Docs & Writing

r3ze959 Bundle

Translate a complete PDF into Chinese while preserving its pages, figures, tables, and scientific meaning. Use for 翻译全文、整篇PDF翻译、保留版式导出中文PDF. For explanation or critique without translation, use a paper-analysis skill instead.

r3ze959 Bundle

Create a Chinese slide-by-slide literature presentation outline with source figures, concise slide copy, and speaker notes. Use for PPT大纲、组会文献汇报、配图讲稿 or converting papers and reading reports into a presentation plan; creating a finished PPTX is a separate requested deliverable.

r3ze959 Bundle

Explain and critically assess one academic paper, including its scientific argument, methods, figures, evidence, and limitations. Use for 单篇论文精读、全文解析、逐图讲解 or a focused question about a supplied paper; full-PDF translation and cross-paper synthesis are separate tasks.

rayekry777 Bundle

从 Java/Spring 等后端项目的 Controller 或等价路由层快速导出无状态接口索引，只记录 HTTP 方法、完整路径、处理方法、参数/返回类型名称、明确权限注解和源码位置。用于生成精简 JSON、YAML 或 Markdown 接口资料供其他项目导入；不展开 DTO、不追踪 Service、不判断业务是否完成、不推断未声明接口，也不判断前端实现状态。

wayne2wang Bundle

Turn any PDF slide deck and optional rough notes into a naturally taught narrated walkthrough through guided intake, Mac-voice script development, a two-slide ElevenLabs review, audio-aligned captions, and a synchronized player and video. Use for presentations, training, lectures, workshops, and other slide walkthroughs, with optional deployment.

zhiqingresearch Skill

根据当天或指定时间范围内的 git 提交记录，以及 Codex、Claude 聊天日志，生成简短工作日报；按实际参与的项目、系统或业务线分组，每个项目输出 1-5 条。当用户要求“生成日报”“根据今天提交写日报”“根据 Codex/Claude 记录写日报”“按项目/系统分组写日报”时必须使用。

anandamritraj Bundle

Use to review the output of any GOAL phase (a Goal Brief, a spec, a diff or PR, an eval report, a release plan, or telemetry) from four forward-deployed perspectives at once. Convenes a pod of four persona-agents (FD Product Manager, FD Tech Lead, FDE, FD Domain Expert/Business Owner), auto-selecting which lenses matter for the current phase (read from .goal/state.json), and returns one synthesized Pod Review with a verdict and a queue of proposed actions. The pod advises; the human decides and holds the gate. Use when the user asks for a pod review, a multi-perspective review, or to review a phase's work, and at GOAL phase gates.

angzeli Bundle

Document, prune, refactor, or review scientific code and Jupyter notebooks while preserving scientific, data, interface, execution-state, and artifact contracts. Use for evidence-backed comments, docstrings, notebook Markdown, units, shapes, schemas, ordering, missing-value conventions, assumptions, numerical choices, or readability work that must not change analysis semantics. Do not trigger for ordinary notebook execution, data analysis, debugging, performance work, methodology changes, output regeneration, dependency updates, or feature implementation.

angzeli Bundle

Grade codebase and scientific-computing tasks before execution to select the minimum sufficient inspection, patch scope, abstraction, validation, documentation, review, subagent, and commit effort. Use for code edits, bug fixes, repository audits, CI/build failures, bounded features, refactors, CLI or parser changes, notebook edits, migrations, releases, packaging, and scientific workflow changes. Do not use for pure conceptual Q&A, general explanations, prose or email writing, brainstorming, ordinary conversation, or requests that neither modify nor validate a codebase.

cdeistopened Skill

Create on-screen text hooks and captions for short-form video clips. Built around the Complementarity Principle - on-screen text should ADD to what the viewer hears, not repeat it. Includes podcast clip workflow, hook categories, and Triple Word Score optimization.

