anastasiyaw/claude-code-config
37 skills · 10 total installs
$npx skills add anastasiyaw/claude-code-configSkillInstalls
feature-newScaffold a new feature narrative document in an existing layer following the ULTRAPACK-style template extended for feature-layer architecture (principle 28).layer-newScaffold a new layer in a project's docs/layers/ tree following the feature-layer architecture (principle 28).agent-harness-designDesigning agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool results, agent budgets (10…article-structure-reviewСтруктурный self-review технической статьи перед публикацией. Покрывает три дыры, которые не ловятся точечными скиллами типа humanize/infostyle: thesis/proof…cross-harness-continuationUse when work moves between Claude Code and Codex, a session resumes from a handoff, or an agent may rewrite an existing implementation.deep-reviewParallel competency-based code review. Launches independent Agent reviewers per competency (security, performance, architecture, database, concurrency,…desktop-sessions-discoveryDiscover, search, and selectively restore Claude desktop app sessions hidden across multiple accountIds.diffusion-engineeringПрактическая инженерия диффузионных моделей: архитектуры, обучение, инференс, оптимизация памяти.distill-feedbackTurn captured user-correction signals into durable rules (learn-from-corrections loop).flux2-klein-promptingExpert prompt engineering for FLUX.2 [klein] image generation and editing model.flux2-lora-trainingComprehensive reference for training LoRAs on FLUX.2 Klein 9B and Qwen Image Edit 2511 models.forensic-prompt-compilerForensic image-to-prompt compiler for image generation models.frontend-designСоздание высококачественных, визуально выдающихся фронтенд-интерфейсов.gemini-delegateДелегирование задач в Gemini CLI (несколько OAuth-аккаунтов, свитчер, квоты, передача контекста).harness-auditScore a project's agent harness across 5 subsystems (Instructions / State / Verification / Scope / Lifecycle), identify the bottleneck, and produce a…harness-designDesign and build multi-agent harness architectures for long-running AI application development.humanize-englishMake AI-generated English text sound natural and human. Use when: writing blog posts, articles, marketing copy, any English content that must not read as…humanize-russianНатурализация русскоязычного текста - убрать маркеры ИИ-генерации.ios-developmentComprehensive iOS app development skill. Use this skill for ANY iOS-related task: writing Swift/SwiftUI/UIKit code, architecting apps, debugging crashes,…lean-codeOn-demand minimalism intensifier — write the leanest correct code, kill over-engineering before it starts.massed-compute-opsOperate Massed Compute GPU virtual machines through its MCP server.ml-research-labMachine-learning research loop for dataset curation, fine-tuning, evaluation, inference deployment, experiment tracking, and model explainability.notebooklm-grounded-researchUse when: NotebookLM, notebooklm MCP, large documentation sets, courses, books, papers, or citation-backed research are mentioned.observability-monitoringDesign, audit, and troubleshoot production monitoring and observability using user-impact checks, layered telemetry, USE/RED, SLI/SLO/SLA, error budgets,…pixel-art-storyboardConvert short scene descriptions, book/album cover briefs, or 2-paragraph synopses into seamless-loop animated pixel-art covers rendered as self-contained…pixel-art-studioCreate production-quality pixel art and animations programmatically.plan-swarm-reviewIterative plan review using multisampling + focused decomposition. Launches parallel independent agents to find issues that single-pass review misses.plan-to-ticketsUse when a large plan, PRD, feature, refactor, research plan, or multi-step coding task must be split into small ready-for-agent tickets with acceptance…product-meaning-extractorDeep product analysis before creating videos, presentations, or ads.proof-verifyPlan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify…remotion-production-guideRemotion (React video framework) production guide with Apple-style design rules.repo-mapRanked symbol map of a codebase within a token budget — a compact "what matters in this repo" before reading files.script-evaluatorEvaluate video scripts and presentations for flatness, tension, and emotional impact.video-narrative-arcProven narrative arc templates for product videos and ads. Use when: 'write script', 'video structure', 'narrative arc', 'scene plan', 'storyboard', '15 second…video-post-productionVideo post-production rules: audio mastering, color, captions, platform export.vlm-segmentationЭкспертный скилл по прикладной инженерии VLM, сегментационных моделей и диффузионных архитектур для GPU-деплоя.workflow-orchestrationНаписание и запуск Claude Code dynamic workflows (детерминированный JS-оркестратор субагентов, research preview 2026-05-28).