Writing AI Skills

Guide for authoring user-defined custom UnitySkills skills inside your own Unity project - a [UnitySkill] C# method plus the conventions that let agents and the server discover and gate it

Diagnostic guide for RL-based post-training of language models (GRPO, PPO, REINFORCE, DPO). Use proactively when debugging a training pipeline that shows no improvement, loss anomalies, reward…

Korean and French screenwriting practice (韩国/法国编剧方法) — from the international masterclass; Oh Seung-uk (Christmas in August, The Shameless; field research in disguise, "write the emotion", first act…

Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from…

Use when deciding whether an OpenMeld change needs a Changelog entry, writing or publishing an entry, preparing release notes, validating Changelog projections, or historically backfilling missing…

Write a tight, retention-focused YouTube script from a topic, outline, or research brief. Use when the user asks for a video script, wants to turn notes or research into a YouTube video, needs a…

Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx…

Write domain-authentic review articles that synthesize rather than stack. Covers 10 scientific domains (physics, chemistry, biology, medicine, mathematics, computer_science, earth_environment,…

MANDATORY for every coding agent (Claude Code, Codex, or any other) on every change-set — every applicable source file the agent creates or updates MUST start with the project's copyright/authorship…

Creating and using feature flags in sidecar for gating experimental functionality. Covers flag registration, checking flags in code, config file and CLI overrides, and priority resolution. Use when…

Load when authoring, writing, or designing a Kotlin Toolchain local plugin to extend the declarative build with code generation, build-time processing, custom verification, or packaging that…

Create or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill, improving trigger descriptions, or deciding what belongs in a skill versus references,…

Route any website you need to visit through markdown.new by prefixing the URL. **WHEN TO USE:** - You would normally open a website link to read content (docs, blog posts, changelogs, GitHub issues,…

Author a Wisp custom theme CSS file that uses documented tokens and import constraints. Use when the user wants a custom look, hide the paragraph lead bar, restyle chat Markdown, override colors, or…

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Best practices and domain knowledge for building videos programmatically with Remotion (videos in React/TypeScript, rendered to MP4). Use whenever writing or editing Remotion code — scaffolding a…

Build advanced procedural animation in Three.js. Use for launch kinematics, gravity turns, staging, spin docking, target-frame decomposition, spring-follow motion, rotating-frame alignment, peeling…

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my…

Always-on guidance for solving tasks resourcefully. Teaches agents to escalate through skills, CLI tools, and custom scripts instead of refusing. Applies to any request where the agent lacks a…

Independently research and write an AI-narrative / due-diligence card for a crypto token — the kind of "叙事分析" card that covers what story a token is telling and what's independently verifiable about…

网文语言与文风光谱。当用户需要调整文风、选择叙述视角、运用修辞技法、植入玩梗、增强画面感时触发。覆盖白描/华丽/口语化/文艺/中二/翻译腔/新媒体风等文风类型，以及特写/慢镜头/蒙太奇/空镜头/长镜头等画面感技术。

Refresh and improve existing blog posts to outrank competitors using a 6-phase content audit and SERP gap analysis. Use when the user wants to update, refresh, or improve an existing blog post,…

This skill should be used only when the user explicitly asks to use `$ralph-specum-feedback`, or explicitly asks Ralph Specum in Codex to draft or submit feedback.

Use when building any webhook-triggered workflow, scheduled/production-bound workflow, wiring a per-node error output, or any workflow where silent failure would drop user-visible work. Triggers on…

Teach an unfamiliar topic from first principles with a picture-first HTML explanation, saved in Grain when connected. Use for "explain from scratch," "I'm lost," "what does this mean?", "explain in…

Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for…

Load when a story needs factual grounding the writer doesn't have: historical detail, cultural texture, domain accuracy, or how other authors handled similar material. Pass the question and story…

USE THIS when asked to work on a new or existing (MOBILE) CDS React component in packages/mobile

Typst paper assistant for existing .typ manuscripts in English or Chinese. Use for compile/export diagnosis, venue formatting, BibTeX/Hayagriva checks, grammar, logic, abstract/title, tables,…

Diagnose GitHub bug reports in openai/codex. Use when given a GitHub issue URL from openai/codex and asked to decide next steps such as verifying against the repo, requesting more info, or explaining…

Use when writing Xiaohongshu post content body, creating engaging captions, developing brand voice, or writing product descriptions and recommendations

Hand a 1C change to a human instead of editing sources: manual Configurator package («Найти» / «Заменить целиком на») or review diff. For vendor-locked, binary-form or MCP-only cases, or «ручное…

Archive or clean up facts from active MEMORY.md into memory-archive/ without deleting them. Use when the user wants to forget, remove, tidy old memory, or free space for new memories.

Interact with Google Chat - send, read, edit, delete and react to messages, share images and files, reply in threads, and manage spaces and DMs. Use when user asks to: send a message on Google Chat,…

用"孙学"风格写作：极度克制的白描叙事，短句节奏，数字锚定，物件承载情感， 沉默即高潮。适用于第一人称非虚构叙事、个人经历长文、情感故事、回忆录、 纪实散文、人物特写。当用户要求"孙哥风格""孙学写法""冷叙事""白描长文" "克制的情感表达""不煽情的故事""冰山写法""像《我的女友景甜》那样写"时使用此技能。 也适用于用户要求写出"不像 AI""有人味""高级感""文学性"的中文叙事长文。…

Review IEEE conference, journal, Transactions, Letters, or magazine manuscripts from a technical reviewer perspective using routed IEEE review gates. Use when evaluating scope fit, novelty, validity,…

This skill should be used when the user asks to "write a branching story", "interactive fiction", "choose your own adventure", "plan the branches", "choice graph", "add a choice", "gamebook", "Twine",…

Use when adding, editing or reviewing skills, role prompts or skill metadata.

Writes re-engagement emails to revive cold or lost leads. Use when the user asks to "re-engage", "reactivate", "closed-lost email", "win back", "reconnect with old leads", "ramp re-engagement",…

Create original short videos using the 空中群集｜近表面转向到稳定落地 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user wants this causal, camera, motion, rhythm, or payoff structure with new subjects…

Read an approved GRACE 4 GraceChangeSpec and optional design context, then create a GraceChangePlan with assertions, scopes, tasks, and verification gates.

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline…

Compare an existing selling point with product facts and competitor evidence. Use for “Could a competitor make the same claim?” Delivers a uniqueness comparison and evidence gaps for an existing claim

Investigate a specific test failure to its root cause and document the why. Detects whether a failing test is flaky (intermittent) or a deterministic bug during reproduction. Use when a test fails and…

Analyze Yuque documents to extract vocabulary, sentence, and tone patterns into a reusable writing-style profile. Use when the user wants to understand or reproduce their voice or keep documents…

Web search and content extraction via the Tavily API. Use when you need real-time web results, citations, or raw article content without a browser. Requires TAVILY_API_KEY.

Use when the user wants to turn one or more Entire-tracked sessions, checkpoints, or repeated agent workflows into a reusable agent skill.

Write, edit, or review UI copy, CLI messages, help text, code comments, and technical documentation covering product behavior, errors, status, setup, compatibility, or technical results.

Turn a brief, data, or desk research into a customer interview plan: research questions, screener, guide, and a note format. Use when someone is about to talk to customers and needs to decide who to…

Interview the user to decide what a skill's eval should test, then build the spec and iterate until the skill ships. Use when the user wants help designing a skill's eval, has a skill with no eval, or…