dobroslavradosavljevic Bundle

ALWAYS apply by default in every turn when writing to the user, naming code/files/folders/APIs/terms, explaining decisions, summarizing work, or teaching concepts. Enforces human-readable plain language and sensible names; avoid jargon, cryptic abbreviations, academic tone, and clever-but-unclear identifiers unless the user already uses that term or a precise technical word is truly required. Also use when the user says plain-language, plain language, simpler words, explain simply, less jargon, better names, or readable naming.

florian101010 Skill

End-to-end feature workflow with planning, implementation, QA, and documentation sync. Use when delivering a new feature or larger enhancement.

florian101010 Skill

Pre-release quality gate covering functional checks, baseline validation, and documentation integrity. Use before publishing a new version or tagging a release.

mehdi-benhariz Skill

Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing.

youliang-zhu Bundle

Interactively manage local project-interview archives and help candidates refine existing project narratives while preserving the candidate's own thinking and factual boundaries. Use when Codex needs to create or resume interview-project workspaces; work from user-provided descriptions, code, PPT/PPTX, PDF, papers, documents, or job descriptions; clarify a project; research a small number of highly relevant academic, open-source, or industry developments; fill knowledge gaps; prepare quick introductions, full project walkthroughs, deep-dive questions, or multi-project self-introductions; and run project interview rehearsals.

xiaohanzhao123 Skill

End-of-session documentation reconcile. Runs the Curator to propose a short ADD/RETIRE/PROMOTE list, waits for the human to accept or reject, then runs the Librarian to apply only the survivors. Invoke as /wrap when finishing a working session. User-invoked; never auto-run.

tyrchen Bundle

Vendor reference repos as git submodules under ./vendors and produce deep research memos under ./docs/research covering architecture, design, key data structures, and load-bearing algorithms. Use whenever the user says "do research on X", "study how Y works", "submodule this repo and look into it", "understand the design of Z before we start", "spike on …", references prior-art crates / repos that should be evaluated, or asks to refer to ./vendors before designing or implementing. Trigger even when the user does not say the word "research" if they paste GitHub URLs and ask Codex to learn from them, compare alternatives, or extract patterns.

werf Skill

Code review of a pull request, branch, or diff. Covers technical, product, and risk perspectives in one pass and produces a consolidated report. Use when asked to review a PR, branch, or code changes.

weihuo1988-svg Bundle

捕获、清理、结构化、分类并存储口述笔记或 Codex 移动端听写内容。用于用户口述语音笔记、要求记录口头想法、把中英文口述整理成项目笔记、将内容切片路由到合适项目文档、识别日程安排并创建手机提醒或写入 Markdown 日程账本，或从口述中提取身份、偏好、关系、重要日期、稳定目标、角色和工作上下文等长期记忆候选。

linuxchata Skill

Defines the coding standards, patterns, and conventions for ASP.NET Core REST API controllers. Rules cover routing, HTTP verbs, response types, XML documentation, dependency injection, and asynchronous execution. Apply these rules uniformly to ensure a consistent, predictable, and well-documented API surface.

cxijin6-cell Bundle

Use when the user asks for Markdown authoring, cleanup, conversion planning, structured notes, documentation formatting, or preserving readable Markdown output. Also use when the user writes markidown and appears to mean markdown.

dream-zjk Skill

Use when writing or improving documentation — READMEs, module docs, API references, runbooks, or tutorials.

heyeddi-com Bundle

Diagnose and fix failing GitHub Checks on PR work by default: fetch evidence, write ephemeral ci-fails report, apply fixes, verify locally. Run automatically — do not wait for user to ask. Never merge without authorize merge. Companion to /heyeddi fails.

linkupplatform Bundle

ONLY when the user explicitly wants a thorough, exhaustive, or comprehensive multi-source investigation or report that can run for minutes — due diligence, market landscapes, "compare X across many entities", verified fact-finding. ALSO read this when writing code that integrates the /v1/research endpoint (modes, reasoning depths, async polling). Slower and more expensive than linkup-search. For normal lookups and research use linkup-search instead; for bulk records from a page use linkup-extract. Uses Linkup's async /v1/research REST endpoint. Requires LINKUP_API_KEY.

