Alexander Cedergren

Use when auditing API routes for schema drift, missing auth, or validation gaps. Scans routes against shared TypeScript types to find mismatches, missing middleware, and undocumented endpoints. Read-only — produces a severity-grouped report. Keywords: audit routes, schema drift, auth gaps, missing validation, type mismatch, orphaned schemas. Triggers on "audit API routes" or "find schema drift".

Use when the user asks to "review OCI architecture", "avoid OCI anti-patterns", "plan an Oracle Cloud migration", "evaluate OCI Well-Architected risks", or "choose which OCI skill applies".

Use when given a bug report, failing test, stack trace, or CI failure that needs diagnosis and repair. Autonomously diagnoses root cause, implements minimal fix, verifies correctness, and commits. Keywords: fix bug, failing test, stack trace, CI failure, debug error, broken test. Triggers on "fix bug" or "debug failing test".

Use when the user asks to "launch OCI compute", "choose an OCI shape", "debug compute capacity", "configure instance principals", or "optimize OCI instance cost".

Use when the user asks to "create an OCI database", "choose DB System vs ADB", "manage PDB lifecycle", "route ADB work", or "plan Oracle database provisioning".

Use when auditing or fixing drift between project documentation and the actual codebase. Detects stale architecture diagrams, wrong file paths, outdated test counts, and undocumented structural changes. Pass 'fix' to apply repairs; default is report-only. Keywords: doc drift, stale docs, sync docs, documentation audit, update docs, architecture docs outdated. Triggers on "audit doc drift" or "sync documentation".

Use when the user asks to "bridge Better Auth into Fastify", "fix Fastify session resolution", "forward auth cookies", "patch IDCS org context", or "decorate Fastify request auth".

Use when user asks to find, install, or search for agent skills. Also use when user asks 'can you do X' or 'is there a skill for X' where X is a specialized capability. Keywords: install skill, find skill, npx skills, skills.sh, extend agent, add capability. Triggers on "find skill" or "install skill".

Use when the user asks to "optimize OCI cost", "investigate an OCI bill", "estimate egress cost", "right-size OCI resources", or "plan Resource Scheduler savings".

Use when scraping web pages, extracting content from JS-rendered sites or SPAs, running search-plus-scrape workflows, or mapping entire site URL trees. Produces clean LLM-friendly Markdown. Prefer over WebFetch when JavaScript execution is required. Keywords: web scraping, fetch URL, scrape website, search web, extract content, SPA, JS-rendered, site map, crawl, Firecrawl. Triggers on "scrape website" or "extract web content".

Use when the user asks to "call OCI Generative AI", "choose an OCI GenAI model", "debug GenAI 429", "plan OCI RAG", or "compare Command A, Llama, Gemini, or gpt-oss".

Use when running codebase quality gates (typecheck, lint, tests, security, dead code, circular deps, audits). Reports pass/fail across all checks without making edits or suggesting fixes. Keywords: health check, pre-PR validation, quality gates, repo diagnostics, CI gates. Triggers on "run health check" or "validate quality gates".

Use when making text sound human, removing AI tells, or fixing writing that sounds like ChatGPT. Detects and rewrites AI patterns: overused phrases (testament to, pivotal, landscape, delve), structural tells (rule of three, em dash overuse, negative parallelisms, copula avoidance), promotional language, and vague attributions. Keywords: AI-generated, humanize, writing style, natural writing, human voice, remove AI patterns, conversational tone. Triggers on "humanize writing" or "remove AI tells".

Use when the user asks to "write OCI IAM policy", "debug OCI 403", "Terraform apply gets 403", "configure dynamic groups", or "use identity domains".

Use when implementing a feature, adding an endpoint, or making a non-trivial code change that requires pre-flight validation, TDD cycle, scope enforcement, and a clean commit. Combines pre-flight + tdd + scope-check + quality-commit into one flow. Keywords: implement feature, add endpoint, TDD, new functionality, code change. Triggers on "implement feature" or "add endpoint".

Use when the user asks to "Terraform state on OCI", "native OCI backend", "Terraform import OCI", "Terraform apply 403", "Terraform ZPR", or "Terraform Bastion".

Use when the user asks to "design an OCI landing zone", "plan compartments", "enable Security Zones", "build hub-spoke OCI", or "meet CIS OCI Foundations".

