spectre-cli-localization
Procedure for localizing Spectre.Console.Cli command and option descriptions in DaxStudio.CommandLine. Use when internationalizing the dscmd command-line tool.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Procedure for localizing Spectre.Console.Cli command and option descriptions in DaxStudio.CommandLine. Use when internationalizing the dscmd command-line tool.
Step-by-step procedure for extracting hardcoded English strings from a DAX Studio XAML view file and replacing them with {x:Static} resource references. Use when localizing or internationalizing XAML files.
Draft `teach:` commit messages for `.github/workflows/improve-add-skill.yml`. Use when preparing or reviewing a correction commit that should trigger the Improve Add Skill workflow from `$add` categorization feedback, including moved plugin entries, removed or excluded plugins, changed `.reason.md` categories, or review-approved rationale that should be generalized into `.codex/skills/add/**`.
Cardano dependencies management, CHaP, source-repository-package, version bumps
Design and implement a new feature or component from a GitHub issue. Use for net-new functionality, not bug fixes.
Enable C# nullable reference types on files that still have `#nullable disable` in the NuGet.Client codebase. Use this skill whenever the user asks to enable nullable, migrate nullable, remove `#nullable disable`, annotate nullability, or fix nullable warnings for any NuGet project or file. Also trigger when the user mentions a GitHub issue about nullable enablement, references PublicAPI.Shipped.txt annotation updates, or says things like "let's do nullable on X" or "enable nullable for these files."
Find open Dependabot PRs for the current GitHub repo, compare each PR head to its base branch, replay only the net dependency changes in a fresh worktree and branch, run npm validation, and optionally commit, push, and open a PR. Use when you want to batch or manually replicate active Dependabot updates.
Add or update UniRL model package support. Use when adding diffusion or autoregressive model pipelines, model config dataclasses, Bundle/Pipeline/Stage/Conditions implementations, LoRA targets, FSDP wrapping hints, RolloutReq/RolloutResp plumbing, or multimodal text/image/video conditioning.
代码规范与完整开发工作流,涵盖 Python、PyTorch/深度学习、Shell 脚本、配置文件。贯穿始终的四条设计原则:易读直观、拒绝过度抽象、单一职责、命名自解释。强制三段式流程:(1)写代码前——在已有项目上开发时必须先了解项目全貌避免重复实现,然后先出 plan(思路+实现步骤)并获得用户批准才能开工;(2)写代码中——遵循命名/类型/docstring/张量操作/异常处理等规范,同时时刻守住四条设计原则;(3)写代码后——必须先补齐对应单元测试并本地跑通,再主动调用 simplify 简化新代码,最后调用 review 做审查。触发条件:用户要求写/生成/重构 Python 或 PyTorch 代码;用户要求在已有项目/代码库上开发;用户创建新模块、脚本或训练循环;用户说"按代码规范来"或引用 /code-standards。
End-to-end recipe for adding a new task under `examples/` — the three pieces that have to line up (`task.yaml`, `seed/`, and `grader/`), what to put in each, the `TaskGrader` API surface, the `coral validate` → smoke-test loop, and the common mistakes (repo_path pointing at the wrong dir, score direction backwards, hidden answer keys leaking into seed/, grader writing to codebase_path which the daemon force-removes, private-vs-public confusion, missing `run()` signature). Use whenever the user wants to add a new CORAL task or port an existing benchmark into CORAL.