qredence
Official@qredence · France
AI Systems
Agent Skills by qredence
Showing 39 vetted skills indexed across 4 GitHub repositories.
Qredenceruntime-cleanup-worker
Consolidate runtime and API surfaces around fleet_rlm while preserving public contracts.
Qredencefrontend-refactor-worker
Coordinate frontend file moves, import updates, and symbol renames with validation.
Qredencebackend-refactor
Rewrite and clean fleet_rlm backend modules with test updates.
Qredenceruntime-validation-repair-worker
Repair validator regressions across CLI, API, and browser surfaces.
Qredenceoptimization
Automate iterative DSPy prompt and RLM skill bundle optimization with GEPA and MLflow tracking.
Qredencedspy-programs
Design DSPy signatures and compose runtime modules for Fleet-RLM task execution.
Qredencedelegation
Delegate recursive tasks to child RLM sandboxes with budget management.
Qredencebrowser-interaction
Fetch and inspect JavaScript-heavy web pages using a Daytona-enabled Playwright browser snapshot.
Qredencevolume-bootstrap
Clarify Daytona sandbox volume layout and durable memory structure.
Qredencediagnostics
Diagnose runtime failures and observability issues in fleet-rlm using Daytona endpoints.
Qredencesandbox-execution
Execute Python code in Daytona sandboxes with durable volume persistence.
Qredencelong-context
Chunk large documents and codebases for Daytona RLM workspace processing.
Qredencedspy-gepa
Automate DSPy GEPA evaluation and optimization of agent skills from YAML datasets.
Qredencedspy-development
Guide DSPy signature, program, and optimization workflow development within AgenticFleet.
Qredenceagent-converter
Converts agent definitions between Markdown and TOML formats, individually or in batches, preserving frontmatter fields and developer instructions.
Qredencedspy-core
Consolidate DSPy guidance for signatures, modules, compilation, and testing.
Qredencefastapi-router-py
Generate FastAPI routers with CRUD operations, authentication dependencies, and typed response models.
Qredencefastapi
Build FastAPI apps with Annotated, dependency injection, and Pydantic models.
Qredencebabysit-pr
Poll GitHub PR CI checks, reviews, and mergeability until merge or close.
Qredencedspy-fleet-rlm
Implement and debug DSPy patterns within the fleet-rlm codebase.
Qredencerlm
Chunk large context files and delegate analysis to subagents for synthesis.
Qredencedspy-optimization
Automate DSPy optimization with teleprompters, metrics, and training data.
Qredencefrontend-ui-integration
Integrate frontend UI workflows with existing backend APIs and design systems.
Qredencedspy-basics
Teach DSPy signatures, modules, and program composition basics.
Frequently Asked Questions About qredence
FAQPage SchemaWhat specific development tasks are enabled by these capabilities?▼
These capabilities enable DSPy signature design, RLM module composition, FastAPI router generation, and persistent memory management. Users can perform iterative prompt optimization, sandbox-based code execution, and structured documentation of project context for complex software systems.
Which personas benefit most from these technical resources?▼
Software engineers, backend developers, and system architects focused on DSPy integration and RLM orchestration benefit most. These resources are designed for technical teams managing complex codebases, requiring structured memory retrieval, sandbox-based runtime validation, and systematic prompt optimization.
What are the primary prerequisites for implementing these memory and sandbox systems?▼
Implementation requires a Daytona-enabled environment for sandbox execution and volume persistence. Users must also have a configured DSPy environment and ChromaDB instance to support the semantic retrieval and memory persistence features provided by the fleet-rlm architecture.