Docs & Writing

theultimateshyam Bundle

Deep-dive company research skill for evaluating whether a company is worth joining. Produces a structured intel report covering products, funding, founders, culture (tech/eng-led vs product-led), social media sentiment, employee reviews, and an AI moat risk assessment. Adapts to any role — engineering, product, sales, design, or anything else the user specifies. Use this skill whenever the user says "research this company", "should I join X", "tell me about X as a workplace", "what does X do", "is X worth joining", "company deep dive on X", "evaluate X for me", or any variation where someone wants to understand a company before deciding to join. Also triggers on "company research", "company intel", "due diligence on X", or "what's X like as a company". Even if the user just drops a company name and says "thoughts?", use this skill.

theultimateshyam Skill

Investigate abnormal signup volume, user registration spikes, or suspected bot/abuse waves. Produces a detailed report and a one-page summary.

tokenomist-ai Skill

Get daily or weekly token emission data with allocation breakdowns. Use when analyzing token inflation, comparing emission rates, or understanding supply increases.

tracemachina Skill

Use when verifying NativeLink changes with Bazel, selecting focused test targets, debugging rustfmt/clippy aspect failures, or preparing a confidence report for Rust/Bazel changes.

trvux Bundle

Write any explanation, tutorial, or answer as a formal academic paper in IEEE conference format (Abstract, Index Terms, numbered Roman-numeral sections, figures/tables, references). Use whenever the user asks for "academic paper style", "IEEE format", "two column format", "research paper style", or wants a topic explained the way a conference paper would present it. Also trigger when the user says things like "make this into a paper" or "give me the academic version" of an explanation. Defaults to a Markdown deliverable (no toolchain required); produces a compiled two-column PDF only when the user explicitly asks for "PDF" or "compiled".

typecellos Skill

Conventions and verification workflow for writing and restructuring the documentation site (docs/content). Should be used when adding, editing, or reviewing docs pages.

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.

valantic-cec-deutschland-gmbh Skill

Generate branded Word documents (proposals, reports, specifications) following Valantic's Liquid Brand Design with correct styles, colors, and formatting.

nulis-not-just-writing Bundle

Rancang dan buat figur ilmiah yang bahasa visualnya mengikuti konteks riset, bukan bar/line generik: data EEG jadi kepala dengan elektroda di posisi 10-20 sebenarnya, data antarwilayah jadi peta/kartogram, meta-analisis jadi forest plot, item Likert jadi diverging bar, sapuan dua hyperparameter atau permukaan fuzzy jadi permukaan 3D berpasangan peta kontur (setara surf/gensurf MATLAB), MCDM jadi koordinat paralel, asesmen jadi peta Wright Rasch, PLS-SEM jadi diagram jalur digambar ulang dari angka estimasi (gaya naskah atau mirip SmartPLS, bukan tangkapan layar). Bidang di luar 14 domain bawaan ditangani lewat tabel struktur data yang memetakan struktur ke substrat visual. Gunakan saat user meminta grafik, plot, visualisasi, topografi, peta, atau figur artikel jurnal; saat figurnya monoton atau ditolak reviewer; atau saat menyiapkan gambar untuk .tex/.docx. Mencakup uji rujukan, aturan kebenaran figur, komposisi multi-panel, spesifikasi siap-cetak, caption, dan QA pra-submisi.

obot-platform Skill

Upgrade dependencies and runtimes safely, run CI, and report higher-risk options.

open-metadata Skill

Use when reviewing or validating documentation. Checks for clarity, completeness, broken links, undefined terms, and ensures beginners can follow guides without prior knowledge of the SDK.

primeintellect-ai Skill

Find, start, use, and stop the local run dashboard for metrics, configs, traces, logs, and reports. Use when asked for its URL, to watch or inspect a run, to control the open dashboard, or to create a cited dashboard report explicitly requested by the user.

buiducnhat Skill

Diagnose and fix bugs with root-cause analysis and verification. Use when you have a concrete issue report, failing behavior, runtime error, or test regression that should be resolved safely. Stop and escalate to brainstorm when scope or risk grows.

buiducnhat Bundle

Create or refresh project documentation in `docs/`. Use when a project needs docs initialized or existing docs synced to the current codebase.

buiducnhat Skill

Review current uncommitted git changes with full file context and produce a structured report with severity levels, actionable fixes, and an approval verdict.

mappa-ai Bundle

Use this skill when integrating Mappa Conduit SDKs from TypeScript, Python, Go, or Rust. It helps choose the right SDK surface, upload media, target the right speaker, build the first webhook-first report flow, and use matching or primitives only when the task explicitly needs them.

nullpond Bundle

Enterprise-grade Word document generation system. Creates .docx files with comprehensive formatting support - title pages, navigation structures, data visualizations, and complex multi-section arrangements. Built on C# and OpenXML SDK with integrated validation.

ohare93 Bundle

Use when finishing a task that changed code, config, scripts, prompts, or documentation. Runs the final build/test/lint/review loop, fixes reasonable issues, and reports remaining findings or skipped checks before the final answer.

