القائمة
Hub skill for fleet-rlm: when to use dspy.RLM vs ReAct/CodeAct and which workflow skill to load next.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Delegate recursive work to child RLM sandboxes with budget management. Use when decomposing tasks into sub-queries, fanning out batched work, managing LLM call budgets, or building parent-child RLM hierarchies.
Diagnose fleet-rlm runtime failures, API contract drift, sandbox errors, and observability issues. Use when something is broken — Daytona connection failures, websocket mismatches, escalation not triggering, budget exhaustion, or missing traces.
Optimize fleet-rlm DSPy programs and RLM skill bundles using GEPA with MLflow tracking. Use when running optimization loops, designing feedback metrics, building training datasets, or comparing runs.
Design DSPy signatures and compose runtime modules for fleet-rlm tasks. Use when creating input/output field definitions, choosing between built-in signatures, selecting execution modes, or wiring custom modules.
Fetch and inspect JavaScript-heavy pages with Playwright in a Daytona browser-capable snapshot.
Process documents and codebases exceeding a single context window using canonical dspy.RLM variable mode in the Daytona REPL.
| name | rlm |
| description | Hub skill for fleet-rlm: when to use dspy.RLM vs ReAct/CodeAct and which workflow skill to load next. |
Canonical DSPy module: https://dspy.ai/api/modules/RLM/
Module variants overview: https://dspy.ai/diving-deeper/built-in-module-variants/
dspy.RLMUse RLM when context is too large, unevenly relevant, or benefits from programmatic exploration — not a single full-context LM call.
fleet-rlm routes to dspy.RLM when:
execution_mode is rlm / rlm_onlyurl_document_rlm)large_context_rlm, threshold via FLEET_RLM_LARGE_CONTEXT_THRESHOLD)Other turns are classified by the typed RouteTurnSignature router: direct (ChainOfThought), tools (dspy.ReAct loop), or rlm (sandboxed Python).
print() and Python.llm_query, llm_query_batched, SUBMIT(...).sub_rlm, sub_rlm_batched, volume load_skill(name)./home/daytona/memory/ (skills/system/*.md seeded from scaffold).sandbox-executiondelegationdspy-programslong-contextoptimizationdiagnosticsvolume-bootstrapbrowser-interaction