菜单
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Auto-generated frontmatter
Perform a dual-mode deep reading of any academic paper provided as a PDF attachment or URL. Use this skill when the user requests analysis, close reading, interpretation, or summarization of a scholarly paper. Produce two reports in a single pass: Part A is a rigorous in-depth academic analysis for researchers; Part B distills the core logic and essential value for rapid comprehension.
Use this skill when users need to search academic papers, download research documents, extract citations, or gather scholarly information. Triggers include: requests to "find papers on", "search research about", "download academic articles", "get citations for", or any request involving academic databases like arXiv, PubMed, Semantic Scholar, or Google Scholar. Also use for literature reviews, bibliography generation, and research discovery. Requires OpenClawCLI installation from clawhub.ai.
Ad intelligence & app analytics assistant. Search ad creatives, analyze apps, view rankings, track downloads/revenue, and get market insights. Get your API key at https://www.admapix.com. Triggers: 找素材, 搜广告, 广告素材, 竞品分析, 广告分析, 排行榜, 下载量, 收入分析, 市场分析, 投放分析, App分析, 出海分析, search ads, find creatives, ad spy, ad analysis, app ranking, download data, revenue, market analysis, app intelligence, competitor analysis, ad distribution.
OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
| name | oracle |
| description | Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation. |
| description_zh | 调用第二个 AI 模型交叉审查代码 |
| description_en | Cross-validate code with a second AI model |
| version | 1.0.1 |
Oracle bundles your prompt + selected files into one "one-shot" request so another model can answer with real repo context (API or browser automation). Treat outputs as advisory: verify against the codebase + tests.
Default workflow: --engine browser with GPT in ChatGPT.
--dry-run + --files-report).npx -y @steipete/oracle --helpnpx -y @steipete/oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"npx -y @steipete/oracle --dry-run summary --files-report -p "<task>" --file "src/**"npx -y @steipete/oracle --engine browser -p "<task>" --file "src/**"npx -y @steipete/oracle --render --copy -p "<task>" --file "src/**"--file)--file "src/**", --file src/index.ts--file "!src/**/*.test.ts"node_modules, dist, coverage, .git, etc.--files-report to spot token hogs before spending.~/.oracle/sessions.oracle status --hours 72oracle session <id> --render--slug "<3-5 words>" for readable session IDs.