FEAT: 添加skills_hub 模块

Author: leeyyi

docs/mkdocs/en/skill.md

@@ -2143,17 +2143,56 @@ The **Dynamic Tool Selection** mechanism has been fully implemented and verified
 - ❌ All tools need to be available simultaneously
 - ❌ Token cost is not a primary concern
 
-## References and Examples
-
-- Background:
-  - Blog:
-    https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills
-  - Open repository: https://github.com/anthropics/skills
-- This repository:
-  - Interactive demo: [examples/skills/run_agent.py](../../../examples/skills/run_agent.py)
-  - Dynamic tool selection full example: [examples/skills_with_dynamic_tools/run_agent.py](../../../examples/skills_with_dynamic_tools/run_agent.py)
-  - Example structure guide: [examples/skills/README.md](../../../examples/skills/README.md)
-  - Example skills:
-    - [examples/skills/skills/python-math/SKILL.md](../../../examples/skills/skills/python-math/SKILL.md)
-    - [examples/skills/skills/file_tools/SKILL.md](../../../examples/skills/skills/file_tools/SKILL.md)
-    - [examples/skills/skills/user_file_ops/SKILL.md](../../../examples/skills/skills/user_file_ops/SKILL.md)
+## Skill Hub - Discovering and Fetching Skills from Remote Sources
+
+**Skill Hub** (`trpc_agent_sdk.skills.hub`) is a set of adapters (`SkillSource`) for discovering and fetching skills from remote sources. It provides three capabilities: searching for available skills from a source (GitHub, ClawHub, skills.sh, and others), inspecting metadata for a specific skill, and downloading the complete file contents for that skill. Users can also implement the `SkillSource` interface to integrate their own skill source.
+
+### `SkillSource` Contract
+
+Every adapter implements the same four-method interface:
+
+```python
+from trpc_agent_sdk.skills.hub import SkillSource, SkillMeta, SkillBundle
+
+class SkillSource(ABC):
+    def source_id(self) -> str: ...
+    def search(self, query: str, limit: int = 10) -> list[SkillMeta]: ...
+    def inspect(self, identifier: str) -> SkillMeta | None: ...
+    def fetch(self, identifier: str) -> SkillBundle | None: ...
+```
+
+- `SkillMeta` - lightweight search/inspect result (`name`, `description`, `source`, `identifier`, plus optional `repo`/`path`/`tags`/`extra`)
+- `SkillBundle` - the downloaded skill (`name`, `files: dict[str, str | bytes]`, `source`, `identifier`, `metadata`)
+
+`fetch()` only returns an in-memory `SkillBundle`. Writing it to disk (including overwrite policy, atomic writes, and concurrency safety) is the **caller's** responsibility, because different harnesses have different installation semantics. For this purpose, the SDK also exports three path validation functions:
+
+```python
+from trpc_agent_sdk.skills.hub import validate_skill_name, validate_category_name, validate_bundle_rel_path
+```
+
+### Built-in Adapters
+
+| Adapter | Source | Identifier format |
+| --- | --- | --- |
+| `GitHubSource` | GitHub repos, via the Contents / Git Trees API | `"owner/repo/path/to/skill-dir"` |
+| `WellKnownSkillSource` | Any domain exposing `/.well-known/skills/index.json` | `well-known:{base_url}/{skill_name}` or a raw HTTPS URL |
+| `HermesIndexSource` | A centralized, pre-crawled skills catalog | Same identifiers as the underlying `GitHubSource` entries |
+| `SkillsShSource` | [skills.sh](https://skills.sh) | `skills-sh/{owner}/{repo}/{skill_path}` |
+| `ClawHubSource` | [ClawHub](https://clawhub.ai) | slug, e.g. `"notion"` |
+| `ClaudeMarketplaceSource` | Claude Code marketplace repos (`.claude-plugin/marketplace.json`) | Resolves to a `GitHubSource` identifier |
+| `LobeHubSource` | LobeHub agent marketplace (converted to synthetic `SKILL.md`) | `lobehub/{agent_id}` |
+
+### Minimal Usage
+
+```python
+from trpc_agent_sdk.skills.hub import GitHubAuth, GitHubSource
+
+source = GitHubSource(GitHubAuth())  # no authentication is required for public repositories
+meta = source.inspect("anthropics/skills/skills/skill-creator")
+bundle = source.fetch("anthropics/skills/skills/skill-creator")
+# bundle.files: {"SKILL.md": "...", "scripts/...": "...", ...}
+```
+
+### Full Example
+
+See the complete Skill Hub usage example: [examples/skills_hub/run_agent.py](../../../examples/skills_hub/run_agent.py)

