage git worktrees in this repository for parallel implementation, sequential integration, release-branch preparation, and session cleanup. Use when creating a detached worktree first and only then creating its task branch inside that worktree, aligning task branches with shipping policy (`develop` for beta integration, `release/*` or `hotfix/*` for stable lanes), rebasing session branches into `develop`, or removing merged worktrees after validation.

Stress-test plans and designs through a one-question-at-a-time interview. Use when the user asks to 'grill me', pressure-test a repository strategy, module architecture, feature design, OpenSpec namespace spec, or proposed change. Walk each decision branch, surface dependencies, and recommend an answer for every question.

Guidance for using the .NET Aspire CLI and agent integration to create, adopt, run, inspect, debug, update, publish, deploy, and automate Aspire AppHosts. Use when choosing or explaining Aspire commands and workflows such as aspire new, init, restore, run, start, ps, stop, wait, resource, describe, logs, otel, add, update, publish, deploy, do, doctor, docs list, docs search, docs get, or agent; when setting up AI coding agents with aspire agent init or aspire agent mcp; when browsing official Aspire guidance before editing unfamiliar integrations, custom commands, or AppHost APIs; when troubleshooting distributed apps with resource status, logs, traces, endpoints, or MCP docs tools such as list_docs, search_docs, and get_doc; or when running multiple AppHost instances in parallel with --isolated.

**WORKFLOW SKILL** — Create, update, review, fix, or debug Copilot CLI customization files (`copilot-instructions.md`, `AGENTS.md`, `*.instructions.md`, `*.agent.md`, `SKILL.md`, hook JSON, `plugin.json`, and plugin command files). USE FOR: authoring terminal-first customization workflows; troubleshooting why CLI instructions, skills, agents, hooks, or plugins are ignored; configuring `applyTo` and `excludeAgent`; defining CLI tool restrictions; creating custom agents or command packs; packaging reusable CLI customizations. DO NOT USE FOR: general coding questions; non-customization runtime debugging; Copilot in VS Code customization (use `copilot-vscode-agent-customization` instead); MCP server configuration; VS Code prompt files or extension development. INVOKES: file system tools, ask-questions tool, subagents for codebase exploration. FOR SINGLE OPERATIONS: For quick YAML or JSON fixes, or for creating one known file from a clear pattern, edit directly instead of loading the full skill.

Optimize existing AI agent skills with a dual-loop workflow for activation tuning and execution quality. Use when improving a skill after initial creation, diagnosing false triggers or missed triggers, converting subjective output goals into binary assertions, building or refining eval.json test suites, or iteratively refining SKILL.md rules against repeatable checks with a final human review pass.

Specialized for ad-hoc testing Blazor web apps in interactive server render mode with SignalR using playwright-cli. Use when performing quick tests on Blazor components, real-time updates, forms, and UI interactions in server-rendered applications.

Spec-driven development (SDD) using OpenSpec with GitHub Copilot. Use when initializing OpenSpec in a project, writing specifications (requirements + scenarios), proposing changes with delta specs, designing and breaking down tasks, implementing from tasks.md, verifying against specs, syncing/archiving completed changes, managing the openspec/ directory, or adopting specs in existing brownfield codebases. Triggers: "openspec", "spec-driven", "SDD", "write specs", "propose a change", "delta spec", "archive change", "opsx", "/opsx:", "GIVEN/WHEN/THEN scenarios", "requirements specification", "change proposal", "brownfield specs", "verify implementation".

Deterministic custom subagent selection helper. Use when you need a reproducible, auditable decision on which custom subagents to activate for a user query (runs scripts/agent_evaluator.py).

Guidance on configuring VS Code's terminal auto-approve settings for commands with dynamic arguments.

Create and evaluate documentation using the Diátaxis framework. Use when writing, organizing, or auditing documentation to ensure it serves distinct user needs through four systematic categories (Tutorials, How-to Guides, Reference, Explanation). Ideal for diagnosing documentation problems, separating mixed content, and ensuring each piece serves a single, clear purpose.

