Context

Project processkit security policy Artifacts into runtime policy files for Agent-IDS and Tetragon-style enforcement. Use when an agent-ids-rule or image-provenance-policy Artifact must become an executable security configuration.

Mobile app UX — touch targets, navigation, platform conventions, accessibility. Use when designing mobile interfaces, reviewing mobile UX, adapting web designs for mobile, or reconciling iOS and Android conventions.

Generates clear, structured status updates for stakeholders — from project context, backlog state, or a brief description of recent work. Use when asked to write a status update, weekly report, progress summary, or team briefing about a project or initiative.

Dockerfile best practices — layer optimization, caching, security, image size. Use when writing, reviewing, or optimizing Dockerfiles, investigating bloated images, or fixing cache-busting build orders.

Manage Constraint entities — rules and limits the project must respect (budget, latency SLO, team size, compliance). Use when recording a rule, limit, or boundary that affects decisions — budget ceiling, latency SLO, regulatory requirement, team bandwidth.

Production incident handling — triage, communicate, mitigate, fix, postmortem. Use when production is broken, users are affected, an outage is in progress, or a deploy has caused regressions and the priority is restoring service.

Manage Discussion entities — structured, multi-turn conversations that explore questions and produce decisions. Use when a question or design choice needs multi-turn exploration before a decision is reached — RFCs, design debates, trade-off analyses.

Kubernetes cluster management — resources, networking, storage, Helm, troubleshooting. Use when writing Kubernetes manifests, running kubectl or helm, debugging pods and services, or configuring ingress, DNS, storage, or network policies.

Investigates a question systematically before answering — verifying claims through sources, distinguishing known facts from inferences, and calibrating expressed confidence to actual certainty. Use when asked to research a topic, verify a claim, evaluate a technology, or answer a question where accuracy matters more than speed.

Creating Word documents programmatically with python-docx — headings, styles, tables, lists, images, and sections. Use when generating DOCX reports, proposals, contracts, letters, or any structured Word document from data or templates.

Reconcile a processkit project’s migrations, health findings, and repository collaboration queue. Use when resolving all migrations, pk-doctor findings, GitHub issues, pull requests, or release blockers.

Creating PowerPoint presentations programmatically with python-pptx — slides, layouts, text boxes, charts, tables, and images. Use when generating slide decks, briefings, reports, or presentations from data or templates.

Legacy/migration guidance for v1 StateMachine entities. In v2, lifecycle rules are implementation contracts owned by MCP servers, not first-class records to create during normal project work.

Git workflow conventions — branch naming, conventional commits, PR descriptions, and merge strategy. Use when deciding on a branch name, writing a commit message or PR description, or choosing a merge strategy.

Conventions and helpers for lightweight relationships between entities expressed as frontmatter references (not first-class Binding entities). Use when linking two entities with a simple, unscoped, untemporal relationship — 'this work item blocks that one', 'this decision relates to that work item'. For scoped/temporal relationships, use binding-management instead.

Load testing methodology — test types, scenario design, capacity planning, CI integration. Use when planning or running a load test, choosing a load testing tool, designing scenarios, analyzing results, setting up performance testing in CI, or estimating capacity from test data.

Generates Excalidraw diagrams programmatically as hand-drawn-style JSON. Use when creating architecture diagrams, flowcharts, or hand-drawn-style visuals for documentation, or when converting existing diagrams to editable Excalidraw JSON.

SQL query patterns, schema design, and optimization — joins, CTEs, window functions, indexing, and anti-patterns. Use when writing or optimizing SQL queries, designing or reviewing a relational schema, reading EXPLAIN plans, choosing indexes, or implementing pagination, deduplication, or analytical queries.

Creates SVG logos with scalable geometry, color theory, and variant generation. Use when designing logos, icons, or brand marks, generating favicons or social avatars, or reviewing a logo for scalability, color, or variant coverage.

Test-driven development workflow — red-green-refactor, naming, doubles, when to apply. Use when writing code with TDD, practicing the red-green-refactor cycle, deciding between TDD and test-after, naming tests, choosing test doubles, or exploring property-based and mutation testing.

