Tinte Landing
Design or substantially improve a landing page for tinte. Use when building a marketing site, hero section, product page, pricing page, or any page whose job is to make a first-time visitor understand and want the product. Carries tinte composition rules, type scale, voice, and token API.
Ray
Generate code screenshots via ray.tinte.dev API. Use when user asks for code screenshots, code images, code snippets as images, or says "ray". Calls POST https://ray.tinte.dev/api/v1/screenshot and saves the PNG result.
Tinte
Agent-native design system infrastructure. Browse, install, and preview design systems from tinte.dev. Use when user asks about themes, design systems, presets, color palettes, or says "tinte". Works with shadcn/cli v4 presets and registries.
Quality Baseline
Baseline a repository before quality work. Use when asked to audit maintainability, reliability, performance, security, test quality, technical debt, or code health across a codebase; to identify and rank gaps before fixing them; or to compare quality state over time. Remain read-only on target source.
Record A Case
Record completed or interrupted maintenance work as an evidence ledger. Use after resolving, disproving, reviewing, or investigating an issue, PR, incident, or agent run; when backfilling an old session; or when another skill needs a durable case before extracting a method.
Handoff
Escribe el handoff de un ciclo de trabajo en el vault, verificando el estado contra git antes de afirmarlo. Usar al cerrar una sesion larga, antes de compactar, cuando el usuario dice handoff, /handoff, escribi el handoff, donde quedamos, antes de irme, cerra el ciclo, o cuando un hilo se vuelve demasiado largo para retomarlo de memoria. No usar para resumir una conversacion corta ni para escribi…
Review Gate
Gate a diff before pushing or requesting review: deterministic checks first, then focused lenses selected by what the diff changes. Use before opening or updating a PR, when asked to pre-review a change, or after an external review round to harvest each finding into a new gate.
Unfold
Understand, diagnose, change, or review an unfamiliar codebase through one evidence-backed mission. Use when learning architecture, tracing a feature, investigating a bug, implementing a real change with guided or agent execution, reviewing a diff or PR, or checking whether tests and the built artifact prove the intended behavior. Prefer over prose-only repository explanations and ungrounded debu…
Solution Gate
Experimental: Gate the shape of a fix before it is written. Two reviewer runtimes on different model families propose independently, each declaring falsifiable predictions; the cheapest refuting probe runs before any synthesis; proposals are scored against a catalog of recorded fix-failure shapes. Use when a diagnosed defect has more than one plausible solution shape, when the change alters a con…
Trail Decisions
Candidate: Keep a decision trail (a.k.a. show-your-work) while implementing, so a later reviewer can audit the choices and not just the diff. A TSV appended one row per real decision (what, why, evidence), written in the moment, never reconstructed. Use at the start of any implementation task an agent runs unattended or that a human reviews after stepping away. Consumed by review-gate's choice-au…
Signature Repro
Candidate: Root-cause a bug you cannot reproduce because it needs another OS or hardware you don't have, by detecting its structural OR visual signature on the machine you DO have. Use whenever you're about to write cannot-reproduce-needs-Windows/Linux/a-device/a-monitor, when a bug is platform-specific but you're on a different platform, when a visual bug (black rectangle, phantom window, broken…
Performance Proof
Prove a performance improvement before and after changing algorithms, data structures, latency, throughput, memory, bundle size, build time, or repeated work. Use when a concrete path is slow or resource-heavy, when considering Map, Set, heap, trie, queue, cache, index, batching, or memoization, or when asked to optimize code without guessing.
Resilience Audit
Pressure a system's failure paths. Use to audit or verify timeouts, cancellation, cleanup, retries, idempotency, partial writes, recovery, leaks, bounded queues or caches, overload, backpressure, dependency failure, malformed upstream data, cross-platform lifecycle behavior, or concurrent state transitions.
Pick An Issue
Survey an unfamiliar or shared issue backlog, qualify a small set of worthwhile contributor-side candidates, compare them in an evidence-backed matrix, recommend one, let the user make the final selection, and seed the canonical Issue Contract. Use for requests like "what should I work on here", "find a good issue to fix", or choosing among open issues. Stop before reproduction or implementation.…
Test Strength
Test whether regression coverage can actually detect the defect it claims to guard. Use when tests are green but may be weak, when reviewing coverage quality, after fixing a bug, or when asked for falsification, mutation testing, property-based testing, fuzzing, boundary integration, artifact verification, or flake detection.