メニュー
Guide and template for wrapping an MCP server as a self-contained Claude Code skill with a Python wrapper script. Use before creating any MCP-backed skill.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/archibate/dotfiles-claude --skill mcpcallコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Create or edit agent-facing/LLM prompts using modern prompt-engineering practices. Use this skill before editing agent-facing docs, rule files, references, skills, memory, or any form of LLM prompt. Also use it before writing LLM tests or evaluations. This is mandatory: NEVER skip this skill before writing agent-facing text; MUST use it before editing a file that will be fed to AI agents.
High-quality C++ OOP coding style (archibate / parallel101 lineage) that overrides sloppy AI-default C++. Use this skill WHENEVER writing, editing, refactoring, or reviewing C++ code (.cpp / .h / .hpp / .cc / .cxx), designing C++ classes, interfaces, APIs, or libraries, or when the user mentions C++ design, OOP, design patterns, dependency injection, RAII, or "clean / modern C++". Apply it even when the user does not explicitly ask for a style: the default way models write C++ leans on free functions, public mutable state, raw new/delete, sentinel return codes, and long loose parameter lists — this skill replaces all of that with abstract-class-or-data-class design, dependency injection, type-rich APIs, value-based error handling, and RAII ownership.
Evidence-driven C++ high-performance computing design, profiling, and optimization across algorithmic time/space complexity, data layout, cache and memory behavior, numerics, SIMD, multicore scheduling, and CPU/accelerator pipelines. Use before designing or changing computation-intensive kernels, high-throughput data structures, performance-critical loops, SIMD/OpenMP/TBB/CUDA code, mixed-precision or sparse representations, or when investigating throughput, latency, scaling, cache, bandwidth, compiler-vectorization, or profiling problems.
SOC 職業分類に基づく
SKILL.md を表示中
| name | mcpcall |
| disable-model-invocation | true |
| description | Guide and template for wrapping an MCP server as a self-contained Claude Code skill with a Python wrapper script. Use before creating any MCP-backed skill. |
Convert any MCP server into a self-contained Claude Code skill with a Python wrapper in scripts/mcpcall.py.
Each MCP skill bundles its own scripts/mcpcall.py with the server URL baked in. No shared dependency, no cross-skill references — fully portable. Uses httpx (respects http_proxy/https_proxy) and MCP Streamable HTTP transport. Dependencies resolved by uv on first run via PEP 723 inline metadata.
The script is executable (chmod +x) with a #!/usr/bin/env -S uv run --script shebang, so it can be called directly without any prefix.
scripts/ subfolderscripts/mcpcall.py:
references/template-noauth.pyreferences/template-auth.pychmod +x scripts/mcpcall.pyscripts/mcpcall.py --listSKILL.md with tool docsEdit SERVER_URL:
SERVER_URL = "https://mcp.example.com/v1"
Edit both constants:
SERVER_URL = "https://mcp.example.com/v1"
ENV_VAR = "MY_API_KEY"
The script reads the API key from the environment variable at runtime — fully stateless.
---
name: my-mcp-skill
description: <what it does>. TRIGGER when <when to activate>.
allowed-tools:
- Bash(*mcpcall.py*:*)
---
name — kebab-case, matches directory name.description — concise capability + explicit TRIGGER clause.allowed-tools — glob pattern auto-approving mcpcall invocations.# My MCP Skill
<one-line description>. No API key required.
## Setup (auth variant only)
Requires `MY_API_KEY` environment variable:
```bash
export MY_API_KEY=<key>
```
## tool_name
<description>
- `param` (required): <what it is>
```bash
scripts/mcpcall.py tool_name param:"value"
```
Key-value — flat parameters (strings, numbers, booleans):
scripts/mcpcall.py search query:"search terms" num:10 verbose:true
Type coercion: true/false → bool, integers → int, floats → float, else string.
JSON — arrays or objects:
scripts/mcpcall.py classify --args '{"texts": ["a", "b"], "labels": ["x", "y"]}'
Both can be combined — kv_args as base, --args JSON merged on top.
my-mcp-skill/
├── SKILL.md # frontmatter + tool docs
└── scripts/
└── mcpcall.py # self-contained PEP 723 script (chmod +x)
| Skill | Template | Server |
|---|---|---|
jina-ai | auth | https://mcp.jina.ai/v1 |
grep-app | noauth | https://mcp.grep.app |
deepwiki | noauth | https://mcp.deepwiki.com/mcp |