Writing Skills

Operate on Unity Terrain — create TerrainData, sculpt heights, paint texture layers, and smooth/flatten regions. Use when creating or editing terrain, sculpting or smoothing the heightmap, or painting terrain texture layers, even if the user just says "地形" or "刷地面". 操作 Unity Terrain(创建 TerrainData、雕刻高度、绘制纹理层、平滑/压平区域);当用户要创建或编辑地形、雕刻或平滑高度图、或绘制地形纹理层时使用。

Source-anchored design rules for Cysharp UniTask 2.5.10 (Unity 2018.4+) — struct semantics, PlayerLoop timing, cancellation, composition, conversion, async enumerables, triggers, and pitfalls. Use when writing or reviewing async UniTask code, choosing PlayerLoopTiming, handling CancellationToken, or composing WhenAll/WhenAny, even if the user just says "异步" or "零分配async". 为 Cysharp UniTask 2.5.10(Unity 2018.4+)提供源码锚定的设计规则(struct 语义、PlayerLoop 时机、取消、组合、转换、异步流、触发器、陷阱);当用户要编写或审查 async UniTask 代码、选择 PlayerLoopTiming、处理 CancellationToken、或组合 WhenAll/WhenAny 时使用。

Manage the Universal Render Pipeline (URP) — URP assets, the renderer, and renderer features. Use when configuring the URP asset, adding or editing renderer features, or adjusting URP rendering settings, even if the user just says "URP配置" or "渲染特性". 管理通用渲染管线(URP:URP 资产、渲染器、渲染器特性);当用户要配置 URP 资产、添加或编辑渲染器特性、或调整 URP 渲染设置时使用。

Last-resort guidance for safely hand-editing Unity serialized YAML (.unity/.prefab/.asset/.meta/ProjectSettings) — reference/fileID repair, GUID safety, and merge-conflict fixes. Use when REST cannot reach the change and YAML must be hand-edited — fixing m_Script GUIDs, broken fileID references, .meta files, or merge conflicts, even if the user just says "场景文件打不开" or "引用丢了". 安全手编 Unity 序列化 YAML(.unity/.prefab/.asset/.meta/ProjectSettings)的最后手段(引用/fileID 修复、GUID 安全、合并冲突修复);当 REST 无法触达、必须手编 YAML 时使用——修复 m_Script GUID、断裂 fileID 引用、.meta 文件或合并冲突。

Source-anchored design rules for YooAsset v2.3.18 — initialization, default-package shortcuts, play modes, asset handles, loading, updates, filesystem, build, and pitfalls. Use when writing or reviewing YooAsset code, initializing packages, loading assets via handles, setting up hot-update/download, or choosing a play mode, even if the user just says "热更" or "资源包". 为 YooAsset v2.3.18 提供源码锚定的设计规则(初始化、默认包快捷方式、运行模式、资源句柄、加载、更新、文件系统、构建、陷阱);当用户要编写或审查 YooAsset 代码、初始化 package、用句柄加载资源、配置热更/下载、或选择运行模式时使用。

Draft a LaTeX research paper from all previous stage outputs

Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data management plan", "DMP", "DMSP", "NIH data sharing plan", "write the data plan for my grant", or when a grant proposal needs a data-management section. NOT a submission tool — produces a draft the user pastes into the funder portal (DMPTool, NIH ASSIST, Horizon Europe portal).

Read-only audit of `.tex`, `.qmd`, or `.md` text for AI-voice tells — boilerplate transitions ("Moreover", "Furthermore", "It is important to note that"), AI-cliché lexicon ("delve", "navigate the complexities", "tapestry", "robust framework"), em-dash overuse, symmetric paragraph shapes, tricolon abuse, hedging stacking, "not only X but also Y" frames, and formulaic openers. Produces a report; does NOT rewrite. Use when user says "humanize", "does this sound like AI?", "check for AI tells", "de-AI this draft", "remove AI voice", "audit my prose for sycophancy", or before journal submission / posting a working paper.

Read-only proofreading pass over lecture `.tex` or `.qmd` files. Checks grammar, typos, overflow, terminology consistency, and academic writing quality; produces a report without editing. Use when user says "proofread", "check for typos", "look for grammar issues", "copy-edit this", "any writing errors?", or before a lecture release.

Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the syllabus and slide decks. Use when user says "respond to my evals", "what do these course evaluations tell me", "turn my teaching feedback into a plan", or after a semester's evals arrive.

Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for a single lens, use `/visual-audit`, `/pedagogy-review`, or `/proofread` directly.

Translate a Beamer `.tex` lecture to a Quarto RevealJS `.qmd` mirror. Multi-phase: TikZ extraction → slide-by-slide translation → citation conversion → automatic QA parity check. Use when user says "translate to quarto", "port to revealjs", "make an html version", "convert this beamer to quarto", "mirror this lecture in qmd", or after a Beamer deck is ready for web publication. Output lands in `Quarto/`.

Adversarial visual-layout audit of a Quarto `.qmd` or Beamer `.tex` deck. Flags overflow, font inconsistency, box fatigue, spacing, and alignment issues. Use when user says "visual audit", "check the layout", "does this overflow?", "look for visual issues", "audit the slides", or after reworking a deck's appearance. Does NOT check writing or pedagogy — pair with `/proofread` or `/pedagogy-review`.

Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or requests a technical design or spec before coding — especially for complex features involving multiple components, ambiguous requirements, or significant architectural changes.

Independently critique an RPI plan and phase details against supplied evidence without editing plan sources. Use when planning credibility needs a read-only assessment.

Creates a pull request for the current branch, generating a clear title and a description that summarizes the changes and includes instructions on how to test them. Use when asked to open, draft, or create a PR.

Proposes a scoped version bump for a roosterjs hotfix. Given one or more commits provided by the user, determines which packages had files changed by those commits, bumps the version only for the affected version groups, and creates a draft PR. Use when asked to do a hotfix, a scoped/targeted version bump, or to release only specific commits.

> Use when adding triple-slash comments to Swift types, methods, or properties; creating a .docc catalog folder; writing articles or extension files for a Swift package; fixing DocC build warnings about broken symbol links or missing documentation; or setting up module-level documentation for the first time.

Help users transform abstract ideas into actionable project specs that align engineering and design teams on the problem and success metrics.

Help users master professional writing to bridge gaps between stakeholders, scale their leadership influence, and ensure organizational clarity through structured narratives and async-first norms.

> Academic writing specialist for publication-grade English prose. Drafts, revises, and audits essays, reports, analysis sections, executive summaries, conclusions, and literature reviews while enforcing sentence-structure variation, high-frequency academic verbs, calibrated hedging, and anti-AI stylistic compliance. USE for academic writing, essay polish, paragraph rewrite, prose revision against any rubric tier (HD/D/C, A/B/C, top-band/mid-band, etc.), anti-AI audit, reverse outlining, claim-evidence mapping, and rubric enforcement on assignments.

> installing the `.deepsec/` workspace, bootstrapping `INFO.md`, running cost-aware `scan` / `process` / `triage` / `revalidate` / `export` passes, gating PRs with `process --diff`, writing custom matchers, and triaging findings. Use whenever the user mentions deepsec, asks an agent to scan a repo for vulnerabilities, runs into `pnpm deepsec` / `bunx deepsec` commands, wants a CI-based PR security review, sees a `.deepsec/` directory, or asks about `INFO.md` / matchers / `process --diff` / `revalidate`, even when the tool name is not spoken. Deepsec scans are expensive (a single full scan can cost hundreds to tens of thousands of dollars) so the skill exists in part to keep the user from getting surprised.

Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.

Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.

Author, edit, and review GuardDog YARA source-code detection rules (.yar) that follow the capability/threat/risk model. Use when adding a new detection rule, changing an existing rule's patterns or metadata, splitting capabilities from threats, debugging false positives, or writing rule test cases under guarddog/analyzer/sourcecode/.

Review generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. Invoke it on your own initiative the moment you finish writing, editing, or refactoring non-trivial production code, before presenting or committing — don't wait to be asked. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).