docs/mkdocs/zh/skill.md

@@ -2141,17 +2141,69 @@ Tools:
 - ❌ 所有工具都需要同时可用
 - ❌ Token 成本不是主要考虑因素
 
-## 参考和示例
-
-- 背景：
-  - 博客：
-    https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills
-  - 开放仓库：https://github.com/anthropics/skills
-- 本仓库：
-  - 交互式演示：[examples/skills/run_agent.py](../../../examples/skills/run_agent.py)
-  - 动态工具选择完整示例：[examples/skills_with_dynamic_tools/run_agent.py](../../../examples/skills_with_dynamic_tools/run_agent.py)
-  - 示例结构说明：[examples/skills/README.md](../../../examples/skills/README.md)
-  - 示例技能：
-    - [examples/skills/skills/python-math/SKILL.md](../../../examples/skills/skills/python-math/SKILL.md)
-    - [examples/skills/skills/file_tools/SKILL.md](../../../examples/skills/skills/file_tools/SKILL.md)
-    - [examples/skills/skills/user_file_ops/SKILL.md](../../../examples/skills/skills/user_file_ops/SKILL.md)
+## Skill Hub —— 从远程来源发现并获取 Skill
+
+**Skill Hub**（`trpc_agent_sdk.skills.hub`）是一组用于从远程来源发现和获取 skill 的适配器（`SkillSource`）。它能做三件事：搜索某个来源（GitHub、ClawHub、skills.sh 等）上有哪些 skill、查看某个 skill 的元信息、下载它的完整文件内容。用户也可以实现SkillSource 接口来对接自己的skill source. 
+
+### `SkillSource` 契约
+
+每个适配器都实现同样的四方法接口：
+
+```python
+from trpc_agent_sdk.skills.hub import SkillSource, SkillMeta, SkillBundle
+
+class SkillSource(ABC):
+    def source_id(self) -> str: ...
+    def search(self, query: str, limit: int = 10) -> list[SkillMeta]: ...
+    def inspect(self, identifier: str) -> SkillMeta | None: ...
+    def fetch(self, identifier: str) -> SkillBundle | None: ...
+```
+
+- `SkillMeta` —— 轻量的 search/inspect 结果（`name`、`description`、`source`、`identifier`，以及可选的 `repo`/`path`/`tags`/`extra`）
+- `SkillBundle` —— 下载到的 skill（`name`、`files: dict[str, str | bytes]`、`source`、`identifier`、`metadata`）
+
+`fetch()` 只会返回内存中的 `SkillBundle`。如果要使用远程 skill，需要先安装到本地目录。SDK 提供了 `SkillSpec` 和 `create_default_skill_repository(remote_skills=..., install_root=...)` 的联动入口：构造 repository 时先把远程 skill 原子写入 `install_root`，再像普通本地 skill 一样扫描索引。SDK 也导出了三个路径校验函数，供自定义安装逻辑复用：
+
+```python
+from trpc_agent_sdk.skills.hub import validate_skill_name, validate_category_name, validate_bundle_rel_path
+```
+
+### 内置适配器
+
+| 适配器 | 来源 | 标识符格式 |
+| --- | --- | --- |
+| `GitHubSource` | GitHub 仓库，如 https://github.com/anthropics/skills | `owner/repo/path/to/skill-dir`，例如 `"anthropics/skills/skills/skill-creator"` |
+| `WellKnownSkillSource` | 暴露 `/.well-known/skills/index.json` 的站点，如 https://www.mintlify.com/docs/.well-known/skills/index.json | HTTPS URL，例如 `"https://example.com/.well-known/skills/plan"` |
+| `HermesIndexSource` | [Hermes Skills Index](https://hermes-agent.nousresearch.com/docs/api/skills-index.json) | `owner/repo/path`，例如 `"anthropics/skills/skills/skill-creator"` |
+| `SkillsShSource` | [skills.sh](https://skills.sh) | `skills-sh/{owner}/{repo}/{skill_path}`，例如 `"skills-sh/owner/repo/plan"` |
+| `ClawHubSource` | [ClawHub](https://clawhub.ai) | `{slug}`，例如 `notion` |
+| `ClaudeMarketplaceSource` | 含 `.claude-plugin/marketplace.json` 的 GitHub marketplace 仓库，如 https://github.com/anthropics/skills | `owner/repo/path`，例如 `"anthropics/skills/plugins/docx"` |
+| `LobeHubSource` | [LobeHub agent marketplace](https://chat-agents.lobehub.com/index.json) | `lobehub/{agent_id}`，例如 `lobehub/writer-bot` |
+
+### 最小用法
+
+```python
+from trpc_agent_sdk.skills import SkillSpec
+from trpc_agent_sdk.skills import SkillToolSet
+from trpc_agent_sdk.skills import create_default_skill_repository
+from trpc_agent_sdk.skills.hub import GitHubAuth, GitHubSource
+
+source = GitHubSource(GitHubAuth())  # 拉取公开仓库无需认证
+meta = source.inspect("anthropics/skills/skills/skill-creator")
+
+repository = create_default_skill_repository(
+    remote_skills=[
+        SkillSpec(
+            source=source,
+            identifier="anthropics/skills/skills/skill-creator",
+            name="skill-creator",
+        ),
+    ],
+    install_root="data/skills/.downloaded",
+)
+skill_toolset = SkillToolSet(repository=repository)
+```
+
+### 完整示例
+
+查看完整的 Skill Hub 使用示例：[examples/skills_hub/run_agent.py](../../../examples/skills_hub/run_agent.py)

