Business & Operations

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.

Detect capability gaps and record standardized evolution recommendations.

PowerPoint presentation generation using python-pptx. Create slides from Claude output, data analysis, or structured content. Covers slide templates, shapes, charts, tables, and themed presentations. Use for generating .pptx files programmatically.

Write effective blameless postmortems with root cause analysis, timelines, and action items. Use when conducting incident reviews, writing postmortem documents, or improving incident response processes.

Manus-style file-based planning for complex tasks. Use task_plan.md, findings.md, and progress.md to maintain persistent context. Use for multi-step tasks, research, or work spanning many tool calls.

Autonomous fixed-budget ML experiment loop — setup, iterative hypothesis testing, git-based keep/discard tracking, and indefinite autonomous execution. Implements the karpathy/autoresearch protocol.

Linear project management - issues, projects, cycles, and roadmaps. Use for Linear-related tasks like managing issues, tracking sprints, and organizing projects.

Jira project management and issue tracking integration

Google Cloud CLI operations and resource management

Load and synthesize framework architecture context for reflection and planning tasks.

Flutter and Dart expert including widgets, state management, and platform integration

Customer feedback analysis — sentiment detection, NPS/CSAT frameworks, feature request clustering, support ticket triage, churn signal detection, and feedback-to-roadmap translation

Collaborative document creation via a structured three-stage workflow. Use for writing specs, PRDs, design docs, proposals, RFCs, and any long-form document where quality and clarity matter. Brainstorms 5-20 options per section, builds iteratively, and tests with reader sub-agents.

Structured debug log analysis for Claude Code sessions — auto-discovers most recent log, runs reducer, extracts error patterns, correlates with full log, produces observability report. Fills 5 identified gaps: hook error body capture, agent identity, file path tracking, stall correlation, success visibility.

Atlassian ecosystem integration covering Jira project management, Confluence documentation, Bitbucket source control, and cross-product automation workflows

Benchmark external agent frameworks, auto-detect source type, scan for prompt injection, and convert findings into a concrete TDD upgrade backlog for agent-studio evolution.

Ask the minimum clarifying questions before implementation when requirements are ambiguous or missing crucial details

Cognitive framework for medical diagnostic decision-making addressing systematic biases (commission bias, satisfaction of search, availability error, anchoring error, attribution error). NOT for clinical knowledge acquisition or specific disease protocols.

Implements real-time bidirectional communication between DAG execution engines and visualization dashboards via WebSocket. Covers connection management, typed event protocols, reconnection

Coaches behavioral and values-fit interview preparation with negative framing, deep follow-ups, introspection, and mission alignment. Use for culture-fit rounds, Anthropic behavioral prep,

Breaks natural-language problem descriptions into sub-tasks suitable for DAG nodes. The entry point of the meta-DAG. Identifies phases, dependencies, parallelization opportunities, and vague/pluripotent

Prepare for L6+ coding interviews — in-memory databases, concurrency, state management, iterative follow-ups. Use when practicing real-world system-building problems or preparing communication

Coaches end-to-end ML system design interviews covering inference pipelines, recommendation systems, RAG, feature stores, and monitoring. Use for L6+ design rounds, ML architecture whiteboarding,