菜单
fleet-rlm-specific DSPy patterns, debugging, and integration with the qredence/fleet-rlm-dspy codebase. Use when working on fleet-rlm DSPy modules, debugging fleet-rlm DSPy issues, or following fleet-rlm architecture conventions.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Execute batched or parallel RLM work using Daytona sandboxes. Use when running multiple sub-tasks, parameter sweeps, or batch recursive RLM calls in the daytona_pilot runtime.
Debug fleet-rlm runtime issues from Claude Code. Use when diagnosing daytona_pilot failures, API and websocket contract problems, sandbox persistence bugs, or runtime readiness drift.
Execute Python code in Daytona sandboxes with durable volume persistence. Use when running code in a Daytona sandbox, processing data with stateful execution, or persisting results across sessions.
(EXPERIMENTAL) Research implementation for RLM long-context processing using standalone Python scripts. For production use, prefer the rlm skill which uses the fleet-rlm package with Daytona sandboxes. This skill is for experimentation, evaluation, and alternative implementation patterns.
Long-term memory persistence for RLM using Daytona durable volume storage. Use when storing, recalling, listing, or searching data that persists across sandbox sessions in the daytona_pilot runtime.
Run fleet-rlm through its current public entrypoints. Use when you need the right command for the Web UI, API server, MCP server, terminal chat, or Daytona smoke validation from a Claude Code workflow.
| name | dspy-fleet-rlm |
| description | fleet-rlm-specific DSPy patterns, debugging, and integration with the qredence/fleet-rlm-dspy codebase. Use when working on fleet-rlm DSPy modules, debugging fleet-rlm DSPy issues, or following fleet-rlm architecture conventions. |
Patterns, debugging techniques, and integration guidance for using DSPy within the qredence/fleet-rlm-dspy codebase.
This skill requires uv as the Python package manager.
uv venv
source .venv/bin/activate
uv pip install dspy
Rule: Never use raw
pip. Always useuv pipfor installs anduv runfor script execution.
Use this skill when:
fleet-rlm codebaseThe qredence/fleet-rlm-dspy codebase organizes DSPy code as:
src/fleet_rlm/
├── signatures.py # Re-export shim (imports from _prod and _demo)
├── signatures_prod.py # Production signatures (runtime)
├── signatures_demo.py # Demo/example signatures
├── core/
│ ├── interpreter.py # Core reasoning / DSPy program execution
│ ├── llm_tools.py # LLM tool integration
│ └── config.py # DSPy configuration
└── ...
# Production signatures
from fleet_rlm.signatures import AnalyzeLongDocument, CodeChangePlan
# Core interpreter
from fleet_rlm.core.interpreter import ...
# Configuration
from fleet_rlm.core.config import ...
See patterns.md for:
The assets/examples/ directory contains real examples from fleet-rlm:
uv: uv pip for installs, uv run for scriptsfrom fleet_rlm.signatures import ...LOG_JSON=0 for human-readable logs during developmentclear-cache.py after modifying DSPy modules