InternScience/DrClaw

acpx

Use the ACPX CLI through DrClaw's existing exec/long_exec tools to run Codex in the current project workspace.

docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of…

align-target-style

Convert a user style request into concrete rewrite constraints and apply that style during de-flavoring. Use when the user specifies a target tone, audience, or writing persona.

detect-ai-patterns

Diagnose formulaic writing patterns and authorial gaps before rewriting. Use when text feels generic, over-smoothed, abstract, or structurally mechanical and you need a targeted edit plan.

preserve-meaning

Guard against meaning drift during de-flavor rewrites. Use when rewriting text to sound more natural without adding facts, changing claims, or losing important constraints.

rebuild-specificity

Rebuild specificity, texture, and authorial judgment in a rewrite without inventing facts. Use when text feels abstract, generic, over-smoothed, or full of empty framing.

clawhub

Search and install agent skills from ClawHub, the public skill registry.

cron

Schedule and manage recurring or one-time jobs for main/project agents.

failure-escalation

Terminate on unrecoverable external blockers and report precise error details.

local-skill-hub

Manage dormant local skill templates and attach them to project agents or equipment agents.

memory

Two-layer memory system with grep-based recall.

planner

A guideline for how to plan, split, assign tasks, and report back. Governs how the main agent triages user instructions, plans multi-agent work, splits plans into execution blocks, assigns blocks to project agents via route_to_project, tracks progress with…

ssh-long-session

Manage long-running remote SSH jobs through tmux and inspect their output safely.

today-paper-summary

Retrieves papers the user browsed today, downloads PDFs, generates summaries, and returns an enriched list. Use when the user asks what papers they read today, wants a summary of today's papers, or asks about their recent reading activity.

academic-deep-research

Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native…

arxiv-watcher

Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.

daily-paper-push-writing

A research/push notification writing guide. Use this skill with high priority when users ask you to perform tasks like daily paper push.

Source text: Chinese

daily-paper-push-writingwo-image

A research/push notification writing guide. Use this skill with high priority when users ask you to perform tasks like daily paper push.

Source text: Chinese

casual-gomoku

Play a chat-based 6x6 gomoku game. Render the board in text, accept coordinates like B3, alternate turns, and declare the winner when either side connects five in a row.

Source text: Chinese

casual-tarot-reading

Run a light, conversational tarot-style reading for fun. Offer one-card or three-card spreads, draw symbolic cards, interpret them in a playful but gentle way, and avoid deterministic or high-stakes claims.

Source text: Chinese

guess-word-yes-no

Run a yes-or-no word guessing game. Choose a common secret word, answer only with 是 or 否 for up to 15 rounds, and reveal the word after 15 questions or a correct guess.

Source text: Chinese

mini-rpg-adventure

Run a 15-turn lightweight chat RPG with a fixed three-act rhythm. Ask for scene, setting, identity, and difficulty; generate 100-200 Chinese characters per scene, track scene-specific resources, enforce checkpoints on turns 5 and 10, and end with a structured…

Source text: Chinese

office-survival-choices

Run a 15-turn office or lab survival choice game with mounting pressure. Explain the fail/pass conditions up front, trigger a pressure event every two turns, track energy, pressure, dignity, and inventory, and resolve survival on turn 15.

Source text: Chinese

solo-undercover

Run a single-player Who Is the Undercover style game. Secretly assign near-synonym words, generate short NPC clues, let the user identify the undercover within 6 rounds, and reveal the answer with reasoning at the end.

Source text: Chinese

turtle-soup-yes-no

Host a Haiguitang yes-or-no mystery game. Pick one soup base from the bundled soup bank, answer only with 是 or 否, track rounds, and reveal the answer after 15 questions or a correct guess.

Source text: Chinese

natural-conversation

Enables natural, human-like conversation without robotic patterns. Reduces AI-typical phrases, adds personality and warmth. Always active for human interactions.

Source text: Japanese

claude-code-skill

Control Claude Code via MCP protocol. Execute commands, read/write files, search code, and use all Claude Code tools programmatically with agent team support.

clawhub

Search and install agent skills from ClawHub, the public skill registry.

cron

Schedule and manage recurring or one-time jobs for main/project agents.

failure-escalation

Terminate on unrecoverable external blockers and report precise error details.

large-file-writes

Write large files in append chunks to avoid truncated tool-call arguments.

local-skill-hub

Manage dormant local skill templates and attach them to equipment agents.

memory

Two-layer memory system with grep-based recall.

meow

For any input, respond with a single meow.

multiomics-integration

Multi-Omics Integration - Integrate multi-omics: gene expression, protein data, pathway enrichment, and metabolic pathways. Use this skill for multi-omics tasks involving get gene expression across cancers get uniprotkb entry by accession get functional…

check-review-alignment

当用户明确要求"核查/优化综述 `{主题}_review.tex` 的正文引用"或"运行 check-review-alignment"时使用。通过宿主 AI 的语义理解逐条核查引用是否与文献内容吻合，只在发现致命性引用错误时对"包含引用的句子"做最小化改写，并复用 `systematic-literature-review` 的渲染脚本输出 PDF/Word。核心原则：不为了改而改，无法确定是否为致命性错误时保留原样并在报告中警告。⚠️ 不适用：用户只是想生成系统综述正文（应使用…

Source text: Chinese

complete-example

当用户明确要求"填充示例内容""生成示例""补充 LaTeX 示例"时使用。AI 增强版 LaTeX 示例智能生成器，实现 AI 与硬编码的有机融合：AI 做"语义理解"（分析章节主题、推理资源相关性、生成连贯叙述），硬编码做"结构保护"（格式验证、哈希校验、访问控制）。

Source text: Chinese

get-review-theme

当用户明确要求"从文件/图片/网页/描述中提取综述主题"或"生成主题+关键词+核心问题结构化输出"时使用。支持文件（PDF/Word/Markdown/Tex）、文件夹、图片、自然语言描述、网页 URL 等多种输入源，自动识别输入类型并提取内容，生成可直接用于 systematic-literature-review 及其他文献综述技能的结构化输出。

Source text: Chinese

guide-updater

当用户明确要求"更新项目指南""同步指南""沉淀洞见到指南"时使用。将对话中新产生的可复用写作洞见实时沉淀到项目指南文件，保持术语口径一致、结构稳定、可检验与可复现。调用时必须指定指南文件路径。

Source text: Chinese

make-latex-model

当用户明确要求"LaTeX 模板优化""样式参数对齐""make_latex_model"时使用。支持任意 LaTeX 模板的样式参数对齐、标题文字对齐、标题格式对比（加粗）、HTML 可视化报告、LaTeX 自动修复建议和像素级 PDF 对比验证。

Source text: Chinese