adaptive-reasoning
от enzoricciulli
Productivity & TasksКратко
Automatically assess task complexity and adjust reasoning level.
Описание
Что делает этот навык
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.
Когда его использовать
- 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
Пример сценария
User asks: 'Debug why this distributed system has race conditions under load'
- 1
Score the request on complexity dimensions: multi-step logic (+3), code architecture (+2), high stakes (+1) = score 9
- 2
Threshold ≥8 met, activate extended thinking via /reasoning on
- 3
Analyze concurrency patterns, shared state, and timing assumptions in the described system
- 4
Produce a detailed diagnosis with root causes and remediation steps
- 5
Append 🧠🔥 at the end of the response
Detailed race condition analysis with identified root causes and fixes, ending with 🧠🔥
Установка
clawhub install enzoricciulli/adaptive-reasoningВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.