.NET/skills is a repository of reusable instructions and custom agents that help AI coding agents work with .NET and C#. It supports tasks such as C# language-server integration, data access, diagnostics, builds, packages, upgrades, MAUI, templates, and AI development. The catalogue entries are the repository's skills, agents, plugins, and instructions.
Borrowing it
Nothing to install: this file belongs to dotnet/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dotnet/skills/main/.github/instructions/eval-quality.instructions.mdgit clone --depth 1 https://github.com/dotnet/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/dotnet/skills/eval-quality)<a href="https://agentmods.dev/instructions/dotnet/skills/eval-quality"><img src="https://agentmods.dev/badge/instructions/dotnet/skills/eval-quality/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/dotnet/skills/eval-quality"><img src="https://agentmods.dev/badge/instructions/dotnet/skills/eval-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00393 | $0.00393 |
| Opus 5.5 | $0.00157 | $0.00157 |
| Sonnet 5.5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
skills eval-quality.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Evaluation quality review
When reviewing these files, apply the evaluation design quality bar in
CONTRIBUTING.md and .agents/skills/create-skill-test/SKILL.md. For a grader,
reference, or fixture change, inspect its owning eval.yaml and apply only the
checks relevant to that artifact.
Leave an inline comment only for a specific, actionable defect. Check that:
- each scenario is necessary for the target; each preference-eligible scenario adds distinct capability, risk, or customer-journey value, while dormancy and no-op guards protect a meaningful routing or preservation invariant;
- prompts are natural developer requests and do not name the skill, reveal the answer, or prescribe its workflow;
- deterministic graders prove the complete required result and, when scope or preservation is part of the request, cover every in-scope file;
- golden evidence passes the deterministic contract and a realistic broken mutation would fail it;
- rewrite scenarios include an already-correct no-op case, and routing boundaries include an uncued dormancy case that proves recognition, restraint, and redirection;
- preference-eligible stimuli have enough task breadth for the expected tie rate, not only the five-stimulus floor;
- fixtures reproduce only the intended condition and are complete and consistent;
- skill evals use the Vally path, agent evals use the native SDK path, and declared time budgets are realistic;
- broad routing or behavior claims have separate evidence across model families;
- a proposed skill-content fix follows failure classification and is supported by the observed evidence.
Do not duplicate deterministic findings already reported by check_eval_quality.py. Do not request
style-only changes. If evidence is missing, state what must be added and why the current eval could
accept an incorrect result or reject a correct one.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 15d ago First seen · 36 lines · 393 tokens per session scan A f5f84a0a8edc
skills eval-quality.instructions.md is an instructions file published in the GitHub repository dotnet/skills (5,696 stars, last pushed today), licensed MIT. It adds 393 tokens to every session, about $0.0016 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-07.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.