scaffold

Run a high-stakes decision through a council of five persona-diverse advisors (Contrarian, First-Principles, Expansionist, Outsider, Executor) in parallel, then anonymized peer review, then a chairman synthesis of where they agree, clash, and what to do. Use for real tradeoffs ("council this", "pressure-test this", "should I X or Y"), not factual or low-stakes questions.

Composite review-and-fix for the current diff — run the correctness review (validate) and structural-quality review (simplify) in parallel, merge their findings, then apply all fixes in a single serial pass and re-verify. Supports --effort, --fix, --comment. For a full-repo survey use /audit.

Run all quality lenses (validate, simplify), aggregate findings into a design doc, then drive the full feature chain (PRD → TDD → PR) to fix them systematically.

Structural-quality review of changed code — score against the four-dimension rubric, gate at 10/10, and (in auto-fix mode or with --fix) apply reuse/simplification/efficiency/altitude cleanups. Includes a diff-economy lens; correctness is /validate, full-repo survey is /audit.

Validate the current diff for correctness bugs and test-integrity regressions (a test weakened to pass is a defect); supports --effort low|medium|high|max, --full to scan the whole repo, --fix to apply fixes, --comment to post as PR inline comments.

Generate or update a mermaid diagram with the `.mmd` text as source of truth — defaults to a lightweight zero-dependency Node live-preview server that watches the .mmd and hot-reloads a browser tab (pan/zoom), with a self-hosted mermaid.live editor via Docker, system-viewer SVG, VS Code live preview, or a public mermaid.live publish URL as alternatives. Use for architecture, flowchart, sequence, ER, state, or class diagrams; "diagram this", "draw the architecture", "make a mermaid diagram", "render this mermaid", or "/diagram". Never converts to a lossy shape format.

Lazy-senior-dev generation mode — force the simplest working solution (YAGNI, stdlib first, no unrequested abstractions)

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

Add linter configs and GitHub Actions workflows for languages detected in the current repo. Use when the user wants to add linters, set up code quality checks, or after sync-scaffold suggests running /add-linter.

Score source files against the four rubric dimensions (Quality, Readability, Encapsulation, Clarity), ranked worst-first with cited violations. Accepts an optional path and --fix flag.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Create a pull request for the current branch and immediately subscribe to PR activity. Use when the user wants to open a PR, submit changes for review, or push and create a pull request.

Review design.md for structural quality — abstraction discipline, vocabulary precision, bounded logic, simplicity. Auto-fixes when called from the chain; shows findings for approval when called standalone.

Use when the user wants to build a new feature, implement a new capability, add functionality, or start a development task from scratch. Runs design Q&A → PRD → TDD → review automatically.

Use when the user wants to stress-test a plan or feature idea, sharpen terminology, or resolve design decisions through Q&A before writing any code.

Export scaffold skills into another repo in the target harness format. Use when the user wants to add scaffold skills to a project, export capabilities, copy skills to another repo, or run hoist-skill.

Checkpoint the session into git so it survives a close and resumes from any device. Use on "pause", "checkpoint", "cache this session", "save my place", or "I'm stepping away" — writes a handoff, commits work in flight, and pushes.

Open GitHub branch protection settings for the current repo and show the full configuration checklist — restrict pushes, block force pushes, require PRs, require status checks. All items are idempotent. Use when the user wants to set up, configure, or verify branch protection on main.

Resume a checkpointed session from the pushed handoff and continue where it left off. Use on "resume", "pick up where I left off", "continue from the handoff", or starting cold on another device — pulls, reads .pause/handoff.md, and keeps going.

Capture a completed session as a reusable, registered skill. Run when the user wants to turn the current session into a skill, extract a repeatable workflow, or create a new skill from work just finished. Reconstructs context, interviews briefly, generates a SKILL.md + tests, registers it in RESOLVER.md, and opens a PR to scaffold.

Use when the user wants to build a feature or fix a bug using test-driven development, or mentions red-green-refactor, TDD, or test-first development.

Use when the user wants to turn current conversation context and codebase understanding into a structured PRD. Do not re-interview — synthesize what is already known.

Sync this repo from the upstream scaffold, or bootstrap scaffold support if it isn't set up yet. Use when the user wants to sync from scaffold, initialize scaffold, or run the bootstrap script.