Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

smart-context

bởi joe3112

AI & LLMs
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Token-efficient agent behavior — response sizing, context pruning, tool efficiency, and delegation.

Mô tả

Kỹ năng này làm gì

Instructs agents to match response length to question complexity, batch tool calls, and avoid loading files unnecessarily. Covers response sizing rules, context pruning, vision call costs, and delegating bulk work to cheaper sub-agent models.

Instead of applying uniform verbosity to every task, it uses a cost-aware decision tree that trims tokens on simple work while preserving depth where complexity demands it.

Khi nào nên dùng

  • Cutting API costs on high-volume agent pipelines
  • Batching parallel tool calls to reduce round-trips
  • Skipping memory lookups for simple greetings or status checks
  • Delegating bulk file formatting to a lighter model
  • Getting direct answers without preamble or restatements

Quy trình ví dụ

ĐẦU VÀO

User asks: Is the config file present?

AGENT
  1. 1

    Classifies question as yes/no type

  2. 2

    Determines a single targeted check is sufficient — no full file read needed

  3. 3

    Makes one tool call with a specific path lookup

  4. 4

    Skips confirmation read after the check

ĐẦU RA

Yes, config.json exists in the project root.

Cài đặt

clawhub install joe3112/smart-context

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết