Security Architect
Pragmatic security architect for a non-security-expert owner. Covers auth design (JWT/OAuth/sessions), where secrets and tokens live on each platform (iOS/Android/macOS/Windows/Linux/web), MITM and TLS, web vulns (XSS/CSRF/CORS/CSP), backend authorization (IDOR, injection, webhooks, rate limits), database rules (Supabase RLS/Firestore/Postgres policies), and AI-agent/MCP tool permissions. Load wh…
Skill Authoring
How to write skills, CLAUDE.md/AGENTS.md, fix logs, and handoff documents that a weaker or zero-context model can actually execute. Load when authoring or updating any instruction file, SKILL.md, project memory, or institutional-knowledge document — including when converting lessons from a session into durable files — and when about to act on a recorded capability-negative ("no such flag", "the A…
Motion Craft
Implementation-agnostic motion judgment for product UI. Load when you are adding, reviewing, or tuning animation in any framework - durations, easings, springs, staggers, entrances/exits, gesture handoff, reduced motion - when a spec says "smooth" or "delightful" with no numbers attached, or when you notice animation being judged by feel instead of against a budget. NOT for debugging one animatio…
Delegation And Review
Rules for delegating work to subagents and judging what comes back — when to spawn vs. do it yourself, how to write a dispatch packet, how to review agent-produced changes without rubber-stamping, when to retry vs. change approach vs. ask the user, and how to hand off long-running work across sessions. Load when about to spawn a subagent or write a dispatch prompt, when fanning out parallel work,…
Product Roadmap
Product-owner planning partner — turns a goal plus the repo's actual state into a verdict, a Now/Next/Later/Not-now roadmap, milestones with acceptance criteria, and agent-ready tasks. Load when the user asks "what should we build next?", any roadmap/milestone/release/MVP/priority/PRD question, wants the current repo assessed for product direction, or wants similar GitHub projects mined for insig…
Design Review Gate
Turns design review into observable checks. Load when you are judging a built UI surface ("does this look right/professional?", a visual QA request, before/after comparison of styling work), when generated design variants need comparison, or when any design document is about to be adopted, authored, or treated as authoritative - a DESIGN.md, tokens file, brand guide, or a reverse-engineered compe…
Ui Design Craft
Static visual judgment for generated or restyled UI. Load when you are about to produce or modify any user-facing surface - a landing/marketing page, product screen, mockup, or component styling - when a brief says "make it look good/premium/modern" with no design system attached, or when you notice generated UI converging on default AI aesthetics. NOT for motion decisions (motion-craft), for run…
Cross Model Review
Get an adversarial review from a DIFFERENT model family before a load-bearing merge/ship — the mechanized form of "the author is not the judge" when the strongest independent lens is another model, not just a fresh-context subagent of your own. Load when about to merge/ship load-bearing work (code, or a load-bearing plan/spec/doctrine doc), or when the user asks to get an external/second model to…
Operational Rigor
Core execution discipline for any non-trivial task — multi-step work, anything that modifies files or systems, debugging, or work whose correctness matters, even when the user does not ask for rigor. The latest load moment is observable — you are about to take your first mutating action (edit, write, state-changing command); loading earlier is better, and if you notice you are already past it, lo…
Ground Truth Gates
Build executable verification gates (golden set, replay corpus, project checks) so "it works" becomes a checked fact instead of a claim. Load when changing any LLM-judgment step (classify/extract/route/prompt), refactoring logic that processes real logged data, designing tests for a fix, setting up a commit/ship gate for a project, designing a runtime guard (a hook, validator, or auth check) and…
Personal Goal Planning
Coach-style personal goal planning — a five-step protocol that turns a person's situation into tiered goals (2–4 weeks / 2–3 months / 6–12 months) with one mainline, a small set of executable tasks, a realistic weekly rhythm, and a weekly review loop with a stuck rule. Load when the user asks to plan personal or career goals, a study/fitness/side-project plan, "help me figure out what to focus on…
Domain Evidence Discipline
Evidence discipline for non-code deliverables — marketing copy, research reports, data analyses, business/ops documents. Defines, per domain, what counts as evidence, the typed authority order, what verification-by-observation means, and the fraud table a reviewer hunts. Load when producing OR judging a non-code work product whose correctness depends on sources and claims rather than a runtime. N…