harness-engineering-copilot
Harness Engineering for GitHub Copilot
Strategies and patterns for building high-leverage harnesses through Copilot's customization system. A harness is the scaffolding — context layering, constraint enforcement, entropy management, and feedback loops — that makes agents reliably productive.
Related skills:
harness-engineering— generic methodology (tool-agnostic).agent-customization— Copilot file formats, syntax, YAML frontmatter, tool aliases, and configuration rules. Defer all "how do I write this file" questions there.
Sources: OpenAI — Harness Engineering | Martin Fowler — Harness Engineering
Use this skill in two modes:
- Design mode — decide how to layer context, split roles, and add enforcement.
- Audit mode — review an existing Copilot harness with fixed passes, explicit budgets, and consistency checks.
Strategy 1: Context Layering
More from arisng/github-copilot-fc
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
20openspec-sdd
>-
2blazor-blueprint-ui
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.
2beads
Track complex, multi-session work with dependency graphs using beads issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.
1ralph-knowledge-merge-and-promotion
Ralph-v2 knowledge extraction, staging, merge, and promotion reference. Use when running Librarian EXTRACT, STAGE, or PROMOTE modes, applying merge rules, writing extracted frontmatter, or promoting staged knowledge into `.docs`.
1agent-evaluator
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).
1