Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

adaptive-reasoning

bởi enzoricciulli

Productivity & Tasks
4.2kLượt tải do clawskills.sh công bố
6Sao
1Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Automatically assess task complexity and adjust reasoning level.

Mô tả

Kỹ năng này làm gì

Scores every incoming request on complexity dimensions like multi-step logic, ambiguity, and code architecture, then automatically enables extended thinking when the score warrants it. Appends visual indicators (🧠 or 🧠🔥) to signal when reasoning mode is active. Runs silently as a preprocessing step with no user intervention required.

Avoids the manual overhead of toggling reasoning mode by making the decision automatically based on a consistent scoring rubric.

Khi nào nên dùng

  • Debugging a race condition in a distributed system
  • Designing a caching strategy with conflicting constraints
  • Answering a nuanced trade-off question about system architecture
  • Quickly responding to simple lookups without wasting tokens
  • Auto-downgrading after a complex task when follow-up is trivial

Quy trình ví dụ

ĐẦU VÀO

User asks: 'Debug why this distributed system has race conditions under load'

AGENT
  1. 1

    Score the request on complexity dimensions: multi-step logic (+3), code architecture (+2), high stakes (+1) = score 9

  2. 2

    Threshold ≥8 met, activate extended thinking via /reasoning on

  3. 3

    Analyze concurrency patterns, shared state, and timing assumptions in the described system

  4. 4

    Produce a detailed diagnosis with root causes and remediation steps

  5. 5

    Append 🧠🔥 at the end of the response

ĐẦU RA

Detailed race condition analysis with identified root causes and fixes, ending with 🧠🔥

Cài đặt

clawhub install enzoricciulli/adaptive-reasoning

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

Liên kết