mihaideyu Bundle

Generates weekly work reports from Yuque monthly logs. Use when the user asks to summarize this week's work, generate a weekly report, or similar prompts like "帮我总结下本周工作内容" or "帮我生成周报".

mihaideyu Bundle

Generates monthly work reports from Yuque "XX月工作" and/or workspace weekly MDs; four-part structure (业务、OBCloud易用性升级、OAgent、团队)；no invented facts; professional plain style. Use for 月报, monthly report, 生成本月/某月月报, 根据语雀月总结工作.

zephyr236 Bundle

Generate Chinese software copyright (软著) application materials — specification manual and source code document. Analyzes the project, draws SVG diagrams, and converts to formatted DOCX using academic template.

andydixon Bundle

Generate or update a repository SUMMARY.md that explains what a software project is, what it does, and how it evolved through Git history. Use when the user asks to summarise a codebase, create project history documentation, produce a v3-style management-readable technical narrative, analyse milestones from Git tags, or document significant commits and their product impact.

rpeeyush Bundle

Teach and coach users toward job-interview readiness through short explanations, worked examples, active recall, adaptive drills, and targeted feedback. Use when a user wants to learn an interview topic, improve weak answers, study from a job description or resume, practise STAR stories, turn an interview report into a study plan, or says things such as "teach me X for interviews", "help me learn this", "explain and quiz me", or "make me interview-ready".

s3644 Skill

Academic paper peer review simulator. Use when the user needs: review a paper, peer review, manuscript review, referee report, quick assessment, methodology check, guided review, re-review verification, or reviewer calibration against a gold set. Simulates multi-perspective review with 0-100 quality rubrics across 5 dimensions. Triggers: review paper, peer review, manuscript review, referee report, review my paper, critique paper, editorial review, calibrate reviewer, 審查論文, 同儕審查.

talaniz Skill

Use red-green-refactor cycles when implementing or changing executable behavior or fixing bugs. Also invoked as tdd. Apply repository-specific test and evidence requirements; do not invent failing tests for documentation-only changes.

viamagic333-lang Bundle

Generate and keep documentation in sync with source code. Produces README sections, API references, JSDoc/docstrings, and architecture overviews directly from the codebase. Use when the user asks to "document this code", "generate API docs", "write a README", "add docstrings", "describe the module", or when new code lands without docs. Also use proactively after non-trivial public API changes.

yaacovcorcos Bundle

Build and maintain clear company handbooks, knowledge bases, process docs, decision records, and onboarding docs. Use when creating, improving, auditing, or organizing internal company documentation, team operating knowledge, policies, or company wiki systems.

linuxfoundation Skill

Conduct an lfx-v2-member-service pull request to a clean state: reconcile the AI reviewers' threads against the latest commits and developer replies, work with the engineer on findings that go against the architecture, and report whether the change is clean. Use when the task is to check whether AI-review findings are fixed or validly rebutted and to update the agentic gate. Posts one machine-readable agentic-check comment plus a summary of open blockers.

sigmacomputing Bundle

Build, validate, retrieve, and safely update Sigma report code representations through /v2/reports. Use for fixed-layout or pixel-perfect reports, invoices, statements, regulatory documents, and PDF delivery. Covers report pages, absolute pixel layout, header/footer panels, common elements, verification, full-contents replacement, and workbook conversion to reports. Do not use for responsive dashboards; use sigma-workbooks instead. Requires SIGMA_API_TOKEN from the sigma-api skill.

lnscc Bundle

Keep created or edited code, documentation, skills, plans, configuration, messages, and other artifacts simple, efficient, and minimal. Use the smallest clear and complete result without sacrificing correctness, safety, requirements, or repository conventions.