Query SQL Server databases from the command line using mssql-cli (or sqlcmd). Use when the user provides a SQL Server connection string and needs to execute queries, explore schema, or run batch SQL scripts against the database. Handles connection string parsing (ADO.NET, ODBC, Azure SQL formats) into CLI flags, query execution, and result capture.

Build and refine a constitution defining valid commit scopes for each commit type. Use when maintaining .github/git-scope-constitution.md, discovering new scopes from git history or repo structure, validating scope choices, or conducting weekly scope reviews. Scopes are repo-specific; types are universal.

Unified CLI interface for Google Workspace APIs (Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, etc.) with structured output and multi-service support

Comprehensive research and grounding of answers using official VS Code and GitHub Copilot documentation. Use before conducting web searches for VS Code features, Copilot capabilities, configuration, debugging, extensions, remote development, or any official Microsoft documentation queries.

Classify documentation files into domain-based sub-categories within Diátaxis top-level categories (tutorials, how-to, reference, explanation). Use when organizing wiki files into sub-folders like ralph/, copilot/, sdk/ within a Diátaxis category, determining where a file belongs using the three-rule heuristic (keyword extraction → reuse check → create check → fallback), reclassifying research/ staging files into standard categories, or performing batch wiki reorganization. Supplements the `diataxis` skill which handles top-level classification — this skill adds sub-category depth.

Deploy a static HTML file or static site directory to GitHub Pages. Use when the user wants a durable GitHub-hosted URL for a static page, diagram, report, or generated site, and can provide GitHub authentication via GITHUB_TOKEN or GH_TOKEN.

Strategies, workflows, patterns, and best practices for maximizing harness engineering through GitHub Copilot agent customization. Focuses on how to structure context layering, design multi-agent constraint enforcement, implement checklist-driven audit loops, manage prompt and embed budgets, define artifact ownership, scale customization across repos, and evolve harnesses over time. For Copilot-specific syntax, file formats, and configuration rules, defer to the `agent-customization` skill. Triggers: "copilot harness", "copilot harness strategy", "agent-first copilot", "copilot harness patterns", "copilot context layering", "copilot agent fleet", "copilot entropy management", "copilot harness maturity", "scale copilot harness", "copilot customization strategy", "maximize copilot harness", "copilot harness checklist", "agent prompt budget", "instruction compression", "multi-agent audit", "agent variant", "runtime-specific tools", "custom agent runtime".

Design and implement harnesses for AI-agent-driven software development. A harness is the scaffolding—context engineering, architectural constraints, feedback loops, and entropy management—that enables coding agents to produce reliable, maintainable software at scale. Use when assessing a codebase's agent-readiness, building repository knowledge bases, designing layered architectures with mechanical enforcement, setting up application legibility (observability, browser automation), implementing "garbage collection" agents, or adopting an agent-first development workflow. Triggers: "harness engineering", "agent-first development", "harness", "agent-readiness", "agent legibility", "repository knowledge base", "coding agent scaffolding", "AI-maintainable codebase", "garbage collection agents", "context engineering for agents", "architectural enforcement", "structural tests", "custom linters for agents", "agent autonomy", "harness assessment".

Create and manage high-quality custom instruction files for GitHub Copilot. Use when you need to define new project-specific guidelines, workflows, or coding standards in the instructions/ directory.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Convert between Claude Code command markdown files (*.md) and GitHub Copilot prompt files (*.prompt.md). Use when porting custom prompts or CLI commands between ecosystems.

Analyze git changes, group into atomic commits, generate conventional commit messages with proper type(scope) format. Use when committing changes, grouping staged/unstaged files, or generating commit messages. Enforces universal commit types + repo-specific scopes from .github/git-scope-constitution.md.

Build Blazor-native agent user interfaces using AG-UI protocol with Microsoft Agent Framework (MAF) and ASP.NET Core. Use when implementing the 7 AG-UI protocol features (agentic chat, backend tools, human-in-the-loop approvals, generative UI - async tools, tool-based UI rendering, shared state, and predictive state updates). Covers ASP.NET Core MapAGUI endpoints, Agent Framework integration, Blazor component rendering, SSE streaming architecture, and 2026 UX patterns for agentic interfaces (Dual-Pane Architecture, Observable Plans, HITL governance).