examples/skills_hub/.env

@@ -0,0 +1,8 @@
+# Set TRPC_AGENT_API_KEY、TRPC_AGENT_BASE_URL、TRPC_AGENT_MODEL_NAME
+TRPC_AGENT_API_KEY=your-api-key
+TRPC_AGENT_BASE_URL=your-base-url
+TRPC_AGENT_MODEL_NAME=your-model-name
+
+# Optional: a GitHub personal access token (raises the unauthenticated
+# 60 req/hr GitHub API limit to 5,000/hr). Not required to run this demo.
+# GITHUB_TOKEN=

examples/skills_hub/.gitignore

@@ -0,0 +1 @@
+data

examples/skills_hub/README.md

@@ -0,0 +1,51 @@
+# Skill Hub 示例
+
+本示例演示 `trpc_agent_sdk.skills.hub`（Skill Hub）：在启动 `LlmAgent` 之前，通过 `SkillSpec` + `create_default_skill_repository(remote_skills=...)` 从 GitHub 上按需拉取一个技能（Anthropic 官方的 `skill-creator`），写入本地技能目录，再像本地技能一样交给 `SkillToolSet` 使用。
+
+## 什么是 Skill Hub
+
+Skill Hub（`trpc_agent_sdk.skills.hub`）把"从各种来源发现并获取 skill"统一到同一个接口后面。每个来源都是一个 `SkillSource` 适配器，对外提供一致的 `search` / `inspect` / `fetch` 三种能力：
+
+| 适配器 | 来源 |
+| --- | --- |
+| `GitHubSource` | GitHub 仓库目录（本示例使用） |
+| `WellKnownSkillSource` | 站点 `.well-known/skills` |
+| `HermesIndexSource` | Hermes 内置 skill index |
+| `SkillsShSource` | skills.sh |
+| `ClawHubSource` | ClawHub registry |
+| `ClaudeMarketplaceSource` | Claude Skills Marketplace |
+| `LobeHubSource` | LobeHub |
+
+`SkillSource.fetch()` 只返回内存中的 `SkillBundle`（`name` + `files` + `metadata`）。SDK 提供 `SkillSpec` 声明和 `create_default_skill_repository(remote_skills=..., install_root=...)`，在构造 repository 时把远程 skill 写入本地 `install_root`，再交给标准 `FsSkillRepository` 扫描。
+
+## 关键特性
+
+- `GitHubSource(GitHubAuth(token))` 无需认证即可拉取公开仓库（60 次/小时限额，足够本示例使用；设置 `GITHUB_TOKEN` 可提升到 5000 次/小时）
+- 安装逻辑内部复用 SDK 导出的路径校验，避免恶意 `SkillBundle` 写出到目标目录之外
+- 已安装的技能会被跳过，除非 `SkillSpec(replace_if_exists=True)`
+- 拉取完成后，技能通过标准的 `create_default_skill_repository` + `SkillToolSet` 链路对 agent 可见，和本地技能没有区别
+
+## Agent 层级结构说明
+
+- 根节点：`LlmAgent`（`skill_hub_demo_agent`），挂载 `SkillToolSet` 与 `skill_repository`
+- 无子 Agent；单智能体通过 `skill_load` / `skill_list_docs` 等技能工具完成任务
+
+## 关键代码解释
+
+- `agent/hub.py`：
+  - `create_skill_tool_set()`：通过 `SkillSpec` 声明 GitHub skill，并调用 `create_default_skill_repository(remote_skills=..., install_root=...)` 完成安装 + 索引
+- `agent/agent.py`：`create_agent(skills_dir)` 把返回的 `skill_repository` / `skill_tool_set` 绑定到 `LlmAgent`
