KazusaAIChatbot

Pull read-only diagnostic data from the Kazusa MongoDB database into JSON files. Use this skill whenever the user asks to export, inspect, dump, pull, or retrieve chat history, user profiles, user image, persistent user memories, shared memory, character state, or arbitrary MongoDB collection rows from this repo. Prefer the bundled project scripts and .env settings over ad hoc database queries.

Create human-readable quality evaluation artifacts for LLM debug, prompt testing, prompt comparison, model routing, RAG/cognition/consolidation/debug-channel behavior, and regression review. Use whenever a task asks to test, debug, inspect, evaluate, compare, or validate LLM output quality; when running live/local LLM calls; when changing prompts; or when reviewing possible LLM regressions.

Retrieve and review protected Kazusa LLM trace evidence for generated dialog, starting from visible dialog text, message identifiers, delivery tracking ids, or trace ids.

Use when planning, modifying, debugging, testing, or validating the Kazusa web control console frontend, including static HTML/CSS/JS pages, FastAPI control-console routes, cognition/prompt debug views, UI placement, Playwright or browser validation, screenshot signoff, stale Chrome in-memory JavaScript/cache issues, and control-console framework rules.

Write, refactor, and run tests in this repo using the project testing contract. Use this skill whenever adding or changing pytest tests, refactoring test style, deciding between real LLM tests and patched unit tests, testing graph/subgraph behavior, or running tests. It covers both how tests should be written and how regular versus real LLM tests must be executed and inspected.

Use this skill whenever the user asks architectural questions about LLM systems, especially prompt design, agent/subagent responsibility boundaries, routing, retrieval planning, tool/capability design, reliability, latency, or how to divide work between an initializer/planner and specialized agents. This skill is particularly important for this repo because the target runtime uses a local/weaker LLM with finite context and chatbot latency constraints; invoke it even when the user does not explicitly mention local LLMs. When modifying an existing LLM pipeline, use this skill to audit existing contracts and minimize blast radius before editing.

Enforce and review Python coding style for this project. PEP 8 is the baseline, with the project's explicit positive and negative constraints applied on top. Use this skill whenever you are writing new Python code, reviewing existing Python files, or responding to feedback about code quality. Trigger on any task that involves creating or modifying .py files, reviewing a function or class, or when the user asks about code style, best practices, or refactoring. Always apply these rules proactively -- don't wait for the user to ask.

Use when a user pastes visual_directives or asks Codex to generate a character image, seed image, visual-agent image, or character illustration from local metadata such as seed_reference_manifest.json.

Maintain Kazusa's curated shared/world/common-sense memory knowledge base. Use this skill whenever the user asks to add, collect, edit, search, remove, deduplicate, sync, upload, or inspect world knowledge, common sense, local slang, character-world facts, or durable curated entries for the MongoDB memory collection. Prefer the local JSONL source and maintenance CLI over ad hoc MongoDB edits.

Evaluate a chatbot character's real behavior in a simulated live environment. Use this skill whenever the user asks to test, audit, inspect, probe, or run multi-turn character conversations through the debug channel or production service, especially when they want per-turn log inspection, RAG/memory/cognition analysis, real database effects, or adaptive dialog based on the character's response. This skill should trigger even if the user says "simulate", "debug channel", "real life response", "behavior audit", "inspect her/his behavior", or asks for a series of conversations with a character.

Enforce safe handling of CJK characters — especially Chinese/Japanese quotation marks — when writing or editing Python source files. Apply whenever writing a .py file that contains CJK string content, or whenever a Python file with CJK content is being created, moved, or refactored. Trigger immediately if a Write tool call would produce a file containing CJK typographic quotes inside Python string literals delimited by ASCII double quotes.

Preserve an LLM-first architecture for user-input interpretation. Use this skill whenever you are designing, reviewing, or modifying code that decides whether user instructions, preferences, permissions, accepted commands, or commitments should be persisted or acted on. Trigger especially when you see deterministic pre-processing or post-processing over user input, acceptance gating added after an LLM call, local keyword classification of user-directed rules, or code that rewrites LLM decisions into a different channel. Prefer prompting, schema design, and clearer LLM output contracts over hardcoded filters.

Create detailed character JSON profiles for the Kazusa AI chatbot. Use this skill whenever you need to design a new character, adapt an existing character from external sources (like anime/game wikis), fine-tune character parameters, or validate character definitions. The skill covers all aspects of character creation: basic demographics, personality framework (MBTI, speech patterns), boundary profiles (emotional response patterns), and linguistic texture (speech nuances). Include both conceptual guidance and numerical scale specifications for all parameters.