Aznatkoiny

Optimize, rewrite, or create prompts for Claude models. Use when the user wants to improve an existing prompt, turn a rough thought dump into a well-structured prompt, write a prompt from scratch, craft a Deep Research request, or tune a prompt for a specific…

Research-driven skill creation workflow. Guides you through intent capture, web research, prompt optimization, multi-agent deep research, and skill packaging — all grounded in real sources, not training data. Also invoked by plugin-forge's write-contract and…

Arm a forge eval suite into a frozen build contract. Run when .forge/state.json shows phase=evals, after /plugin-forge:build-evals; re-run after any suite edit or triage grader-error to re-version and re-freeze. Four gates in order via forge-eval: reference…

Generate a runnable eval suite (tasks, graders, judges, targets) for a Claude Code plugin BEFORE it is built. Use for "build evals", "eval suite for my plugin", "test my plugin", "retrofit evals", "mine traces into tasks". In the forge pipeline this is the…

Launch the isolated build-until-green loop for a forge project. Run when .forge/state.json shows phase=armed, after /plugin-forge:arm-evals. Walks the preconditions checklist (trust dialog, hooks enabled, MCP OAuth preflight for live servers, worktree base…

Build a new Claude Code plugin eval-first — interview, design contract, frozen eval suite, headless goal-loop build, verified ship. Use for "build me a plugin", "plugin for X", "forge a plugin", "resume forge", "forge status". Single entry point for the…

House style for every file plugin-forge emits into a generated plugin. Load before writing or reviewing any generated SKILL.md, agent, hooks.json, hook script, .mcp.json, plugin manifest, marketplace entry, README, or settings snippet — and before ship runs…

Decision cards for selecting Claude Code primitives while designing a plugin - skill vs hook vs subagent vs agent team vs MCP server vs bundled script vs LSP vs workflow vs loop. Load during any plugin architecture or composition discussion, when writing a…

Optimize prompts for Claude's latest models (Claude 5 family — Opus 5, Sonnet 5, Fable 5 — plus the still-active Opus 4.8, Sonnet 4.6, and Haiku 4.5) using Anthropic's official prompt-engineering guidance. Use when users want to improve, refine, debug, or…

Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: - Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) - Creating custom Gymnasium environments - Training, debugging, or evaluating RL…

Conversational skill that interviews the user to capture professional experience and build/update their career-profile.json. Use when the user says "update my resume", "add my recent experience", "refresh my profile", "capture my work history", "build my…

Core consulting thinking frameworks and methodologies for structuring business problems, communicating findings, analyzing strategy, building financial models, and designing operations. Use when any agent or command needs to apply MECE decomposition, pyramid…

End-to-end real estate investment analysis skill. Use when users ask to analyze a property deal, run the numbers on a rental, evaluate real estate investments, build a pro forma, compare markets, calculate cap rate, cash-on-cash return, IRR, NOI, DSCR, equity…

C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: - Implementing RL algorithms in C++ for performance-critical applications - Building production RL systems with libtorch - Creating replay buffers…

Comprehensive guide for Deep Learning with Keras 3 (Multi-Backend: JAX, TensorFlow, PyTorch). Use when building neural networks, CNNs for computer vision, RNNs/Transformers for NLP, time series forecasting, or generative models (VAEs, GANs). Covers model…

Set up, install, configure, and deploy OpenClaw (formerly ClawdBot/MoltBot) — a personal AI assistant that runs on your own devices and connects to messaging channels. Use when users ask to "set up OpenClaw," "install ClawdBot," "install MoltBot," "deploy a…

Use an External Brain Obsidian vault with an AI agent. Apply when the user wants to capture a thought, ingest an academic PDF, query relationships, or maintain the vault; do not use for unrelated repositories or ordinary file editing.

Capture a user's personal observation, idea, reflection, hypothesis, or explicit request to remember something in the External Brain vault. Do not use for incidental operational conversation or external documents.

Ingest, compare, or integrate an academic PDF into the External Brain vault with immutable source handling, page-level citations, atomic claims, and cross-paper links. Use for papers and PDF-based research, not ordinary Markdown articles.

Inspect, lint, organize, deduplicate, or repair the External Brain vault. Use for broken links, orphan notes, stale pages, duplicate concepts, provenance gaps, and semantic review; not for ordinary capture or paper ingestion.

Answer questions from the External Brain vault, including comparisons and relationships across papers, with traceable evidence. Use when the user asks what the vault knows; do not use merely to capture new material.

Choose the right deep-learning architecture, loss/activation pairing, and evaluation protocol for a described ML problem (images, text, timeseries, tabular, sequences); produces MODEL_PLAN.md plus starter Keras code, grounded in Deep Learning with Python 2E's…

Clean and reshape CSV/TSV files: fix delimiters and encodings, normalize headers, deduplicate rows, and pivot tables. Use when the user needs a messy spreadsheet or CSV cleaned up or reshaped. Not for modeling or statistics.

Capture, organize, and search meeting notes and decision logs. Use when the user wants to jot a note, find past decisions, summarize a meeting thread, or maintain a running decision log for a project. Not for code or data work.

Draft changelogs and release notes from commit history, bump versions, and prepare tag messages. Use when the user is cutting a release, writing a changelog, or preparing release communications.

Audit repository hygiene: license headers, dependency freshness, CODEOWNERS coverage, and stale branches. Use when the user asks for a repo audit, license check, dependency report, or branch cleanup plan.

A deliberately insensitive baseline for the evaluator.

Convert coding requests into concrete, repository-specific execution prompts.

Turn a rough or vague request to Codex into a precise, repo-grounded, high-performing prompt. Use when the user wants help phrasing, drafting, improving, optimizing, tightening, or "making better" a prompt/request/instruction for Codex; when the user pastes a…

Turn a rough or vague request to Claude Code into a precise, repo-grounded, high-performing prompt. Use when the user wants help phrasing, drafting, improving, optimizing, tightening, or "making better" a prompt/request/instruction for Claude Code; when the…