Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kevintsengtw/dotnet-testing-agent-skills --skill skill-creator-advancedgit clone --depth 1 https://github.com/kevintsengtw/dotnet-testing-agent-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/skills/kevintsengtw/dotnet-testing-agent-skills/skill-creator-advanced)<a href="https://agentmods.dev/skills/kevintsengtw/dotnet-testing-agent-skills/skill-creator-advanced"><img src="https://agentmods.dev/badge/skills/kevintsengtw/dotnet-testing-agent-skills/skill-creator-advanced.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.02925 |
| Opus 5 | $0.00024 | $0.01463 |
| Sonnet 5 | $0.00010 | $0.00585 |
| Haiku 4.5 | $0.00005 | $0.00293 |
Grade A, and why
skill-creator-advanced 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator Advanced
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:
- 可操作的流程:從需求、設計、驗證、evals、benchmark、打包到迭代
- 可重用的腳本:初始化、格式檢查、驗證、測試計畫產生、workspace 準備、benchmark 彙整、regression gate 檢查、打包
- 可拆分的參考文件:把長內容放到 references/,維持 progressive disclosure
- 輕量 review viewer:把 with-skill / baseline 結果整理成可檢閱的 HTML
快速開始(你只要做一個新 skill)
- 先從現有對話、repo、範例任務整理 2-3 個 use cases,不夠再補問。
- 為每個 use case 寫 trigger 語句與 done looks like。
- 建立 skill 資料夾:
python scripts/init_skill_advanced.py <skill-name> --path <output-dir>
- 補完新 skill 的
SKILL.md,優先寫對 YAML 的description。 - 做格式與結構檢查:
python scripts/format_check.py <path/to/skill>
python scripts/quick_validate.py <path/to/skill>
- 規劃真實測試案例,必要時產生測試計畫:
python scripts/generate_test_plan.py <path/to/skill> --out references/test_plan.md
- 準備 eval workspace,讓 with-skill / baseline 能沿用固定目錄結構:
python scripts/prepare_eval_workspace.py <path/to/skill>
- 打包成
.skill:
python scripts/package_skill.py <path/to/skill> <output-dir>
- 若要優化 description 的觸發品質,另外準備 trigger eval set,再跑:
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
操作方式
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。
- Phase 0:從上下文萃取需求
- 先看對話歷史、現有檔案、既有流程,再決定要不要追問。
- 用使用者熟悉的術語溝通;如果對方不熟技術名詞,不要把 jargon 當前提。
- 先判斷是否真的值得做成 skill:如果問題一次性、沒有可重用流程,應直接指出不值得包成 skill。
- Phase 1:需求與 use cases
- 先拿到 2-3 個具體 use cases。
- 每個 use case 至少要有:trigger 語句、必要輸入、主要步驟、輸出、done looks like。
- 若使用者只給模糊目標,應主動提出一組合理 use cases 讓對方確認。
- Phase 2:架構與 SKILL.md
- 決定哪些內容要放
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。- 核心流程留在
SKILL.md,細節與變體移到references/。
- Phase 3:撰寫指令
- 優先寫會改變行為的指令,不要解釋模型本來就知道的常識。
- 能直接下命令就直接下命令;只有在理由能降低誤用時才補一句 why。
- 預設遵守 least surprise:讓 skill 的行為符合一般使用者直覺,不要偷偷改目標。
What ships with it
31 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/evals/evals.json 1.8 KB
- assets/evals/regression_gates.json 142 B
- LICENSE.txt 1.0 KB
- references/description-optimization.md 3.9 KB
- references/distribution-playbook.md 1.3 KB
- references/eval-schemas.md 4.8 KB
- references/eval-workflow.md 4.7 KB
- references/lifecycle.md 5.5 KB
- references/multilingual-trigger-strategy.md 1.4 KB
- references/output-patterns.md 1.8 KB
- references/patterns-troubleshooting.md 8.5 KB
- references/regression-gates.md 1.2 KB
- references/skill-boundary-management.md 1.2 KB
- references/skill-roi-model.md 1.3 KB
- references/testing-playbook.md 5.2 KB
- references/workflows.md 819 B
- scripts/aggregate_benchmark.py 9.7 KB runs code
- scripts/check_regression_gates.py 3.8 KB runs code
- scripts/format_check.py 13 KB runs code
- scripts/generate_report.py 11 KB runs code
- scripts/generate_review.py 8.9 KB runs code
- scripts/generate_test_plan.py 8.2 KB runs code
- scripts/improve_description.py 11 KB runs code
- scripts/init_skill_advanced.py 8.7 KB runs code
- scripts/init_skill.py 11 KB runs code
- scripts/package_skill.py 4.2 KB runs code
- scripts/prepare_eval_workspace.py 5.8 KB runs code
- scripts/quick_validate.py 6.7 KB runs code
- scripts/run_eval.py 20 KB runs code
- scripts/run_loop.py 14 KB runs code
- scripts/utils.py 2.6 KB runs code
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.
- 8d ago First seen · 208 lines · 48 tokens per session scan A f8b7dc72095a
skill-creator-advanced is a skill published in the GitHub repository kevintsengtw/dotnet-testing-agent-skills (28 stars, last pushed 23d ago), licensed MIT. It adds 48 tokens to every session and 2,925 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
clean-architecture-dotnet
Use when domain logic leaks into API/Infrastructure, project references violate layer boundaries, or you need to decide between CQS (always), CQRS bus (complex domains), and DDD patterns (invariants and events).
mutation-testing
Use when running mutation testing, killing mutants, verifying test quality, checking mutation score, or analyzing survivors after the test baseline is green.
generate-microcks-openapi-samples
Use when creating OpenAPI mock examples for Microcks, setting up request/response routing with dispatchers, or mapping request fields to mock responses.
outside-in-tdd
Use when writing tests from the outside-in, defining behavior before code, or any feature where tests should start from observable business behavior and let internal design emerge.
extracting-code-structure
Use when listing all methods, functions, or classes in a file, exploring unfamiliar code, getting API overviews, or deciding what to read selectively without loading entire files.
querying-yaml
Use when querying YAML files, filtering or transforming configuration data, or extracting specific fields from large YAML files like docker-compose.yml or GitHub Actions workflows without loading entire files (saves 80-95% context).