+- `run_agent.py`：清空 `data/` 目录（保证每次都重新走一遍 Skill Hub 拉取流程），创建 agent，跑一轮 `skill_load` + 总结的对话，并打印实际下载到的文件列表
+
+## 环境与运行
+
+- Python 3.10+；仓库根目录执行 `pip install -e .`
+- 配置 `TRPC_AGENT_API_KEY`、`TRPC_AGENT_BASE_URL`、`TRPC_AGENT_MODEL_NAME`（可用 `.env`）
+- 可选：`GITHUB_TOKEN`，用于提高 GitHub API 限额（本示例只读取公开仓库，不设置也能跑）
+
+```bash
+cd examples/skills_hub
+python3 run_agent.py
+```
+
+运行后会在 `data/skills/.downloaded/hub/skill-creator/` 下看到从 GitHub 拉取的真实文件（`SKILL.md`、`scripts/`、`references/` 等）。

examples/skills_hub/agent/__init__.py

@@ -0,0 +1,5 @@
+# Tencent is pleased to support the open source community by making tRPC-Agent-Python available.
+#
+# Copyright (C) 2026 Tencent. All rights reserved.
+#
+# tRPC-Agent-Python is licensed under Apache-2.0.

examples/skills_hub/agent/agent.py

@@ -0,0 +1,43 @@
+# Tencent is pleased to support the open source community by making tRPC-Agent-Python available.
+#
+# Copyright (C) 2026 Tencent. All rights reserved.
+#
+# tRPC-Agent-Python is licensed under Apache-2.0.
+""" Agent that demonstrates fetching a skill from the Skill Hub before running. """
+
+from pathlib import Path
+
+from trpc_agent_sdk.agents import LlmAgent
+from trpc_agent_sdk.models import LLMModel
+from trpc_agent_sdk.models import OpenAIModel
+
+from .config import get_model_config
+from .hub import create_skill_tool_set
+from .prompts import INSTRUCTION
+
+
+def _create_model() -> LLMModel:
+    """ Create a model"""
+    api_key, url, model_name = get_model_config()
+    model = OpenAIModel(model_name=model_name, api_key=api_key, base_url=url)
+    return model
+
+
+def create_agent(skills_dir: Path) -> LlmAgent:
+    """Fetch a skill from GitHub via the Skill Hub, then build an agent that can use it.
+
+    Args:
+        skills_dir: Local directory to install fetched skills into. Populated
+            by `create_default_skill_repository(remote_skills=...)` before the
+            agent is constructed.
+    """
+    skill_tool_set, skill_repository = create_skill_tool_set(skills_dir)
+
+    return LlmAgent(
+        name="skill_hub_demo_agent",
+        description="An assistant that fetches skills on demand from the Skill Hub.",
+        model=_create_model(),
+        instruction=INSTRUCTION,
+        tools=[skill_tool_set],
+        skill_repository=skill_repository,
+    )

examples/skills_hub/agent/config.py

@@ -0,0 +1,19 @@
+# Tencent is pleased to support the open source community by making tRPC-Agent-Python available.
+#
+# Copyright (C) 2026 Tencent. All rights reserved.
+#
+# tRPC-Agent-Python is licensed under Apache-2.0.
+""" Agent config module"""
+
+import os
+
+
+def get_model_config() -> tuple[str, str, str]:
+    """Get model config from environment variables"""
+    api_key = os.getenv('TRPC_AGENT_API_KEY', '')
+    url = os.getenv('TRPC_AGENT_BASE_URL', '')
+    model_name = os.getenv('TRPC_AGENT_MODEL_NAME', '')
+    if not api_key or not url or not model_name:
+        raise ValueError('''TRPC_AGENT_API_KEY, TRPC_AGENT_BASE_URL,
+                         and TRPC_AGENT_MODEL_NAME must be set in environment variables''')
+    return api_key, url, model_name

examples/skills_hub/agent/hub.py

@@ -0,0 +1,46 @@
+# Tencent is pleased to support the open source community by making tRPC-Agent-Python available.
+#
+# Copyright (C) 2026 Tencent. All rights reserved.
+#
+# tRPC-Agent-Python is licensed under Apache-2.0.
+"""Skill Hub glue: declare a remote skill and build a repository for it."""
+
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+from trpc_agent_sdk.code_executors import create_local_workspace_runtime
+from trpc_agent_sdk.skills import BaseSkillRepository
+from trpc_agent_sdk.skills import SkillToolSet
+from trpc_agent_sdk.skills import create_default_skill_repository
+from trpc_agent_sdk.skills.hub import GitHubAuth
+from trpc_agent_sdk.skills.hub import GitHubSource
+from trpc_agent_sdk.skills.hub import SkillSpec
+
+# `skill-creator` is Anthropic's own skill for building and iterating on
+# skills -- a fitting "meta" skill to fetch through the Skill Hub for a demo.
+GITHUB_SKILL_IDENTIFIER = "anthropics/skills/skills/skill-creator"
+GITHUB_SKILL_NAME = "skill-creator"
+
+
+def create_skill_tool_set(skills_dir: Path) -> tuple[SkillToolSet, BaseSkillRepository]:
+    """Build a `SkillToolSet` backed by a GitHub skill installed through the repository factory."""
+    workspace_runtime = create_local_workspace_runtime()
+    # Unauthenticated requests are capped at 60 req/hr, which is plenty for
+    # this demo. Set GITHUB_TOKEN to raise that limit for repeated runs.
+    source = GitHubSource(GitHubAuth(os.getenv("GITHUB_TOKEN") or None))
+    repository = create_default_skill_repository(
+        remote_skills=[
+            SkillSpec(
+                source=source,
+                identifier=GITHUB_SKILL_IDENTIFIER,
+                name=GITHUB_SKILL_NAME,
+                on_error="raise",
+            ),
+        ],
+        install_root=str(skills_dir / ".downloaded"),
+        workspace_runtime=workspace_runtime,
+    )
+    skill_toolset = SkillToolSet(repository=repository)
+    return skill_toolset, repository

examples/skills_hub/agent/prompts.py

@@ -0,0 +1,19 @@
+# Tencent is pleased to support the open source community by making tRPC-Agent-Python available.
+#
+# Copyright (C) 2026 Tencent. All rights reserved.
+#
+# tRPC-Agent-Python is licensed under Apache-2.0.
+""" prompts for agent"""
+
+INSTRUCTION = """
+Be a concise, helpful assistant that can use Agent Skills.
+
+A skill named "skill-creator" was just fetched on demand from GitHub via the
+Skill Hub (`trpc_agent_sdk.skills.hub`) and installed locally before you were
+started, so it is available like any other local skill.
+
+When asked about a skill, call skill_load to load its documentation, then
+skill_list_docs to see what documentation and files are available. Summarize
+what you find concisely; do not run any of the skill's scripts unless
+explicitly asked to.
+"""