CHENyiru3

Maintain this specific academic website repo safely and consistently. Use this skill whenever the user asks to update, review, polish, reorganize, or extend this website, especially when the request touches homepage identity statements, publications, CV assets, shared templates, or duplicated academic content.

Delegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the claude CLI installed.

Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Complete guide to using and extending Hermes Agent — CLI usage, setup, configuration, spawning additional agents, gateway platforms, skills, voice, tools, profiles, and a concise contributor reference. Load this skill when helping users configure Hermes, troubleshoot issues, spawn agent instances, or make code contributions.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Delegate coding tasks to OpenCode CLI agent for feature implementation, refactoring, PR review, and long-running autonomous sessions. Requires the opencode CLI installed and authenticated.

Configure Zed editor settings, keybindings, agent profiles, and AI integrations. Use when modifying Zed configuration, setting up agent profiles such as plan mode, configuring language servers, themes, or AI models. Keywords: zed, editor, settings, keybindings, keymap, LSP, language server, theme, agent, configure, model, MiniMax.

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

Generate a custom checklist for the current feature based on user requirements.

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.

Create or refresh a current-understanding.md continuity report for a Bioinfo SDD feature or half-finished workflow by reviewing current specs, plans, tasks, section state, installed refs, selected packages/tools, wrappers, adapters, checks, evidence, and unresolved next steps.

Auto-commit changes after a BioKit command completes

Create a feature branch with sequential or timestamp numbering

Initialize a Git repository with an initial commit

Reusable minimal galgame driver policy for relationship scenes.

Reconciliation demo action skill for player dialogue.

Reconciliation demo action skill for movement and body language.

Reconciliation demo action skill for reflection and slight hints.

NPC behavior for 绫波丽 (Ayanami Rei) in the Rain at the Overpass fixture.

Rules and voice for the Rain at the Overpass galgame fixture.

Reusable driver policy for room-bound debate, jury, council, and committee dramas.

Game rules and voice for the Thirteen Angry Man deliberation cartridge.

Use the bundled skill tools (tools.json + tools_runner.py) for all structured operations; enforce role tool whitelist; JSON tool_calls only.

Use the bundled skill tools (tools.json + tools_runner.py) for all structured operations; enforce role tool whitelist; JSON tool_calls only.

Create and switch RPG campaigns by copying `campaigns/_template`, updating `ACTIVE.md`.

Author and update RPG content packs (cartridges lore/NPC/quests/locations) while keeping kernel protocols stable and avoiding plot-driven drift.

Convert session/event logs into fiction chapters without creating new canon; enforce State/Event truth and track continuity issues.

Maintain a stable governance panel (assets/followers/army/income/clocks) as a patch-friendly state file, triggered by manage/governance gameplay.

Run a filesystem-backed long-running RPG/DM session using HOT/WARM/COLD memory, short-code HUD, minimal RAG, and ARCHIVE_DELTA append/patch saves.

Create and switch RPG campaigns by copying `campaigns/_template`, updating `ACTIVE.md`.

Use this skill for ADS/ADS2 one-way ANOVA, two-way/factorial ANOVA, interaction effects, Tukey HSD post-hoc tests, ANOVA assumption checks, numeric response by categorical factors, tooth-growth vitamin C designs, and ANOVA power. Trigger on ANOVA, aov, Tukey, interaction, factorial, two-way, dose and treatment, supplement, or numeric outcome across groups.

Use this skill for ADS/ADS2 categorical data, chi-square goodness-of-fit, chi-square independence or homogeneity, Fisher exact test, Mendelian ratios, genotype/survival counts, satisfaction tables, expected counts, CrossTable usage, ordinal categorical choices, and categorical plots. Trigger on chi-square, chisq.test, Fisher, categorical, counts, contingency table, Mendelian, genotype, survival, satisfaction, homogeneity, independence, or goodness-of-fit.

Use this skill for ADS/ADS2 k-means clustering, neuron-type classification from numeric features, comparing clusters to known labels, elbow plots, adjusted Rand index, simple feature extraction from image-like matrices, MNIST-style row/column summaries, or classification feature preparation. Trigger on kmeans, k-means, clustering, neuron type, hap1, hap2, feature extraction, MNIST, pixels, classification, or cluster validation.

