Coding & Dev Tools

reaperinvest Skill

Writes fundraising appeal letters with storytelling, impact data, donation asks, and follow-up sequences.

reaperinvest Skill

Creates independent contractor agreements with scope, payment, IP ownership, and non-compete clauses. Use when hiring freelancers or contractors for your business.

mwmwcreate Bundle

このリポジトリの guide.md にもとづいて、Claudeが聞き手になって半構造化インタビューを行い、逐語録と記録を作る。開始時に説明と同意を確認し、必ず聞くことを通したうえで、答えに応じて具体的な場面を掘り下げる。終わったあとは引用が原文と一致するかを機械的に照合し、本人に確認してもらってから研究者へ渡す。「インタビューを始めて」「インタビューを受けます」「調査に協力します」「話を聞いてください」「interview」などで起動する。

ccsang Bundle

YouTube 字幕下载工具。支持多语言字幕获取、SRT/JSON/TXT 格式输出，自动回退至 Gemini 音频转写和翻译。

ccsang Bundle

Detect if text is AI-generated using matrix.tencent.com

binglin-wu Skill

将中文描述转化为符合顶级会议规范的英文表标题。当用户需要为论文表格撰写Caption时使用，特别适用于NeurIPS、ICLR、ICML等会议的Table Caption。

binglin-wu Skill

对英文学术文本进行微幅缩减，在保留所有核心信息的前提下压缩文本长度。当用户需要精简论文内容、减少字数时使用，特别适用于满足会议页数限制或精简冗余表达。

binglin-wu Skill

将中文描述转化为符合顶级会议规范的英文图标题。当用户需要为论文插图撰写Caption时使用，特别适用于NeurIPS、ICLR、ICML等会议的Figure Caption。

binglin-wu Skill

对英文LaTeX论文片段进行深度润色与重写，全面提升学术严谨性、清晰度与可读性。当用户需要提升英文论文语言质量、准备顶级会议投稿时使用，特别适用于NeurIPS、ICLR、ICML等会议。

binglin-wu Skill

根据论文方法描述设计并生成专业的学术架构图。当用户需要为论文绘制方法架构图、系统框架图时使用，特别适用于CVPR、NeurIPS、ICLR等顶级会议的论文插图。

binglin-wu Skill

从实验数据中挖掘关键特征、趋势和对比结论，撰写符合顶级会议标准的实验分析段落。当用户需要撰写实验分析、Results章节时使用，特别适用于NeurIPS、ICLR、ICML等会议的实验部分。

binglin-wu Skill

根据实验数据推荐最佳学术图表类型。当用户不确定如何可视化实验结果、需要选择合适图表类型时使用，特别适用于Nature、Science、CVPR、NeurIPS等期刊会议的实验结果展示。

7kim Bundle

Brainstorm a topic to generate Python class skeletons with real-world functions. Use this skill whenever a user wants to design a class structure, architect an object-oriented system, or generate Python skeleton code with attributes and methods. Trigger on phrases like "generate a skeleton for X", "create a class structure", "design this as a class", "let's brainstorm X", or any request to turn a concept into Python code with getter/setter methods and business logic functions.

7kim Bundle

Checks a GitHub user's repos and syncs their profile README (the special same-name-as-username repo shown on their GitHub profile page) — updates the repo-count badge and drafts Featured Project entries for repos that aren't covered yet. Use this whenever the user asks to "update my GitHub overview/profile page", "sync my README with my repos", "check if my profile README is out of date", or asks for a recurring/weekly GitHub profile refresh. Works in Claude Code (can open a PR) and in claude.ai chat (read-only preview of the diff).

awake118 Bundle

下载抖音（Douyin）视频与图集。当用户给出抖音分享链接（v.douyin.com/xxx、www.douyin.com/video/<id>、www.douyin.com/note/<id>）并要求保存、下载、备份视频，或抱怨抖音下载器解析失败、画质只有标清、需要登录才能看高清时使用。通过真实 Chrome + DevTools Protocol 读取播放器真实直链，绕过抖音对无 Cookie 请求的 JS-VMP 反爬与验证码中间页。

mk-joshuajallen Skill

Pull the latest changes for cloned M-KOPA repos, optionally filtered by keyword. Use when the user wants to refresh, pull, or update local repos before investigating something, or asks whether local code is current. Triggers on "refresh repos", "pull latest", "update the repos", "is my local code current".

ccsang Bundle

Search for YouTube videos and get playback URLs.

ccsang Bundle

Learn and imitate writing styles from URLs or text files. Support continuous learning from multiple sources.

maybackcompany Skill

OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".

maybackcompany Skill

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". (gstack)

talhamah56 Bundle

Teach the user a new skill or concept, within this workspace.

talhamah56 Skill

Use to map an existing (brownfield) codebase and produce docs/architecture/assessment.md — stack, architecture, implicit bounded contexts, maturity across the 5 axes, debts/risks, and historical decisions to become retroactive ADRs. Re-running updates the assessment. Runs standalone when the codebase changes or to analyze an unfamiliar repo. Trigger with /mapear.

talhamah56 Skill

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

talhamah56 Skill

Use for a GRILLING SESSION — a relentless interview that turns diffuse intent into shared understanding before building. It walks the decision tree ONE question at a time, resolving dependencies between choices, always with a recommended answer; it explores the codebase/docs instead of asking when the answer already exists. Ideal at the spec gate (testable ACs / Definition of Ready) and the design gate (hard-to-reverse decision). It produces an understanding summary that feeds product.md/design.md/spec.md. Trigger directly with /clarificar.

talhamah56 Skill

Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.

talhamah56 Bundle

Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

maybackcompany Bundle

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)

talhamah56 Skill

Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.

talhamah56 Skill

Get a patent-examiner-perspective review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.

maybackcompany Bundle

Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

maybackcompany Skill

Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version". Voice triggers (speech-to-text aliases): "upgrade the tools", "update the tools", "gee stack upgrade", "g stack upgrade".

maybackcompany Skill

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation. (gstack) Voice triggers (speech-to-text aliases): "tech review", "technical review", "plan engineering review".

maybackcompany Bundle

Compress natural language memory files (AGENTS.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress FILEPATH or "compress memory file"

talhamah56 Skill

Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.

talhamah56 Skill

Use to propose and generate the project's agentic layer — rules (CLAUDE.md, settings.json), subagents (.claude/agents), skills (.claude/skills), and workflows/CI — tuned to the stack, tools, process, and domain. Proposes with justification and generates only what is approved. Runs standalone as the project evolves or new tools arrive. Trigger with /camada-agentica.

talhamah56 Skill

Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.