Skills for Real Engineers. Straight from my .agents directory.
sn-search-code
Agent skill fromOpenSenseNova/SenseNova-Skills
用于查找代码示例、开源项目、GitHub Issue、技术问答、开发者讨论、HuggingFace 模型/数据集/Space。
How to install sn-search-code
npx skills add OpenSenseNova/SenseNova-Skills# or add only this skill to Claude Code: copy the folder
skills/sn-search-code/
# into
~/.claude/skills/sn-search-code/ (all projects)
.claude/skills/sn-search-code/ (one project)
1# sn-search-code - 开发者搜索23## 凭证配置45API key、token 与 cookie 统一建议写在仓库根目录 `.env`(参考 `.env.example`),并由 runtime 或用户在执行前加载为同名环境变量。脚本仍只从环境变量或显式 CLI 参数读取凭证;不要把真实密钥写入 skill payload、报告、日志或提交。67搜索 GitHub、Stack Overflow、Hacker News、HuggingFace 四个开发者核心平台。所有脚本无需 API 密钥 即可使用,但 GitHub `--type code` 搜索是例外(见下方说明)。89## 可用脚本1011| 脚本 | 平台 | 用途 | API 密钥 |12|------|------|------|---------|13| `github_search.py` | GitHub | 仓库、代码、Issue 搜索 | `code` 类型**必须**;其他类型可选(提高限额) |14| `stackoverflow_search.py` | Stack Overflow | 技术问答搜索 | 无需 |15| `hackernews_search.py` | Hacker News | 技术新闻和讨论 | 无需 |16| `huggingface_search.py` | HuggingFace | 模型、数据集、Space 搜索 | 可选 `HF_TOKEN`(提高限额) |1718## 依赖1920首次运行或脚本提示缺库时,使用本技能的依赖清单安装到当前 Python 环境:2122```bash23python3 -m pip install -r requirements.txt24```2526不要在脚本内部自动安装依赖。若安装失败、网络不可用或包不可用,停止使用对应脚本并改用网页搜索,说明缺少依赖。2728## 参数说明2930### github_search.py3132```bash33python3 scripts/github_search.py <query> [选项]34```3536| 参数 | 说明 | 默认值 |37|------|------|--------|38| `query` | 搜索关键词(必填) | — |39| `--limit`, `-n` | 返回结果数量 | 10 |40| `--type`, `-t` | 搜索类型:`repositories`, `code`, `issues`, `repo`, `issue` | repositories |41| `--token` | GitHub Token(也可通过 `GITHUB_TOKEN` 环境变量设置) | — |4243> **注意:`--type code` 必须提供 token。**44> GitHub API 对代码搜索接口强制要求认证,未提供 token 会返回 401。45> `repositories` 和 `issues` 类型无需 token,但有 token 可提高速率限制(未认证 10 次/分钟 → 认证 30 次/分钟)。4647```bash48python3 scripts/github_search.py "machine learning framework" --type repositories --limit 549…
Excerpt shown under the repository's MIT license.
More skills in SenseNova-Skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
