serge shima

Professional Claude Skills for AI image and video prompting. Supports Nano Banana (Gemini 3 Pro/Flash), GPT Image 2, Seedance 2.0, Kling 3.0 (multi-shot + native dialogue), Veo. Works with Claude Code, Cursor, Windsurf, OpenCode, Hermes-agent.

AI Creative Director skill for Claude, GPT, Gemini — 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER), Cannes-calibrated scoring, recursive refinement. Insight → Ideation → Evaluation → Presentation.

Skill для AI-агентов (Claude Code, Codex, OpenClaw, Hermes): убирает 37 признаков AI-генерации из русского текста и проверяет, писала ли его нейросеть - канцелярит, штампы ChatGPT, артефакты копипаста | Russian AI-text humanizer & detector skill for coding agents

Architecture-first skill lifecycle for AI agents. 5 modes: CREATE → EVAL → EDIT → REVIEW → PACKAGE. Integrates Anthropic's eval engine (grader/comparator/analyzer agents, blind A/B, benchmarks) with architecture patterns, TDD baseline, and 5-axis scoring. Not just testing - full design-to-distribution.

mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insights-style HTML report on how you work: what you build, where you lose time, and concrete fixes. An agent skill for Claude Code, Codex, and any skills-capable agent.

Deterministic code quality gate for AI coding agents (Claude Code, Codex, pi): git hooks that block test tampering, hold the CRAP bar on changed functions, check diff coverage, secrets and dependencies. 12 languages, one config file. Optional Jev classifier for test hunks.

Скилл для агентов: ежедневная газетная страница-дайджест на любую тему с публикацией по ссылке

Ordered idea-to-ship flow for agentic software development in Claude Code. No vibecode. 7w3 design, canonical spec, executable architecture, an honest cross-family review loop to convergence, production QA, safe deploy. Assembled by practitioners of the @aostrikov_agents_chat community; every source kept as is.