Requirements Interview
Interview before PRD or spec work by exploring code first, resolving product and technical ambiguity, and deciding the right artifact. Use when: starting a feature, expanding features, clarifying requirements. Do not use: for spec-only work, requirements already clear.
Python Ci Setup
Set up a Python CI/CD pipeline with linting, formatting, type checking, tests, security scanning, and publishing. Use when: creating CI for Python, adding checks to workflow. Do not use: for local development setup, non-CI automation.
Validate With Zod
Generate Zod validation patterns for common use cases. Use when: validating API responses, form validation, localStorage parsing. Do not use: for type design, non-validation concerns.
Scientific Paper
End-to-end workflow for creating, reviewing, and critiquing scientific papers with rigorous methodology. Use when: writing papers, reviewing papers, literature reviews. Do not use: for blog posts, technical documentation.
Terraform Change
Plan and review a Terraform infrastructure change safely. Use when: editing Terraform, importing resources, moving resource addresses. Do not use: for infrastructure design, non-Terraform IaC.
Langgraph Agent Design
Design or review a LangGraph agent workflow. Use when: creating a graph, choosing state schema, nodes, tools, checkpoints, interrupts. Do not use: for simple chains, non-agent patterns.
Model State With Xstate
XState v5 recipes for React integration, testing with createActor, and actor patterns. Use when: xstate react, testing state machine, actor patterns. Do not use: for simple component state, non-XState management.
Scientific Case Study Research
Design, validate, and report empirical software engineering case studies. Use when: case study protocols, research questions, units of analysis, triangulation. Do not use: for controlled experiments, surveys, benchmarks.
Approval Gates Before Implementation
HARD GATE: Prevents implementation without explicit spec approval and user confirmation. Use when: starting a feature, before any code. Do not use: during implementation, for tiny refactors, or when approval already granted.
Generate Tests From Spec
Generate tests from a spec's acceptance criteria. Use when: you have an approved spec and need tests, TDD from spec. Do not use: before spec approval, for test planning without specs.
Go Ci Setup
Set up a Go CI/CD pipeline with formatting, vetting, static analysis, tests, vulnerability scanning, and container build. Use when: creating CI for Go, adding checks to workflow. Do not use: for local development setup, non-CI automation.
Code Review Requesting
Structured code review workflow ensuring context and clarity. Use when: implementation complete, tests verified, before merge request. Do not use: during active implementation, before verification checklist, or for design reviews.
Bugfix Loop
Run a disciplined bugfix loop with reproduction, hypotheses, regression test, fix, and cleanup. Use when: fixing bugs, debugging regressions, investigating failures. Do not use: for feature implementation, refactoring.
Generate Spec
Generate a structured spec from direct input. Use when: you already know what you want and just need the formatted template. Do not use: for exploration and interviews (use spec-writer agent).
Vertical Tdd
Implement one behavior at a time with a red-green-refactor loop. Use when: executing tasks.md, doing TDD, implementing a feature from specs. Do not use: for test planning, bulk implementation.
Supabase Workflow
Plan or review a Supabase database/platform change. Use when: changing schema, migrations, RLS policies, Auth, Storage, Edge Functions. Do not use: for general database design, non-Supabase platforms.
Abort Criteria
Decision gates for when to STOP a task and escalate. Use when: time budget exceeded, circular debugging detected, scope creeping, or architectural mismatch found. Do not use: for normal task breaks, PR reviews, or acceptance testing.
Text Review
Rewrites blog post drafts to eliminate AI-generated writing patterns while preserving the author's voice. Use when: removing AI patterns, humanizing text, editing technical posts. Do not use: for academic papers (use paper-review), content generation.
Android Ci Setup
Set up an Android CI/CD pipeline with lint, static analysis, unit tests, dependency review, and build verification. Use when: creating CI for Android, adding Gradle checks. Do not use: for local development setup, non-CI automation.
Generate Adr
Generate an Architectural Decision Record in MADR 4.0 format. Use when: recording a decision, architecture decision record, documenting why we chose X. Do not use: for full architecture analysis, routine choices.
