rlm-controller
由 skywyze 提供
Web & Frontend Development简介
RLM-style long-context controller that treats inputs as external context, slices/peeks/searches, and spawns.
描述
该技能的功能
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.
何时使用
- 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
示例工作流
User asks: Find all authentication errors in this 80,000-line application log
- 1
Stores the log file as external context via rlm_ctx.py store
- 2
Generates a keyword-based slice plan with rlm_auto.py targeting auth-related terms
- 3
Creates async batches of slices with rlm_async_plan.py
- 4
Spawns subcalls via sessions_spawn to process each batch
- 5
Aggregates subcall results into a structured error report
Structured list of authentication error occurrences with line numbers and surrounding context
安装
clawhub install skywyze/rlm-controller运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。