Use when the user asks to "use OCI Bastion", "create Managed SSH", "debug a port forwarding session", "configure dynamic port forwarding", or "update client CIDR allowlist".

Use when bulk-migrating import paths, renaming workspace packages, or reorganizing modules across many files in a monorepo. Uses scripted bulk operations with verification gates and atomic commits. Keywords: migrate imports, rename package, bulk import path change, module reorganization, monorepo refactor. Triggers on "migrate imports" or "rename package".

Use when the user asks to "create OCI alarms", "debug missing metrics", "write MQL", "configure Service Connector", or "monitor OCI resources".

Use when the user asks to "design OCI networking", "debug VCN connectivity", "configure Service Gateway", "choose NSG vs security list", or "plan FastConnect or VPN".

Use when the user asks to "find OCI skills", "route Oracle Cloud work", "install the OCI skill pack", "review OCI skill ownership", or "separate Oracle skills".

Use when the user asks to "create OCI Events rule", "trigger Functions from events", "route events to Streaming", "debug Events delivery", or "filter CloudEvents".

Use when the user asks to "create Oracle slides", "edit an Oracle deck", "build a CloudWorld presentation", "review Oracle-branded PPTX", or "apply Oracle brand to slides".

Use when the user asks to "configure OCI Resource Manager", "debug Resource Manager job", "create ORM stack", "use Resource Manager private endpoint", or "fix Resource Manager dynamic group".

Use when the user asks to "choose OCI security control", "route OCI security issue", "compare Cloud Guard vs Security Zones", "decide ZPR vs NSG", or "use Bastion vs public SSH".

Use when the user asks to "manage Autonomous AI Database", "debug ADB performance", "fix wallet connection", "optimize ECPU cost", or "use SQLcl with Oracle Database".

Use when the user asks to "connect Better Auth to OCI IAM", "configure identity domain OIDC", "fix IDCS callback URL", "set trusted origins", or "bootstrap Oracle auth provider".

Use when the user asks to "map IDCS groups to orgs", "provision org_members from identity domains", "fix Better Auth active org", or "bootstrap first admin".

Use when executing a multi-task implementation plan with parallel agents. Coordinates task assignment, wave sequencing, heartbeat monitoring, git safety, and quality gates. Supports interactive (TeamCreate/Task) and headless (claude -p) modes. Keywords: parallel agents, wave execution, orchestrate, headless, phase execution, task plan. Triggers on "orchestrate agents" or "execute multi-task plan".

Use when starting a new development phase or sprint that needs branch creation, TDD test shell, and roadmap entry done together. Enforces phase scaffolding before implementation begins. Keywords: new phase, sprint start, feature branch, roadmap, test shell, scaffold. Triggers on "start phase" or "scaffold sprint".

Use when creating, updating, validating, or phasing a PRD. Drives interactive discovery, technical architecture, phasing DAG, TDD protocol, and dependency analysis. Keywords: PRD, product requirements, feature planning, acceptance criteria, MoSCoW, phasing, requirements document. Triggers on "create PRD" or "update requirements".

Use when assessing release readiness or running a pre-launch review. Spawns 5 specialist agents in parallel (security, testing, performance, observability, code quality) and synthesizes a prioritized report with ship/don't-ship recommendation. Keywords: production readiness, release review, pre-launch, security audit, test coverage, ship checklist. Triggers on "assess production readiness" or "run launch review".

Use when creating a new skill and publishing it to a GitHub repo for installation via npx skills add. Covers scaffold, spec compliance, skill-judge evaluation, commit, push, and install verification. Keywords: publish skill, add skill to repo, npx skills init, share skill, agentic-tools, skills.sh. Triggers on "publish skill" or "share skill".

Use when committing code changes. Runs lint, typecheck, Semgrep security scan, optional CodeRabbit review, and related tests before creating a quality-gated commit. Flags: --review, --push, --dry-run, --message. Keywords: commit, quality gates, lint, typecheck, semgrep, coderabbit, stage, push. Triggers on "commit changes" or "run quality commit".

Use when deciding whether to extract Terraform code into a reusable module, determining module boundaries, or migrating state after modularization. Covers the refactoring decision (modularize vs inline), anti-patterns causing module sprawl, and state migration risk. Keywords: terraform module, refactor terraform, module boundaries, terraform abstraction, module sprawl, state migration, terraform state mv. Triggers on "refactor Terraform module" or "decide module boundary".

