본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

rlm-controller

skywyze 제작

Web & Frontend Development
866clawskills.sh가 보고한 다운로드 수
2스타
0조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

RLM-style long-context controller that treats inputs as external context, slices/peeks/searches, and spawns.

설명

이 스킬이 하는 일

A policy-driven scaffold for processing inputs too large for a single context window. Stores input as an external context file, slices or searches it in chunks, and spawns batched subcalls to aggregate structured results. Hard limits on recursion depth, slice count, and subcall count are enforced throughout.

Handles inputs that exceed the model context window by splitting work into bounded subcalls rather than truncating or requiring manual chunking.

사용 시점

  • Scanning 50,000-line server logs for error patterns
  • Extracting structured data from large JSONL datasets
  • Analyzing an entire repository across multiple files at once
  • Summarizing dense technical documentation in controlled sections
  • Running keyword searches across multi-file audit trails

예시 워크플로

입력

User asks: Find all authentication errors in this 80,000-line application log

에이전트
  1. 1

    Stores the log file as external context via rlm_ctx.py store

  2. 2

    Generates a keyword-based slice plan with rlm_auto.py targeting auth-related terms

  3. 3

    Creates async batches of slices with rlm_async_plan.py

  4. 4

    Spawns subcalls via sessions_spawn to process each batch

  5. 5

    Aggregates subcall results into a structured error report

출력

Structured list of authentication error occurrences with line numbers and surrounding context

설치

clawhub install skywyze/rlm-controller

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크