用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/kevintsengtw/dotnet-testing-agent-skills --skill skill-creator-advanced命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
.NET Aspire Testing 整合測試框架完整指南。當需要測試 .NET Aspire 分散式應用程式、設定 AppHost 測試或從 Testcontainers 遷移至 Aspire 測試時使用。涵蓋 DistributedApplicationTestingBuilder、容器生命週期管理、多服務編排、Respawn 配置與時間可測試性設計。 Make sure to use this skill whenever the user mentions .NET Aspire, AppHost testing, DistributedApplicationTestingBuilder, cloud-native testing, or migrating from Testcontainers to Aspire, even if they don't explicitly ask for Aspire testing guidance. Keywords: aspire testing, .NET Aspire, DistributedApplicationTestingBuilder, AppHost testing, 分散式測試, AspireAppFixture, IAsyncLifetime, ContainerLifetime.Session, 雲原生測試, 多服務整合, Aspire.Hosting.Testing, Respawn
ASP.NET Core 整合測試的專門技能。當需要測試 Web API 端點、HTTP 請求/回應、中介軟體、依賴注入時使用。涵蓋 WebApplicationFactory、TestServer、HttpClient 測試、記憶體資料庫配置等。 Make sure to use this skill whenever the user mentions ASP.NET Core integration testing, WebApplicationFactory, TestServer, HTTP endpoint testing, or middleware testing, even if they don't explicitly ask for integration testing guidance. Keywords: integration testing, 整合測試, web api testing, WebApplicationFactory, TestServer, HttpClient testing, controller testing, endpoint testing, 端點測試, RESTful API testing, Microsoft.AspNetCore.Mvc.Testing, CreateClient, ConfigureWebHost, AwesomeAssertions.Web, Be200Ok, Be404NotFound, middleware testing, 中介軟體測試, dependency injection testing
.NET 進階測試技能總覽與引導中心。當使用者詢問「整合測試」、「API 測試」、「容器化測試」、「微服務測試」、「測試框架遷移」、「Testcontainers」、「Aspire 測試」等進階測試需求時觸發。會根據具體需求推薦適合的子技能組合,涵蓋整合測試、Testcontainers、Aspire 測試、框架升級等 8 個進階技能。 Make sure to use this skill whenever the user mentions integration testing, API testing, Testcontainers, .NET Aspire testing, WebApplicationFactory, or xUnit/TUnit migration, even if they don't explicitly ask for advanced testing guidance. Keywords: integration testing, 整合測試, API testing, advanced testing, 進階測試, testcontainers, aspire testing, WebApplicationFactory, TestServer, database test, 資料庫測試, EF Core test, MongoDB test, Redis test, Docker test, 容器測試, microservice test, 微服務測試, .NET Aspire, xUnit upgrade, TUnit, framework migration
正在显示 SKILL.md
| name | skill-creator-advanced |
| description | 當使用者要建立、改版、測試、評估或發布 skill 時使用。涵蓋 description 優化、evals、benchmark、邊界管理與打包流程。 |
| version | 2026.3.9 |
| license | Complete terms in LICENSE.txt |
| metadata | {"author":"Allan Yiin","short-description":"Skill 建立、評估、benchmark 與打包迭代流程","openclaw":{"emoji":"🛠️"}} |
此 skill 的目標是把「做 skill」變成可重複執行的工程流程,而不是一次性的 prompt 雜談。
它同時提供:
python scripts/init_skill_advanced.py <skill-name> --path <output-dir>
SKILL.md,優先寫對 YAML 的 description。python scripts/format_check.py <path/to/skill>
python scripts/quick_validate.py <path/to/skill>
python scripts/generate_test_plan.py <path/to/skill> --out references/test_plan.md
python scripts/prepare_eval_workspace.py <path/to/skill>
.skill:python scripts/package_skill.py <path/to/skill> <output-dir>
python scripts/run_eval.py --eval-set <path/to/trigger-evals.json> --skill-path <path/to/skill> --model <model-id>
python scripts/run_loop.py --eval-set <path/to/trigger-evals.json> --skill-path <path/to/skill> --model <model-id> --apply-best
當使用者要建立或改版 skill 時,請用下列順序推進;可以跳步,但要明確說明原因。
scripts/、references/、assets/。description 必須同時回答兩件事:這個 skill 做什麼、什麼情況下應該觸發。description 要用真實使用者語句,而不是作者自嗨式分類。SKILL.md,細節與變體移到 references/。format_check.py 修掉結構與格式問題。quick_validate.py 做最小合規確認。zh、en、mixed、縮寫/俗稱。assets/evals/evals.json。<skill-name>-workspace/iteration-N/,每個 eval 各自有 with_skill/ 與 baseline 目錄。scripts/aggregate_benchmark.py 彙整 benchmark,再用 scripts/generate_review.py 產生 review viewer。scripts/check_regression_gates.py 檢查是否達到發版門檻。package_skill.py 產生 .skill。完整細節見:
references/lifecycle.mdreferences/testing-playbook.mdreferences/description-optimization.mdreferences/eval-workflow.mdreferences/eval-schemas.mdreferences/multilingual-trigger-strategy.mdreferences/skill-boundary-management.mdreferences/regression-gates.mdreferences/skill-roi-model.mdreferences/distribution-playbook.mdreferences/patterns-troubleshooting.mdSKILL.md 放流程與導航。references/,必要時再讀。scripts/init_skill_advanced.py:建立帶測試/發布欄位的 SKILL.md 骨架。scripts/format_check.py:格式與結構檢查器(含 --fix)。scripts/quick_validate.py:最小合規驗證。scripts/generate_test_plan.py:產生測試計畫模板。scripts/prepare_eval_workspace.py:從 assets/evals/evals.json 建立 iteration workspace。scripts/aggregate_benchmark.py:彙整 with-skill / baseline run 結果,輸出 benchmark.json 與 benchmark.md。scripts/check_regression_gates.py:依 benchmark 與門檻設定判斷是否可發版。scripts/run_eval.py:跑 description trigger eval,輸出 query-level 與 run-level 診斷結果。scripts/improve_description.py:依 trigger eval 失敗型態重寫 description,保留 transcript。scripts/run_loop.py:把 eval 與 description 改寫串成多輪迭代,可選擇直接套用最佳 description。scripts/generate_report.py:產生 description optimization 的 HTML 報告。scripts/utils.py:共用的 SKILL.md / JSON 讀寫輔助。scripts/package_skill.py:驗證後打包成 .skill。assets/evals/evals.json:保存真實測試 prompt、預期輸出與 expectations。assets/evals/regression_gates.json:保存 benchmark 的發版門檻設定。scripts/generate_review.py:把 workspace 結果輸出成 review HTML。<skill-name>-workspace/iteration-N/:保存每輪 with-skill / baseline 的輸出、grading 與 benchmark。交付給使用者時,通常包含:
SKILL.md + scripts/ + references/ + assets/)assets/evals/evals.json<skill-name>-workspace/iteration-N/ 的 benchmark 與 review 輸出.skill 打包檔