Keep web applications, APIs and services readable as they grow: choose feature or domain seams, assign state ownership, enforce dependency direction, keep adapters thin, and verify file shape. Use when starting or extending a web app, backend, frontend, API or multi-page product; when a change makes a module hard to read; when architecture review finds a god file, cross-feature imports, a circular dependency or a framework-heavy domain. Load architecture-first first for a new system, and refactoring-safely for an existing oversized module. Do not use for a one-file script, throwaway spike or a purely local naming change.

Claude desktop app (Mac/Windows native) stores sessions per `<accountId>/<orgId>/`. When you switch accounts, old sessions become invisible in UI — they remain on disk but `LocalSessionManager.loadSessions()` only reads the active accountId folder.

Keep each unit comprehensible while the code grows: deep modules over shallow ones, information hiding, honest names, small functions with one job, error handling that does not lose the error, DRY and orthogonality, design by contract, and not leaving broken windows. Merges module-complexity management with naming/function/error-handling discipline and the pragmatic meta-rules. Use when writing or reviewing a function, class or module; when an interface feels wide, a class feels shallow, or a change in one place forces edits in three; when the user says "this is hard to follow", "clean this up", "review this code", "is this a good abstraction", "too many parameters", "pass-through method", "duplicated logic", or asks about naming, comments, error handling or unit tests. Do NOT use to decide where a new module LIVES or which modules exist (use architecture-first), to plan capacity or storage (use system-and-data-design), to execute a named transformation on a file that is already too large (use refactoring-safely), or to strip over-engineering on request (use lean-code). This makes a unit comprehensible; it does not draw the system's boundaries.

Drive and inspect an interactive CLI or TUI with a repeatable local harness, deterministic input, transcripts, and optional profiling. Use for CLI UX checks, prompt flows, startup regressions, hangs, interrupts, resize behavior, or memory growth. Do not use for a non-interactive command that a normal test can cover.

Use when work moves between Claude Code and Codex, a session resumes from a handoff, or an agent may rewrite an existing implementation. Loads the shared CONTINUITY.json contract, preserves accepted decisions, checks Git baseline and scope, and requires explicit replan mode for intentional redesign. Do NOT use for fresh work with no prior agent's decisions to preserve, for a single-harness session that no one else is continuing, or as a general handoff-writing helper (see the session-handoff rule); this skill governs the contract between agents, not the notes one agent leaves itself.

The Stop hook `session-feedback-capture.py` queues finished sessions into `~/.claude/feedback/queue.jsonl`. This skill processes that queue: it finds the user turns that were **durable corrections** of the agent's work and turns them into rules — so the same correction never has to be given twice.

Use when an agent says a test, VM, proof, evaluator, or release gate is overloaded, too strict, blocking staging, or causing false positives; split checks by profile, measure the burden, preserve high-risk evidence, and verify the smallest corrected workflow. Do not use for ordinary test selection, a single test failure, or a full security audit without a harness-scope question.

Make AI-generated English text sound natural and human. Use when: writing blog posts, articles, marketing copy, any English content that must not read as AI-generated. Covers: burstiness, perplexity, banned words, sentence patterns, transitions, tone. Based on: Liang et al. (arxiv 2406.07016, 15M+ abstracts), GPTZero/Originality research. Use BEFORE publishing any AI-generated English text. Do NOT use for Russian text (use humanize-russian) or for macro-level article structure such as thesis/proof balance or a limitations block (use article-structure-review); this skill operates at the word/sentence level on English only.

Scaffold a new layer in a project's docs/layers/ tree following the feature-layer architecture (principle 28). A layer is a bounded concern (security, data, ui, infrastructure, domain) with its own invariants, decisions, gotchas, patterns, and feature narratives. Use when: "create a new layer", "add security layer", "scaffold layer", "start tracking <concern> separately", "/layer-new", "add bounded concern". Operates on the kb-skeleton structure; idempotent -- will not overwrite existing layers. Do NOT use to scaffold an individual feature narrative inside an existing layer; use /feature-new for that (a layer is the container, not the per-feature doc).

Aggressive YAGNI mode, on demand. The always-on baseline is `rules/quality-code.md`; this skill is the **intensifier** you invoke when minimalism matters most. The win is measured ("smallest solution that FULLY satisfies the task"), not a slogan.

Take a short scene description (2-3 paragraphs, 1-3 elements, mood-driven) and turn it into a self-contained HTML file with one or more **canvas-rendered seamless-loop pixel art** scenes.

Refactoring is a behaviour-preserving transformation. If behaviour changed, that was not a refactor, it was a rewrite with optimistic branding — and the reason large restructures fail is almost always that the two were done in one step.

Operate GPU and remote compute across RunPod (Pods and Serverless), Massed Compute VMs, and owned or virtual remote servers through existing bridges, SSH sessions, MCP/API adapters, bounded polling, cost controls, and resumable lifecycle checks. Use when the user mentions RunPod, Massed Compute, a remote GPU/server/VM, SSH bridge/tunnel/bastion/Tailscale, training or inference on rented compute, GPU inventory, billing, or asks to minimize API/SSH connections and avoid rate limits. Do not use for generic cloud architecture, local-only GPU work, or application code with no remote-resource operation.

Prove a concrete behavior, performance, UI, CLI, API, or memory claim with fresh baseline-versus-treatment evidence and one explicit verdict. Use when asked to verify, prove, compare before and after, show evidence, or confirm that a fix works. Do not use for vague claims such as cleaner code, a full plan-based release verification, or a known bug that needs a red-to-green reproducer.

Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master audio', 'export settings', 'platform requirements'. Covers FFmpeg patterns, audio chain, subtitle standards, and platform-specific export configs. Do NOT use to generate or animate the video frames/scenes in code (use remotion-production-guide), to write the script (use video-narrative-arc), or to evaluate script quality (use script-evaluator); this is the finishing stage applied to an already-rendered video.