Task Breakdown
Break a PRD, spec, or plan into vertical tasks in tasks.md. Use when: creating tasks, breaking down work, converting a plan to tasks. Do not use: for individual task execution, sprint planning.
Migrate React Router
Guide migration from React Router v6 to v7 framework mode. Use when: migrating routes, upgrading react-router, v6 to v7. Do not use: for initial React Router setup, general routing patterns.
Decision Framework
Structured decision-making preventing emotional and hasty choices. Use when: making architectural decisions, tool selections, or strategic choices. Do not use: for obvious technical decisions, simple syntax fixes, or time-critical emergencies.
Ci Workflow
Create, review, or debug a CI/CD workflow. Use when: editing GitHub Actions, fixing CI failures, adding release/deploy automation. Do not use: for general DevOps, infrastructure as code.
Manage State With Zustand
Zustand v5 recipes for middleware setup, immer mutations, persistence, and XState sync. Use when: zustand middleware, zustand persist, store patterns. Do not use: for state design patterns, non-Zustand stores.
Rust Ci Setup
Set up a CI/CD pipeline for Rust projects. Use when: creating CI for Rust, adding Clippy/fmt/test/audit to CI. Do not use: for local development setup, non-CI automation.
Generate Glossary
Extract and formalize domain terminology into a glossary. Use when: defining domain terms, building glossaries, hardening terminology. Do not use: for general documentation, simple dictionaries.
Postgres Query Review
Review a PostgreSQL query, migration, index, or query plan. Use when: optimizing SQL, checking migrations, reading EXPLAIN output. Do not use: for general database design, non-Postgres systems.
Skill Authoring
Create or revise Copilot skills that match this repository's structure and naming conventions. Use when: writing a new skill, renaming a skill, reviewing skill quality. Do not use: for general writing, non-skill documentation.
Verification Checklists
HARD GATE: Mandates fresh verification evidence before task completion. Use when: post-implementation, before marking work done. Do not use: before code is written, for planning, or for code review requests.
Llm Integration Review
Design or review an LLM integration in a service. Use when: adding model calls, tools, structured outputs, retries, rate limits. Do not use: for prompt engineering alone, non-service LLM work.
Regression Testing
Mandatory regression test creation for every bug fix across Go, Python, and JavaScript. Use when: fixing bugs, after root cause identified, before applying fix. Do not use: for feature implementation, unit test planning, or non-code changes.
Typescript Ci Setup
Set up a TypeScript CI/CD pipeline with type checking, linting, formatting, tests, security scanning, and build verification. Use when: creating CI for TypeScript, adding checks to workflow. Do not use: for local development setup, non-CI automation.
Gcloud Operation
Run or prepare a safe Google Cloud CLI operation. Use when: using gcloud, changing GCP resources, deploying to GCP. Do not use: for local CLI exploration, non-GCP operations.
Premortem
Run a premortem on a plan, decision, or launch. Assumes it already failed and works backward to find why. Use when: premortem this, stress test this plan, find blind spots. Do not use: for post-launch postmortems, blame analysis.
Update Docs
Update project documentation after implementing a feature. Use when: updating docs, documentation, update docs after implementation. Do not use: for doc-first design, specification writing.
Rust Release
Plan and execute Rust release engineering. Use when: publishing a crate, setting up release automation, cross-compiling binaries. Do not use: for version bumping alone, local build setup.
Agent Rationalization Blocking
Anti-pattern catalog identifying common self-deception in agent workflows. Use when: pre-completion checkpoint, before claiming work is done, validating agent reasoning. Do not use: for external code review or design phases before implementation.
Git Commit
Create a safe Git commit with Conventional Commits format. Use when: committing changes, reviewing staged changes. Do not use: for commit history rewriting, interactive rebasing.
Chromadb Rag Workflow
Design or review a ChromaDB-backed RAG workflow. Use when: creating collections, choosing embedding functions, chunking documents, writing retrievers. Do not use: for general LLM integration, non-RAG patterns.
Subagent Selection
Decision framework for delegate-vs-inline work optimization. Use when: deciding whether to use inline work or spawn specialist agents, cost-benefit analysis needed. Do not use: for simple read-only operations, single-file edits, or direct implementation.