Перейти к содержимому
TakoAPI
Назад к навыкам

chaos-pivot

от manecharo

AI & LLMs
418Число загрузок по данным clawskills.sh
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Prevents LLMs from sunk-cost pushing broken solutions.

Описание

Что делает этот навык

Addresses a silent failure mode in agentic AI where an LLM keeps pushing a broken approach past the point of reason. When an agent is stuck, looping, or failing repeatedly, it forces a structured stop: name the failed assumption, generate three genuinely different alternatives using inversion, analogy, and brute-force simplicity, then probe each for signal. Loops through a design-thinking cycle until a viable path is found or the problem is escalated with a clear failure diagnosis.

Most agents default to cosmetic retries or parameter tweaks around a broken core assumption; this skill forces genuine strategic divergence by requiring each alternative to violate at least one assumption of the previous approach.

Когда его использовать

  • Agent retrying the same broken API call three times in a row
  • Debugging session where every attempted fix hits the same compiler error
  • Code generation task looping on the same logic structure without progress
  • Automation workflow timing out at the same step across multiple runs
  • Data extraction script returning wrong results despite incremental parameter tweaks

Пример сценария

ВВОД

User asks: fix this script that keeps failing to parse the API response

АГЕНТ
  1. 1

    Recognize the trigger: same approach attempted 3 times with no material improvement

  2. 2

    Write a dead end declaration naming the failed assumption and what it revealed

  3. 3

    Generate 3 alternatives: Inversion (parse locally instead of calling the API), Analogy (treat the response like a stream, not a document, borrowing from log-parsing patterns), Reduction (hardcode a known-good response shape and verify just the extraction logic)

  4. 4

    Probe each alternative for signal without needing to fully complete each one

  5. 5

    Run a third-party audit on the strongest result, checking for scope drift and edge cases before declaring done

ВЫВОД

Working parser using the local-computation approach, with audit confirming it handles the actual response structure

Установка

clawhub install manecharo/chaos-pivot

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки