Borrowing it
Nothing to install: this file belongs to mathruffian-dot/gem-to-skill-kit. 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/mathruffian-dot/gem-to-skill-kit/main/.agents/skills/gem-to-skill/SKILL.mdgit clone --depth 1 https://github.com/mathruffian-dot/gem-to-skill-kitWrote 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/mathruffian-dot/gem-to-skill-kit/gem-to-skill)<a href="https://agentmods.dev/skills/mathruffian-dot/gem-to-skill-kit/gem-to-skill"><img src="https://agentmods.dev/badge/skills/mathruffian-dot/gem-to-skill-kit/gem-to-skill/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/skills/mathruffian-dot/gem-to-skill-kit/gem-to-skill"><img src="https://agentmods.dev/badge/skills/mathruffian-dot/gem-to-skill-kit/gem-to-skill.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 | $0.00089 | $0.01107 |
| Opus 5 | $0.00044 | $0.00553 |
| Sonnet 5 | $0.00018 | $0.00221 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
gem-to-skill 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 9d 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
Gem to Skill
依序完成五個階段。每個階段完成並取得使用者確認後才繼續。
1. 確認 Google Drive
執行：
python .\.agents\skills\gem-to-skill\scripts\detect_environment.py
若未偵測到 Google Drive for desktop：
- 提供官方安裝頁：https://support.google.com/drive/answer/10838124
- 引導使用者完成安裝與登入。
- 要求使用者確認能在檔案總管／Finder 開啟 Google Drive。
- 未完成前停止，不進入定位。
Linux 沒有官方 Drive for desktop；請使用者提供已掛載或同步的本機資料夾路徑。
2. 定位 Gem 資料夾
執行：
python .\.agents\skills\gem-to-skill\scripts\find_gem_folder.py
若回傳多個候選，列出路徑並請使用者選擇。
若找不到：
- 請使用者在 Google Drive、檔案總管或 Finder 搜尋 Gem 資料夾。
- 請使用者複製完整資料夾路徑。
- 用
Test-Path -LiteralPath "<path>"或等效方法驗證存在。
不得對整顆磁碟或整個家目錄做無界限遞迴掃描。
3. 唯讀盤點並列出用途
先顯示將讀取的完整路徑並取得同意，再執行：
python .\.agents\skills\gem-to-skill\scripts\inventory_gems.py --folder "<Gem資料夾>"
將結果整理成：
| 編號 | Gem | 原本用途 | 主要輸入 | 預期輸出 | 知識檔 |
|---|
規則：
- 只摘要用途，不逐字貼出完整系統指令。
- 無法解析時標記「需人工說明」，不要猜測。
- 這一步只盤點，不產生 Skill。
- 不把盤點 JSON 寫進本 repo 或 Git。
若格式無法辨識，讀取 references/gem-format.md。
4. 讓使用者挑選並設計升級
詢問要升級哪些編號。只處理被選取的 Gem。
對每個選定 Gem：
- 說明原本用途與必須保留的規則。
- 從
references/upgrade-options.md挑 2–4 個最有價值的加值選項。 - 顯示預計的輸入、輸出、工具、驗證方式與風險。
- 檢查是否可與其他相似 Gem 合併成一個參數化 Skill。
- 等使用者選擇，不自動接受全部建議。
使用者確認後，依 references/output-spec.md 建立 upgrade spec JSON。Spec 放在使用者指定的私人工作目錄或暫存目錄，不提交 Git。
5. 產生、驗證與儲存 Skill
產物必須位於原始 Gem 資料夾之外。
python .\.agents\skills\gem-to-skill\scripts\build_skill.py --spec "<upgrade-spec.json>" --output-root "<目標.agents\skills>"
python .\.agents\skills\gem-to-skill\scripts\validate_skill.py "<目標.agents\skills\skill-name>"
完成後回報：
- Skill 名稱
- 儲存位置
- 保留的 Gem 能力
- 新增的 Agent 能力
- 驗證結果
- 最小使用範例
預設只建立工作區 Skill。要複製到全域技能目錄、覆蓋同名 Skill 或推送 Git，必須另行取得使用者確認。
安全護欄
- 原始 Gem 資料夾永遠唯讀。
- 不上傳 Gem 指令、知識檔、Drive ID 或私人輸出。
- 不自行安裝 Google Drive、套件或全域 Skill。
- 不把「成功產生檔案」當成「功能驗證通過」；必須執行驗證器。
- 若輸出目錄位於原始 Gem 資料夾內，停止並要求新位置。
What ships with it
9 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.
- agents/openai.yaml 254 B
- references/gem-format.md 685 B
- references/output-spec.md 1.3 KB
- references/upgrade-options.md 1.4 KB
- scripts/build_skill.py 4.9 KB runs code
- scripts/detect_environment.py 2.6 KB runs code
- scripts/find_gem_folder.py 2.2 KB runs code
- scripts/inventory_gems.py 3.6 KB runs code
- scripts/validate_skill.py 2.9 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.
- 9d ago First seen · 108 lines · 89 tokens per session scan A 48941474a3c7
gem-to-skill is a skill published in the GitHub repository mathruffian-dot/gem-to-skill-kit (5 stars, last pushed 6d ago), licensed MIT. It adds 89 tokens to every session and 1,107 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…