# ApexYard Skills > 59 slash commands grouped by what you're trying to do — not by what's under the hood. Drop into your Claude Code session inside an apexyard fork. ## In plain English These are the commands you type into Claude Code to get ApexYard to do something. They're grouped by what you're trying to do — keep quality high, move work forward, see everything at once, onboard new code, run things — not by what's under the hood. If you'd rather see a real day with these, read [how it works](https://yard.apexscript.com/how-it-works.md). ## What is it? ApexYard ships 59 slash commands grouped under outcome headings — Keep quality high, Move work forward, See everything at once, Onboard new code, Run things. ## What can it do? Each `/` is a structured workflow with safety rails. The right framework checks fire at the right moments — `/approve-merge` writes a record that the merge gate verifies before the merge actually runs. Every skill ships in `.claude/skills//SKILL.md`. ## What's needed to start? Browse below; invoke any skill from a Claude Code session inside an apexyard fork. New here? Start with `/setup` on a fresh fork, then `/feature` or `/idea` to capture work, then `/code-review` and `/approve-merge` when a PR is ready to ship. --- ## Keep quality high The skills that catch mistakes before they reach customers — reviews, audits, security checks. - `/code-review ` — invoke the Code Reviewer agent (Rex) on a PR. - `/security-review ` — invoke the Security Reviewer agent (Hakim) on a PR. - `/audit-deps` — audit dependencies for vulnerabilities, outdated packages, licences. - `/launch-check` — production readiness audit — multi-dimension go/no-go sweep at milestone boundaries. - `/threat-model` — threat modelling across 6 attack categories (spoofing, tampering, repudiation, disclosure, denial of service, elevation of privilege). - `/accessibility-audit` — WCAG 2.1 AA audit. - `/compliance-check` — GDPR + ePrivacy audit (consent, privacy policy, data handling, right to deletion, DPAs). - `/analytics-audit` — SDK config, event naming, funnel completeness. - `/seo-audit` — meta tags, sitemap, robots.txt, OG, structured data. - `/geo-audit` — AI/LLM discoverability — `llms.txt`, `AGENTS.md`, AI-crawler robots, JSON-LD citation grounding. - `/performance-audit` — bundle size, image opt, lazy load, code split, Core Web Vitals. - `/monitoring-audit` — logging, error tracking, health endpoints, alerting, runbooks. - `/docs-audit` — Diataxis docs audit (tutorials, how-to, reference, explanation). - `/mutation-test` — mutation-testing sensor; milestone cadence, exit-3 graceful-degrade. ## Move work forward Capture an idea, file a ticket, record a decision, approve a merge — everything that turns half-formed thoughts into shipped software. - `/start-ticket | /#` — Declare an active ticket for this session so the ticket-first hook lets code edits through. - `/approve-merge ` — Record per-PR CEO approval and merge in one turn. Only on an explicit per-PR "approved" — never on umbrella "go". - `/approve-design ` — Record per-PR design-review approval for UI PRs. - `/decide` — Make a technical decision and record it permanently — what you considered, what you picked, why. Required before architecture changes. - `/idea` — Capture a new product idea / feature concept / internal tool proposal to the shared backlog. - `/validate-idea` — Lightweight 5-question pre-spec gate between `/idea` and `/write-spec`. - `/write-spec` — Generate a PRD or feature spec from a problem statement. - `/plan-initiative` — Initiative → milestones → tasks with dependency-aware sequencing. - `/feature` — Create a structured feature ticket (user story + acceptance criteria + design notes). - `/bug` — Create a structured bug ticket (Given/When/Then + repro steps + severity). - `/task` — Create a structured technical task ticket (driver, scope, ACs) for tech debt, infra, refactoring. - `/spike` — Create a hypothesis-driven, time-boxed spike ticket. Exempt from decision-record + coverage gates. - `/spike-close --promote | --discard` — Disposition gate for spikes — promote files a fresh `[Feature]`; discard writes a memo. - `/migration` — Create a labelled migration