Designs stable API, interface, schema, event, CLI, module, and service contracts before implementation so callers, consumers, and future agents can depend on them safely. Use when creating or changing public/internal APIs, SDK surfaces, webhooks, GraphQL/REST/RPC routes, database or message contracts, module…
Reviews code changes across correctness, tests, readability, architecture, security, and performance before they are merged, shipped, or called done. Use when the user asks for a code review, when reviewing a PR/diff/commit/agent-produced code, after implementation or bugfix before final confidence, when deciding…
Curates focused project and session context before answering, planning, editing, debugging, reviewing, deploying, or handing off work. Use when starting or resuming work in a repo/workspace, switching tasks, output quality degrades, the codebase is unfamiliar or large, source-of-truth is unclear, docs/code/runtime may…
Appwrite backend development and operations, including destructive account/data erasure and MCP server wiring for coding agents. Use for Appwrite SDK work; any Appwrite CLI command or failure must route through the CLI safety branch.
Record polished Playwright walkthrough videos of a real web product, then review, approve, and convert them through a hash-bound pipeline. Use when the user asks for a product walkthrough video or e2e video proof of a UI journey.
Apply the Diátaxis framework to write, audit, organize, and improve technical documentation. Use when creating or revising tutorials, how-to guides, reference, explanation, docs IA, README sections, or documentation that feels mixed, incomplete, or hard to use.
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
Generates production design variants in Pencil WITHIN A LOCKED DESIGN DIRECTION (post-direction-lock work — for direction discovery use /design-explore). Critiques variants against the project spec + embedded aesthetic frameworks, presents structured trade-off reports, supports critique-only mode (evaluate existing…
Bootstrap the doc structure, design scaffolds, and CLAUDE.md a project needs before /design-explore, /design-agent, /code-agent, or /visual-qa can run — those companion skills hard-block on the artifacts created here. Use whenever the user starts a new project, says "set up specs / scaffold docs / create project…
Automated visual QA for a running frontend — screenshots the real rendered UI at the project's breakpoints and checks it against the project's own spec (tokens, layout rules, design language) AND its sibling screens, not hardcoded assumptions. Standalone on any frontend project; learns the project profile from docs/…
Execute heavyweight ready EngiFoundry Package Jobs in dependency order, obey the configured Executor and its mandatory availability Gate, enforce package engineering discipline, and record concise results. Use for implementation or rework of an existing ready Package PAK; never use for direct light work.
Review EngiFoundry planning, Job work, code, documents, research, or other durable outputs through an independent PAK-scoped Reviewer chain and record pass, rework-required, or factual blocked conclusions.
Declare EngiFoundry Node Skill contracts, their project-state signals, records, responsibilities, and possible navigation destinations so the Agent can assemble the contracts needed for a request.
Use when a software project needs durable cross-session governance for formal documents, WBS or tracker coordination, worktree delivery boundaries, evidence and acceptance states, handoffs, or architecture and design-document control.