CI/CD pipeline setup — GitHub Actions, testing, linting, deployment. Use when setting up CI from scratch, adding GitHub Actions, automating tests, wiring up deployment, or improving an existing build pipeline.

ML pipeline design — data versioning, experiment tracking, deployment patterns, drift monitoring. Use when building an ML pipeline from data to deployment, setting up MLOps tooling (DVC, MLflow, model registry), choosing deployment patterns (shadow, canary, A/B), or designing monitoring for drift and degradation.

Write a Product Requirements Document structured with problem statement, goals, user stories, scope, and success metrics.

Data quality framework — completeness, accuracy, consistency, validation, and contracts. Use when implementing data validation, setting up quality checks for a pipeline, defining data contracts between teams, or investigating data anomalies.

Generates a structured onboarding guide for a new agent or human joining a project — covering codebase orientation, process context, first tasks, and key contacts. Use when asked to onboard someone new, write a getting-started guide, or create a "first week" plan for a project.

Data analysis workflow from import through modeling and communication. Use when analyzing a dataset, exploring data, building a statistical model, selecting features, or communicating findings to stakeholders.

Tailwind CSS v4 — utility-first styling, responsive design, dark mode, and component extraction. Use when building or reviewing Tailwind-based UIs, setting up Tailwind v4, or designing responsive or dark-mode styling.

Structures a systematic legal and compliance review of contracts, policies, or technical decisions — identifying key clauses, risks, and questions for counsel. Use when asked to review a contract, check compliance implications, flag legal risks in a technical design, or prepare for a legal consultation. Always surfaces work for qualified counsel; never replaces legal advice.

Data pipeline patterns — ETL/ELT, batch vs streaming, idempotency, orchestration. Use when designing a data pipeline, choosing between batch and streaming, implementing ingestion or transformation, setting up orchestration, or debugging pipeline failures.

Manage Metric entities — quantified observations the project cares about (velocity, error rates, lead time, NPS). Use when defining or recording a quantitative measure — team velocity, error rate, lead time, customer satisfaction score.

DataFrame operations with pandas and polars — groupby, joins, reshaping, performance. Use when manipulating tabular data, choosing between pandas and polars, optimizing DataFrame code, or translating between the two libraries.

Application metrics with RED/USE methods, Prometheus types, dashboards, and SLO alerting. Use when instrumenting an application with metrics, designing dashboards, setting up alerting, choosing between metric types, defining SLIs/SLOs, or applying RED, USE, or the four golden signals.

DNS records, IP addressing, subnetting, common protocols, and diagnostic tools. Use when configuring DNS records, debugging resolution or connectivity, planning subnets, analyzing HTTPS/TLS errors, or diagnosing latency and routing issues.

Blameless postmortem writing — timeline, root cause analysis, corrective actions. Use when writing an incident postmortem, conducting a post-incident review, building a postmortem template, or coaching a team toward blameless culture.

Generates and maintains CHANGELOG.md files following Keep a Changelog conventions — from git history, commit messages, or a description of changes. Use when asked to write a changelog, update release notes, or document what changed in a version.

LaTeX authoring with LuaLaTeX — document classes, math, TikZ, BibLaTeX. Use when writing or editing LaTeX documents, setting up preambles, typesetting math, building TikZ diagrams, or managing bibliographies.

Systematic debugging — reproduce, read the error, isolate, hypothesize, fix, verify, document. Use when tracking down a bug, unexpected behavior, or test failure — including phrases like "this doesn't work", "why is this failing", or "help me debug".

Authentication and authorization patterns — OAuth2, JWT, sessions, RBAC/ABAC. Use when implementing login flows, securing APIs, managing tokens, designing permission systems, or reviewing auth code.

Writing effective project documentation — READMEs, API doc comments, and inline comments that explain why. Use when writing or improving documentation — READMEs, doc comments, inline comments, or when code lacks explanation for non-obvious behavior.

Protobuf schema design and gRPC service patterns — streaming, error handling, backward compatibility. Use when designing .proto files, implementing gRPC services or clients, choosing a streaming pattern, handling gRPC errors, or evolving a schema without breaking consumers.

Drafts clear, professional emails ready to copy and paste — from a brief description of the situation, audience, and intent. Use when asked to write, draft, or compose an email, reply to a message, or suggest how to phrase something professionally.

Modern Java 17+ — records, sealed types, pattern matching, streams, Spring Boot. Use when writing or reviewing Java 17+ code, modernizing legacy Java, or working in Spring Boot services.

Structures user research — planning sessions, synthesizing findings, and translating insights into product decisions. Use when planning user interviews, analyzing research data, creating personas or journey maps, or turning qualitative feedback into structured recommendations.

Reflex Python web framework for full-stack apps in pure Python — components, state, routing, and deployment. Use when building Reflex apps, designing component hierarchies, managing Reflex state, or deploying a Reflex application.

LLM output evaluation — automated metrics, LLM-as-judge, A/B testing, regression testing. Use when measuring LLM output quality, comparing prompt or model versions, building an automated eval pipeline, setting up regression tests for prompt changes, or evaluating RAG systems and bias/safety.

Secure coding practices grounded in the OWASP Top 10. Use when reviewing code for security issues, implementing input validation, hardening web applications, or adding defenses against injection, XSS, or CSRF.

Frontend architecture and UI design — component hierarchies, accessibility, performance, state management. Use when designing frontend architecture, building component hierarchies, making something accessible, optimizing Core Web Vitals, or choosing a state management approach.

System design methodology — requirements, capacity estimation, component design, trade-offs. Use when designing a new distributed system, evaluating an existing architecture for scalability or cost, performing back-of-envelope capacity estimation, or preparing for a system design review.

Alert design and on-call practices — severity, runbooks, SLO burn-rate alerting, escalation. Use when designing alerts, writing runbooks, reducing alert fatigue, setting up escalation policies, implementing SLO-based alerting, or improving on-call processes.

Creates data-driven infographics and charts as accessible SVG. Use when visualizing data, choosing a chart type, generating an SVG chart or infographic, or reviewing a visualization for clarity and accuracy.

Simulates a panel of expert advisors who each evaluate a problem from their distinct perspective — surfacing blind spots and generating more diverse thinking than a single viewpoint. Use when asked to get multiple perspectives, consult experts, think through a decision from different angles, or when a problem benefits from specialist input.

Generating and manipulating PDF files — from HTML, DOCX, or raw content using reportlab, weasyprint, or pypdf. Use when producing PDF reports, invoices, certificates, or when merging, splitting, or extracting text from existing PDFs.

Select, document, and evolve a Git branching strategy for a repository. Use when comparing Gitflow, GitHub Flow, trunk-based development, feature branches, release branches, or concurrent version lines.

REST API design — resource naming, HTTP methods, status codes, pagination, versioning, OpenAPI. Use when designing a new REST API, reviewing API contracts, writing OpenAPI/Swagger documentation, or choosing pagination, versioning, or error-format strategies.

Vector embeddings and vector DB patterns — model choice, similarity metrics, index tuning. Use when choosing an embedding model, picking or migrating between vector databases, optimizing semantic search quality or latency, or building a hybrid (dense + sparse) retrieval pipeline.

Explain and apply core ML/AI concepts — model types, training pipelines, evaluation metrics, and neural architectures.

Prompt design patterns — few-shot, chain-of-thought, structured output, injection defense. Use when crafting or refining LLM prompts, designing system prompts for agents, requesting structured output, defending against prompt injection, building reusable prompt templates, or iterating on prompt quality.

Retrieval-Augmented Generation pipelines — ingestion, chunking, embedding, vector stores, retrieval, evaluation. Use when building a RAG pipeline, choosing chunking strategies or embedding models, debugging retrieval quality or hallucinations, evaluating an existing RAG system, or scaling/migrating vector stores.

Distributed tracing with OpenTelemetry — spans, context propagation, sampling. Use when instrumenting a distributed system, debugging requests that span services, setting up OpenTelemetry, choosing a sampling strategy, or understanding latency across service boundaries.

SEO — on-page, technical, structured data, Core Web Vitals, and mobile-first indexing. Use when optimizing a website for search engines, adding meta tags or structured data, fixing Core Web Vitals, or auditing technical SEO.