ticket + matching decision record (rollback, downtime, consumers, observability). Required by the migration gate. - `/investigation` — Create an investigation ticket + live-doc for sustained root-cause work. - `/tickets-batch` — Bulk-file 5–20 structured tickets in one flow (shared-context Qs once, 3-Q micro-interview per ticket). ## See everything at once When you have more than one product going at the same time, the question that costs you the most is "what's waiting on me right now?" - `/projects` — List all managed projects with status, branch, open PRs, open issue counts. - `/inbox` — Items needing your attention across the portfolio: PRs, assigned issues, comments, blockers. - `/status [--briefing | -b]` — Per-project git + CI snapshot; `--briefing` for the 4-line compact form. - `/tasks` — Aggregated, scored, sorted task list across the portfolio with direct URLs. - `/roadmap [add | remove | reorder | show] [item]` — Update, create, or reprioritise the product roadmap. Renders a markdown table per milestone. - `/stakeholder-update weekly | monthly | launch` — Generate a stakeholder update from real activity (recent PRs, closed issues, decisions, roadmap) — not from what you remember. - `/agdr browse | search | show | stats` — Searchable library of every technical decision ever recorded across your portfolio. Answers "have we decided this before?". ## Onboard new code Fresh fork, new project handed to you, codebase you want to understand. These skills get you oriented fast — generating diagrams, feature inventories, process flows from real code instead of from memory. - `/setup [--reset]` — First-run framework bootstrap for a new ApexYard fork. Three exchanges and the fork is configured. - `/handover [path-or-url]` — Onboard an external repo into ApexYard management. Reads the target, synthesises a structured handover assessment, scores harnessability across 5 codebase dimensions. - `/c4` — Generate architecture diagrams (Level 1 system context + Level 2 container detail) from a project's codebase. - `/dfd` — Extract a data-flow diagram with trust boundaries + data classifications (Mermaid + optional Threat Dragon JSON). Source of truth for `/threat-model`. - `/process` — Extract a business process from your code (state machines, queue chains, cron, API choreography) via 7-axis scan + gap-targeted interview, then emit a standard process-diagram file. - `/extract-features` — Six-axis Feature Inventory (routes / models / jobs / tests / UI / docs) — a "what we must preserve" spec for greenfield rewrites. - `/feature-diagram` — Per-feature flowchart of routes / models / jobs / screens involved. - `/tech-vision` — Interactive author for the architecture vision template (target / gap / migration / anti-scope). - `/journey` — Self-contained HTML user-journey map (boxes/arrows with per-page modals) — preview between PRD and tech-design. - `/codify-rule` — Turn a human (or Copilot) review comment that caught a Rex-miss into a draft handbook entry. ## Run things Sync the framework, parallelise independent work, cut a release, debug something hairy, share a PDF with a non-technical stakeholder. - `/update [--dry-run] [--rebase]` — Sync the ApexYard fork with upstream. Previews pending commits, creates a sync branch, merges or rebases, walks per-file conflicts. - `/split-portfolio [--verify] [--dry-run]` — Migrate from single-fork to split-portfolio mode (public framework + private portfolio). - `/release [version]` — Cut a new apexyard release (framework-only). Diffs dev vs main, picks a semver bump, generates CHANGELOG, opens release PR. - `/debug` — Hypothesis-driven debugging — architecture-first reading + evidence-before-fix. For bugs that resisted naïve fix attempts. - `/pdf` — Convert markdown / HTML / process-diagram to PDF (pandoc / md-to-pdf / wkhtmltopdf / bpmn-to-image). - `/fan-out ` — Spawn N parallel Agent calls in a single assistant message, optionally with worktree isolation. ## Deprecated - `/onboard` — Use `/setup` for framework configuration, `/handover` for adding a project to the portfolio. This skill redirects to the correct flow. ## Links - Home: - How it works: - Architecture: - GitHub source for each skill: