Skills
Bump package versions across all components
This skill manages coordinated version updates, ensuring all platform packages and plugins are incremented in lockstep. It is ideal for preparing a release or updating dependencies across the entire codebase.
Advanced Retrieval Engineering for Search Systems
This skill enables the construction and optimisation of complex search and indexing pipelines. It specialises in implementing hybrid search, managing vector databases, and refining relevance using advanced reranking techniques.
Git Merge Conflict Resolution Skill
This skill resolves complex git merge conflicts by analyzing both conflicting branches' intents. It ensures code correctness, type safety, and test passing while preferring to combine changes rather than discarding them.
LLM Prompt Engineering and Optimization Skill
This skill focuses on designing, testing, and optimising LLM prompts and system instructions. It covers techniques including chain-of-thought, few-shot prompting, and token budget optimisation for various models.
Comprehensive qa engineering test suite writing
This skill emulates a QA engineer, specializing in writing comprehensive pytest suites to validate system functionality. It ensures coverage across happy paths, identified edge cases, and error modes while managing regression detection.
Full Lifecycle ML Model Development and Deployment
This skill enables the full lifecycle of machine learning, covering model training, fine-tuning (PyTorch/Transformers), and deployment pipelines. It specialises in building robust RAG systems, optimizing inference, and ensuring rigorous eva…
Technical Documentation Engineering Skill
An agentic skill for authoring and maintaining technical documentation, including API references, ADRs, and tutorials. It focuses on producing accurate, code-linked content such as README files and docstrings for developers and operators.
AI Agent Team Manager and Planner
This skill orchestrates complex coding goals by analyzing the codebase, decomposing the objective into actionable tasks, and submitting them to a task server. It manages task parameters including role assignment, priority, scope, and comple…
Build interactive user interfaces with React
This skill enables the development of robust, accessible user interfaces using modern frameworks like React and Next.js. It covers component design, state management, and ensuring high client-side performance using TypeScript.
DevOps Infrastructure and CI/CD Automation
This skill enables the management and maintenance of complex infrastructure, covering container orchestration, cloud deployment, and robust CI/CD pipelines. It includes expertise in monitoring, alerting, and implementing advanced deployment…
Software Architect System Design Skill
This skill enables an agent to perform system decomposition, define API contracts, and document architecture decision records. It focuses on maintaining module boundaries and evaluating technology trade-offs for long-term scalability.
CI failure diagnosis and minimal code fixing
This skill diagnoses CI failures from error reports, making only the smallest, most targeted code changes required to pass tests or linting checks. It strictly adheres to fixing only what is broken, ensuring local verification before commit…
Python Backend API Development Skill
Implements robust server-side logic, APIs, and database operations using Python 3.12+, specializing in FastAPI, SQLAlchemy, and Pydantic. This skill enforces best practices including strict typing, comprehensive testing, and adherence to RE…
Secure zero-knowledge document vault for agents
This skill provides secure, zero-knowledge document management, acting as a persistent vault for sensitive user data. Agents can use it to store, list, and retrieve encrypted files, ensuring privacy for documents like passports or tax retur…
Bernstein Orchestrator Status Monitor
Fetches and displays real-time status from the Bernstein orchestrator, including active agents, task progress, costs, and system alerts.
Ruthless proposal evaluation and scoring
This skill rigorously evaluates technical proposals by assessing feasibility, ROI, and risk against defined criteria. It outputs a structured JSON verdict (APPROVE, REVISE, REJECT) complete with detailed scoring and actionable reasoning.
Analyze agent code quality and reliability metrics
This skill assesses the quality and reliability of agent-generated code by generating a comprehensive dashboard. It reports success rates, lint/test pass rates across various models, and completion time distributions.
Bernstein Cost Analysis and Budget Tracking
Provides detailed cost breakdowns, budget status, and expenditure projections for the Bernstein orchestrator. It enables monitoring of per-model and per-agent costs alongside budget alerts.
Structured multi-stage execution planning for agents
This skill allows developers to decompose complex feature goals into structured, dependency-mapped YAML plans. It facilitates human review and approval of multi-stage workflows before autonomous agents begin execution.
Create tasks for the Bernstein orchestrator
This skill allows users to delegate work, bug fixes, or features to the Bernstein orchestrator. It structures the request by gathering the task title, required role, priority, and scope before queuing the work for an agent.
Review and approve pending tasks in Bernstein
This skill enables agents to review, approve, or reject pending tasks and multi-step plans within the Bernstein system. It provides structured methods for managing task lifecycles, ensuring proper sign-off before execution or merging.
Bernstein Alert Monitoring Skill
Monitor and report active system alerts including failed tasks, stalled agents, and budget warnings to facilitate rapid troubleshooting.
Agent monitoring and lifecycle management
This skill provides comprehensive visibility and control over active Bernstein agents. It allows developers to list running agents, inspect live logs, detect stalled processes, and safely terminate misbehaving agents.
Manage Google Cloud Run Services and Jobs
Provides capabilities to manage Google Cloud Run services, jobs, and domain mappings via the gcloud CLI. It supports deploying, updating, deleting, and managing IAM policies for various Cloud Run resources.