Use when preparing a PR or completing a phase of work and needing a full-spectrum code review. Runs security, API audit, and scope reviewers in parallel and synthesizes findings into a single go/no-go report. Read-only — no file modifications. Keywords: pre-PR review, security audit, API audit, scope review, code review, merge check. Triggers on "review all changes" or "run pre-PR review".

Use when the user asks to "store OCI secrets", "rotate Vault secrets", "debug secret retrieval 403", "use instance principals for Vault", or "Terraform state secret".

Use when reviewing code changes before commit or PR merge. Covers tool sequencing, finding severity priorities, fix ordering strategy, and conflict resolution between tools. Keywords: code review, semgrep, coderabbit, security scan, pre-commit review, PR review, hardcoded secrets, SQL injection, XSS. Triggers on "review with Semgrep" or "run CodeRabbit review".

Use when working with shadcn-svelte components, TanStack Table in Svelte 5, or Tailwind v4.1. Covers non-obvious reactivity bugs, library selection trade-offs, and migration pitfalls not in the official docs. Keywords: shadcn-svelte, TanStack Table, Tailwind v4.1, Svelte 5 runes, bits-ui, superforms, data table, svelte-check. Triggers on "use shadcn-svelte" or "build Svelte data table".

Use when the user asks to "migrate SQLite to Oracle", "replace better-sqlite3", "plan Oracle migration", "convert SQLite schema", or "find SQLite touch points".

Use when extracting a design system from a Stitch project to create a DESIGN.md source-of-truth for consistent multi-screen generation. Covers semantic translation of technical design assets into descriptive language Stitch interprets for visual consistency. Keywords: stitch, DESIGN.md, design system, design tokens, color palette, typography, component styling, design governance, multi-screen consistency. Triggers on "extract Stitch design system" or "create DESIGN.md".

Use when enhancing, polishing, or fixing Stitch UI generation prompts. Adds UI/UX keywords, injects design system tokens, structures page hierarchy, and enforces hex color formatting. Triggers on: Stitch prompt, improve prompt, better output, redesign, multi-screen consistency, design system, DESIGN.md. Triggers on "improve Stitch prompt" or "polish UI prompt".

Use when converting Stitch designs into production React components. Enforces modular architecture: logic in hooks, data in mockData.ts, Readonly TypeScript interfaces, theme-mapped Tailwind classes. Triggers on: Stitch to React, design to code, stitch export, stitch MCP, stitch:get_screen. Triggers on "convert Stitch to React" or "implement design export".

Use when debugging TanStack Query / React Query issues: v4→v5 migration errors (gcTime, isPending, throwOnError), infinite refetch loops, SSR hydration mismatches, choosing between React Query vs SWR, or optimistic update patterns not working. NOT for basic useQuery setup. Triggers on "debug TanStack Query" or "migrate React Query v5".

Use when implementing features, fixing bugs, or adding deliberate test coverage. Enforces test-first (red-green-refactor) cycle, handles mock bootstrap for projects with mockReset:true, prevents code-before-tests violations. NOT for reviewing existing code or running test suites. Triggers on "write test first" or "use TDD".

Use when making Turborepo monorepo architecture decisions: choosing between monorepo vs polyrepo, deciding when to split packages, debugging cache misses, setting package boundaries, or avoiding circular dependencies. NOT for basic CLI syntax. Triggers on: turborepo, turbo cache miss, package boundaries, monorepo architecture. Triggers on "debug turbo cache" or "design monorepo boundaries".

Use when drafting, translating, polishing, or reviewing Swedish text so it sounds natural, fluent, contemporary, and appropriate for its audience. Triggers include "write better Swedish", "make this sound natural in Swedish", "translate into Swedish", "polish this Swedish", "tech company Swedish", "contemporary Swedish words", "Swedish developer docs", and "avoid Anglicisms".

Use when adding or improving test coverage for existing source code without changing production behavior. Selects mock strategy by module type (route handler, repository, plugin, utility, service), handles mockReset:true environments, and prevents common vitest/jest mock wiring failures. Triggers on: write tests, add tests, test coverage, regression coverage, untested module, *.test.ts. Triggers on "write tests" or "add test coverage".

Use when the user asks to "configure ZPR", "debug Zero Trust Packet Routing", "write ZPL policy", "apply security attributes", or "protect OCI resources with ZPR".