Agent Skills
› FradSer/dotclaude
› get-context
get-context
GitHub自动解析代码上下文查询，将目标分类为仓库、库或自然语言问题，并调用研究代理通过多种工具获取信息，生成综合摘要。
触发场景
用户询问代码库或技术概念
需要获取项目依赖背景
比较不同技术方案
安装
npx skills add FradSer/dotclaude --skill get-context -g -y
SKILL.md
Frontmatter
{
"name": "get-context",
"description": "Execute this when the user requests code context for a repository, library, or any natural-language code\/technology question using DeepWiki, Context7, Exa, git clone, and\/or web search+fetch.",
"allowed-tools": [
"Task"
],
"argument-hint": "<query | repo-slug | library-name> [more targets...] [--method=deepwiki,context7,exa,clone,web,all]",
"user-invocable": true
}
get-context
Launch a code-context:context-researcher agent that executes the full workflow in an isolated context. The input is arbitrary: a natural-language question, a repo slug, a library name, or several of these at once.
Argument parsing
- Split
$ARGUMENTSinto positional targets and the optional--methodflag.--method=accepts a comma-separated list fromdeepwiki,context7,exa,clone,web,all. Default:all.- Quoted strings are one target:
"compare zustand vs jotai state management"is a single natural-language query. - Multiple positional tokens are multiple targets:
facebook/react zustand= two targets.
- Classify each target:
- GitHub slug (
owner/repo) or git URL → repo target (DeepWiki / clone). - Bare name matching a known package ecosystem (
react,fastapi,next) or with a version hint (react@18) → library target (Context7). - Anything else (a question, a comparison, a concept) → natural-language target (Exa / web search).
- GitHub slug (
- Empty input: read dependency manifests in the current working directory (
package.json,go.mod,pyproject.toml,Cargo.toml) and use detected dependencies as targets.
Prompt template
Pass the parsed targets and method list to the agent verbatim — do not pre-resolve them in the main context.
Code context request.
Targets (classify each as repo / library / natural-language query):
<positional targets, one per line; or "auto-detect from local dependency manifests" if empty>
Methods to use (in priority order; "all" = let agent choose per target):
<comma-separated method list, default "all">
Local context already known: <one line on what the cwd already contains, or "none">
Execute
Launch code-context:context-researcher using the prompt template above. The agent returns a synthesized summary; the main context stays clean regardless of lookup volume.
版本历史
- 6f2a0b2 当前 2026-08-20 10:58
