一键导入
context-router
Universal query router for all skills' data. Retrieves only relevant data to save tokens.
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。
菜单
Universal query router for all skills' data. Retrieves only relevant data to save tokens.
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-generate concise, visually stunning README.md with project auto-scanning, badges, and 3 style modes.
Generate unit/integration tests with smart edge case analysis (Zero Token Skeleton + Smart Mode).
Persistent team profiles — carry your coding style, rules, and bug-fix knowledge across projects. 3-tier memory (Hot/Warm/Cold) with TF-IDF search.
Deploy local websites to the internet instantly via Cloudflare Tunnel. Zero hosting, zero domain needed.
Suggests suitable tech stack based on project requirements using local database.
Analyzes market trends, hot features, and user expectations.
| name | context-router |
| description | Universal query router for all skills' data. Retrieves only relevant data to save tokens. |
Instead of reading entire data files (hundreds of lines), agents call the Context Router to retrieve only the specific data they need. This dramatically reduces token consumption.
# Search across ALL skill data files for a keyword:
python .agent/skills/context-router/scripts/context_router.py --query "fintech"
# Search within a specific skill's data:
python .agent/skills/context-router/scripts/context_router.py --skill meta-thinker --query "SCAMPER"
# List all available data sources:
python .agent/skills/context-router/scripts/context_router.py --list
# Get a specific item by ID from a skill:
python .agent/skills/context-router/scripts/context_router.py --skill meta-thinker --source industry_database --id fintech
The router automatically discovers all .json files under .agent/skills/*/data/.
All agents should prefer context_router.py --query "..." over reading raw JSON files.