**UTILITY SKILL** — Browse the tool names a runtime accepts in a custom agent's `tools:` frontmatter and produce a validated, minimal allowlist; and how to invoke a runtime's tools to get a task done. USE FOR: choosing or tightening an agent's tools list;…
**REFRESH SKILL** — Keep `tools/inventory.yaml` (the workspace cross-runtime tools inventory) accurate and up to date, grounded in the latest GitHub Copilot CLI. USE FOR: refreshing/updating the tools inventory after CLI updates; validating the inventory YAML…
Triage a GitHub issue backlog — classify, prioritize, dedup, and groom issues. Repo-agnostic: each repo supplies its own label taxonomy via a triage.json config. Use when: triaging new issues, clearing the needs-triage queue, grooming the backlog,…
Audit the real-session efficiency of an agent skill's execution episode in a Copilot session against four goals - minimize LLM token usage, minimize execution time, minimize semantic (model-judgment) steps, and maximize deterministic (script/code-executed)…
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…
Drive the waza CLI (microsoft/waza) — the default skill-evaluation tool for this workspace — to check skill readiness for free (waza check, waza tokens), run behavioral eval suites with LLM graders, compare models A/B, measure quality with an LLM judge, and…
Build and customize .NET 10+ 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…
**DISCIPLINE SKILL** — refine a repo's `.github` customization files (agents, skills, instructions, prompts, constitution) after a merge: each lesson single-sourced in one owner file, inherited by reference, never duplicated. USE FOR: codify lessons, add a…