القائمة
Fetch and inspect JavaScript-heavy pages with Playwright in a Daytona browser-capable snapshot.
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.
Hub skill for fleet-rlm: when to use dspy.RLM vs ReAct/CodeAct and which workflow skill to load next.
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.
Process documents and codebases exceeding a single context window using canonical dspy.RLM variable mode in the Daytona REPL.
| name | browser-interaction |
| description | Fetch and inspect JavaScript-heavy pages with Playwright in a Daytona browser-capable snapshot. |
Use when plain fetch / urllib returns empty or incomplete HTML (SPAs, dynamic docs).
| Approach | Use when |
|---|---|
Python urllib / requests | Static HTML, APIs, raw text downloads |
document_text REPL variable | fleet-rlm already fetched the URL into RLM |
| Playwright (browser snapshot) | Client-rendered pages, need visible text or screenshots |
fleet-rlm selects a browser-capable Daytona snapshot when this skill is active.
# After navigation, always print bounded excerpts for the RLM loop.
print(page.title())
print(page.inner_text("body")[:4000])
artifacts/ path for evidence.llm_query on excerpts, not full page dumps.Bundled instructions are seeded to {volume}/skills/system/browser-interaction.md.
Call load_skill("browser-interaction") from the REPL when the volume is mounted.