skills

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.

Translate fleet-rlm's shared ReAct plus dspy.RLM runtime into Claude Code workflows. Use when you need a Claude-facing mental model for fleet-rlm, especially for daytona_pilot execution, running the local server surfaces, or planning long-context/runtime work.

Validate fleet-rlm with the current repo test lanes. Use when you need the right confidence level for runtime, websocket, frontend-contract, or Daytona-backed changes.

Converts agent definitions between Markdown (with YAML frontmatter) and TOML formats. Use when transforming agent configurations for different agent systems — MD format for rich tool restrictions, TOML format for Codex-style agents with sandbox modes.

Babysits a GitHub pull request by continuously polling CI checks, review comments, and mergeability state until the PR is ready to merge or closed. Diagnoses failures, retries flaky failures up to 3 times, auto-fixes branch-related issues, and stops only when user help is required. Use when asked to monitor a PR, watch CI, handle review comments, or track failures on an open PR.

Core DSPy framework guidance — signatures, modules, programs, compilation, and testing. Use when creating DSPy signatures, building modules, compiling programs, or learning DSPy fundamentals.

Provides comprehensive guidance for DSPy framework development including signature design, program construction, optimization workflows, and best practices. Use when working with DSPy modules, creating new signatures, optimizing teleprompters, or debugging DSPy code in AgenticFleet.

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.

Evaluates and optimizes agent skills using a DSPy-powered GEPA (Generate/Evaluate/Propose/Apply) loop. Loads scenario YAML files as DSPy datasets, scores outputs with pattern-matching metrics, and optimizes prompts via BootstrapFewShot or MIPROv2 teleprompters. Also generates new scenario YAML files from skill descriptions.

DSPy optimization workflows — teleprompters, metrics, evaluation, and compilation strategies. Use when optimizing DSPy programs with BootstrapFewShot, MIPROv2, or custom metrics.

Creates FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.