菜单
DEFAULT for all research and web queries. Use for any lookup, research, investigation, or question needing current info. Fast and cost-effective. Only use parallel-deep-research if user explicitly requests 'deep' or 'exhaustive' research.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Ocean326/Agents --skill parallel-web-search命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | parallel-web-search |
| description | DEFAULT for all research and web queries. Use for any lookup, research, investigation, or question needing current info. Fast and cost-effective. Only use parallel-deep-research if user explicitly requests 'deep' or 'exhaustive' research. |
| user-invocable | true |
| argument-hint | <query> |
| context | fork |
| agent | parallel:parallel-subagent |
| compatibility | Requires parallel-cli and internet access. |
| allowed-tools | Bash(parallel-cli:*) |
| metadata | {"author":"parallel"} |
Search the web for: $ARGUMENTS
Choose a short, descriptive filename based on the query (e.g., ai-chip-news, react-vs-vue). Use lowercase with hyphens, no spaces.
parallel-cli search "$ARGUMENTS" -q "<keyword1>" -q "<keyword2>" --json --max-results 10 --excerpt-max-chars-total 27000 -o "/tmp/$FILENAME.json"
The first argument is the objective — a natural language description of what you're looking for. It replaces multiple keyword searches with a single call for broad or complex queries. Add -q flags for specific keyword queries to supplement the objective. The -o flag saves the full results to a JSON file for follow-up questions.
Options if needed:
--after-date YYYY-MM-DD for time-sensitive queries--include-domains domain1.com,domain2.com to limit to specific sourcesDo not set max_output_tokens on the command execution — the output is already bounded by --max-results and --excerpt-max-chars-total. Capping output tokens will truncate the JSON and break parsing.
Parse the JSON from stdout. For each result, extract:
CRITICAL: Every claim must have an inline citation. Use markdown links like Title pulling only from the JSON output. Never invent or guess URLs.
Synthesize a response that:
End with a Sources section listing every URL referenced:
Sources:
- [Source Title](https://example.com/article) (Feb 2026)
- [Another Source](https://example.com/other) (Jan 2026)
This Sources section is mandatory. Do not omit it.
After the Sources section, mention the output file path () so the user knows it's available for follow-up questions.
/tmp/$FILENAME.jsonIf parallel-cli is not found, install and authenticate:
curl -fsSL https://parallel.ai/install.sh | bash
If unable to install that way, install via pipx instead:
pipx install "parallel-web-tools[cli]"
pipx ensurepath
Then authenticate:
parallel-cli login
Or set an API key: export PARALLEL_API_KEY="your-key"
Design single-agent or multi-agent workflows, orchestration loops, handoffs, evaluator-optimizer cycles, and wake-up or re-entry patterns for agentic systems. Use when Codex needs to decide whether work should stay as a prompt, instruction, skill, single agent, or multi-agent topology, and when turning that choice into concrete prompt contracts, prompt-refinement gates, externalized state schemas, stop rules, approval gates, and close-loop evaluation plans.
面向架构类工作的总入口路由器。用于在广义架构总控、ADR/治理、现有代码库重构、规格驱动设计、DDD/clean architecture、agent systems architecture 与架构文档评审之间选择最合适的入口；当用户知道“这是架构问题”但不知道具体 lane 时优先使用。
Senior architect entrypoint that routes software architecture, 系统设计, 技术方案, 架构评审, ADR, 代码库重构, requirements-driven design, DDD/clean architecture, agent system design, and architecture-document review to the right Architecture Workbench skill. Use when Codex should think like an architect first, choose the best architecture lane, and return trade-offs, risks, migration steps, and next decisions instead of jumping straight into implementation.
基于 SOC 职业分类