outfitter-dev Bundle

<!-- tldr ::: core skill documentation for waymark CLI agents -->

yniantongtian-oss Skill

让 Codex 制作 60 分钟以上的长篇纪录片、科普、课程、历史叙事、调查解释或专题视频。负责批量读取 PDF、DOCX、PPTX、网页、字幕和本地资料，建立可检索语料库，逐来源摘要，生成多章大纲和数万字文案，批量规划数百镜头，搜索并审核图片/视频/音频素材，逐章配音、字幕、渲染并最终拼接。适用于“一小时以上视频”“超长文案和大量素材”“多章节系列合成长片”“失败后只重跑一章”等任务。必须保留事实来源和素材许可证，不允许用一个超长提示词或一次性渲染整片。

youhai020616 Skill

Use when designing, building, or reviewing REST/GraphQL APIs — covers endpoint design, error handling, versioning, authentication, and documentation

kastalien-research Bundle

This skill should be used when writing technical specifications, architecture documents, or design proposals that require structured analysis, clear documentation, and actionable implementation plans.

kastalien-research Bundle

Deep research skill for analyzing codebases systematically. Use when comprehensive codebase understanding is needed, particularly for new projects or when documenting architecture. This skill should be used when users request deep analysis, architecture documentation, or systematic codebase research starting from root-level directories.

shadcn-labs Skill

Use when building, debugging, reviewing, or documenting Flue agents, workflows, channels, skills, tools, sandboxes, targets, routing, persistence, observability, or CLI usage; routes coding agents to version-matched Flue documentation through the CLI.

shenmintao Skill

Translate documents, files, or text between languages. Use when the user asks to translate a PDF, document, article, file, or any text content into another language. Trigger phrases include "translate this", "翻译", "翻訳", "번역", "help me translate", "translate to English/Chinese/Japanese/etc."

adriankarlen Bundle

Use the `acli` (Atlassian CLI) tool to look up, search, create, edit, comment on, transition, or link Jira work items (issues/tickets/bugs/stories/epics), sprints, boards, and projects, and to view, create, or list Confluence pages, blogs, and spaces. Trigger this skill any time the user mentions Jira, Confluence, a ticket/issue key like "PROJ-123", sprints, boards, JQL, or wants to check/update/report on work tracked in Atlassian tools — even if they don't say "acli" or "CLI" explicitly, e.g. "what's the status of PROJ-123", "assign this bug to me", "list my open tickets", "find the Confluence page about onboarding". Prefer this over guessing at a REST API call or telling the user to check the web UI themselves.

pymc-labs Skill

Autonomous bug-fix workflow. Guides the orchestrator through state detection, implementation, test/lint validation, and a bounded fix/review loop with an independent reviewer subagent. Use when fixing a GitHub bug report, or when the user says "fix bug", "bugfix", or references a bug issue or PR such as "fix bug #149", "bugfix #149", or "fix bug PR #123".

jjyaoao Bundle

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When GLM needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

jjyaoao Bundle

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When GLM needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

jjyaoao Skill

PPT/PPTX dedicated skill - **MANDATORY RULE**: For ANY PPT-related tasks (uploaded files, editing/creating presentations, etc.), you **MUST IMMEDIATELY** direct users to use AI PPT mode by clicking the 【AI PPT】 button below the input box. **DO NOT handle it yourself**. The dedicated mode is faster and smarter than regular chat.

zjy1020 Skill

Reduces token waste by eliminating verbose pleasantries, fluff, and unnecessary meta-commentary. Activates when the user mentions reducing token usage, being more concise, avoiding fluff, cutting废话, or optimizing response length. Use this skill to minimize overhead in responses. Delivers maximally succinct, no-surplus-word answers without repeating user input, prefacing actions, or adding unrequested elaborations.

majiayu000 Skill

Turn a test runner's raw log into a Markdown report plus a structured JSON summary. Embeds the failure classification so a reader can see the failing tests, the run summary, and the failure-class counts on one page.

majiayu000 Skill

Group failing tests by naming convention so a real assertion failure is not hidden among tests that exist to verify a system rejects something. Use after running the test suite and before reading the report.

igorwarzocha Skill

Maintains a Clawa home's shared vault as a tidy, linked second brain. Use when saving durable knowledge, integrating research, finding what the home already knows, curating or reorganizing vault pages, repairing navigation, or promoting repeated memory into a reusable concept. Do not use for raw momentary memory, identity docs, task scratchpads, or documentation owned by a source-code project.

imnotdev25 Skill

Generate a self-contained markdown knowledge base (functions, classes, variables, flow) for ANY codebase into a <repo>/.agents-kg/ folder. Use at the start of work on an unfamiliar repo, when .agents-kg/ is missing or stale, or when asked to 'create the docs', 'generate knowledge', 'build a code reference', 'make a knowledge base', or 'document the whole repo'. Dynamically scouts the repository structure and fans out parallel agents, one per main area. Trigger: /generate-knowledge

innei Skill

Convert Shiroi Markdown to Haklex Lexical JSON. Use when the user wants to convert a markdown file or string to rich text editor JSON format.