Use this skill as a final ADS/ADS2 exam answer review checklist. It catches common mistakes in data cleaning, test choice, paired designs, ANOVA interactions, chi-square expected counts, pwr sample-size formulas, regression wording, clustering interpretation, and report language. Trigger on review my ADS answer, check mistakes, before submission, common traps, is this correct, or final checklist.

Use this skill for ADS/ADS2 correlation, simple linear regression, multiple regression, regression assumptions, residual diagnostics, slope interpretation, R-squared, nested model comparison, interaction terms, VIF/multicollinearity, time-window/local regressions, and ICA trend modeling. Trigger on correlation, cor.test, regression, lm, slope, residuals, R-squared, model comparison, VIF, trend, predictor, or association.

Use this skill for ADS/ADS2 exam data import, checking, cleaning, reshaping, typo correction, missing values, duplicates, factor conversion, paired-data merging, or preparing data for R statistical tests. Trigger when the user says clean data, check NA, duplicates, typo, reshape long/wide, pivot, gather, merge before/after, or "import and organize the data".

Use this skill whenever the user is answering an ADS/ADS2 coding challenge, online problem-solving exam, or ICA-style RMarkdown report and needs the overall answer structure. Trigger on ADS exam, ADS2 exam, coding challenge, RMarkdown exam answer, ICA report, "how should I write the answer", or when multiple statistical tasks must be presented coherently.

Use this skill for ADS2 ICA or open-ended analysis reports, especially substance_use.csv, Global Burden of Disease data, filtering by measure/location/sex/age/cause/year, trend plots, age/sex comparisons, asking an original question, reproducible RMarkdown, and interpreting observational data. Trigger on ICA, group exercise, substance_use, open question, prevalence, deaths, opioid, alcohol, trend over time, or "ask your own question".

Run CodeBTI interviews to infer project and language coding-style preferences and generate project-specific CodeStyle.md, SKILL.md, or SPEC.md guidance.

End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. 会话结束后对项目文档和记忆进行洁癖级审查与同步。MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "同步一下", "整理文档", "整理一下", "更新记忆", "梳理一下", "收尾", "这个阶段做完了", "新人能直接上手", or any phrase suggesting a dev milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. Bare "整理" / "tidy" with prior dev context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.

会话结束后的知识库洁癖式收尾同步：把项目文档（README.md、docs/、CLAUDE.md、 AGENTS.md 等）和 agent 记忆拿代码逐项对齐，合并重复、删除过期、修正冲突，避免知识腐烂。 当用户说 "sync up"、"tidy up docs"、"update memory"、"clean up docs"、"/sync"、 "/neat"、"同步一下"、"整理文档"、"整理一下"、"更新记忆"、"梳理一下"、"收尾"、 "这个阶段做完了"、"新人能直接上手"，或任何表示开发阶段结束、文档需要对齐、 记忆冲突、交接给同事/其他 agent 的表达时必须触发。已有开发上下文里的裸 "整理" / "tidy" 也算触发，不要漏触发。适用于 Claude Code、OpenAI Codex、OpenCode、OpenClaw。

运行 CodeBTI 访谈，推断项目级和语言级编码风格偏好，并生成项目专属的 CodeStyle.md、SKILL.md 或 SPEC.md 指导。

Maintain the Yiru_study_in_zje / ZJE Collection MkDocs website safely and consistently. Use this skill whenever the user asks to update, review, polish, reorganize, or extend the ZJE study-materials site, especially for course pages, resource download routing, OneDrive/GitHub release logic, the resource manifest, generated package indexes, contribution instructions, or public layout clarity.

Maintain this specific Jekyll al-folio academic website repo safely and consistently. Use this skill whenever the user asks to update, review, polish, reorganize, or extend this website, especially when the request touches homepage identity statements, publications, CV assets, shared templates, Tech Blog, Life page galleries, Research Radar digests, or duplicated academic content.