Review generated or changed documentation before it ships — READMEs, API references, docstrings, PHPDoc/JSDoc, changelogs, tutorials, and doc sites. Best used reactively after an agent writes or edits docs, after code changes documented behavior, or before publishing docs. Use when the user says 'review the docs', 'is this documentation accurate', 'update the docs', 'write a README', 'document this API', 'add a docstring', or 'add a changelog entry'. Core job: verify every referenced function, flag, endpoint, config key, and code sample against the source; catch docs-vs-code drift; strip filler and unverifiable claims. DO NOT USE for production code review (use clean-code-guard), test review (use test-guard), marketing copy or blog posts, prose style editing of non-technical writing, or documentation site theming.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Write copy that sounds like PostHog — direct, opinionated, developer-facing, and specific. Use this skill whenever Cory is drafting, editing, or critiquing copy intended for posthog.com or any PostHog channel: product pages, landing pages, taglines, headlines, hero copy, button labels, microcopy, blog posts, newsletters, changelog entries, docs intros, social posts, marketing emails, error messages, or feature announcements. Also trigger when reviewing existing PostHog copy, refactoring generic SaaS-speak into PostHog voice, or when Cory pastes a draft and asks for feedback. Trigger even when "PostHog" isn't said explicitly — context cues like working on a product page, refining a tagline, or reviewing a PR for posthog.com mean this skill applies. The goal is copy that doesn't read like AI wrote it, doesn't sound like every other B2B SaaS site, and could pass review from PostHog's content team without flags.

Use when writing, rewriting, or improving technical docs (quickstarts, how-tos, tutorials, concept pages, or API references).

Use when the operator wants to write a blog post, draft a blog article, start a new post for the Prisma blog, or publish to prisma.io/blog.

Use when adding a new docs section or product area, editing llms.ts / the llms.txt or llms/[...slug] / llms-full.txt routes / get-llm-text / skill.md / .well-known endpoints, or working on the "agent score", "llms.txt", or anything "agent-ready" in the docs and site apps. Explains the invariants the Mintlify agent-readiness audit measures and how to hold them.

Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed 9:16 viewport. Outputs HTML + PNG.

> Draft voice-tuned LinkedIn post variants from a free-form brief. Reads a personal voice guide (generated via generate-voice-guide), produces 2–5 variants with distinct framings, applies LinkedIn-specific defaults (arrow bullets, "why this matters" beat, 150–500 words), and self-checks against the voice guide's banned phrases before returning.

> Map complete topic clusters for any subject area — hub pages, spoke articles, supporting content, internal linking architecture. Identifies content gaps, priority order, and builds a structured content calendar. Produces topic maps that build genuine topical authority, not random blog posts.

INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.

> File YouTrack issues for the kotlinx-rpc project (KRPC). Use this skill whenever the user wants to create a bug report, feature request, task, or any issue in YouTrack for kotlinx-rpc. Also use it when the user mentions filing a ticket, reporting a bug, creating a task, logging an issue, or tracking work in YouTrack — even if they don't say "YouTrack" explicitly but the context is clearly about issue tracking for this project. Covers choosing the right issue type, scope, priority, tags, and writing well-structured descriptions that match the team's conventions.

> Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.

> Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models, or PhysicsNeMo questions.

Generate API documentation from a route manifest. Use when you have a list of discovered routes and need to produce markdown documentation.

> Calculates targeted CRAP (Change Risk Anti-Patterns) scores for a named .NET method, class, or single source file. Use when the user explicitly asks to compute CRAP scores or assess risky untested code for a specific target, combining Cobertura coverage data with cyclomatic complexity analysis. coverage" diagnosis, what's blocking coverage, or where to add tests across a project (use coverage-analysis); writing tests; running tests without CRAP context.

> Project-wide code coverage and CRAP (Change Risk Anti-Patterns) score analysis for .NET projects. Calculates CRAP scores per method and surfaces risk hotspots — complex code with low coverage that is dangerous to modify. Use to diagnose why coverage is stuck or plateaued, identify what methods block improvement, or get project-wide coverage analysis with risk ranking. blocking coverage, coverage gap, CRAP scores, risk hotspots, where to add tests, coverage analysis, coverage report. writing tests, running tests without coverage, or troubleshooting test execution (use run-tests).

Reference data for test filter syntax across all platform and framework combinations: VSTest --filter expressions, MTP filters for MSTest/NUnit/xUnit v3/TUnit, and VSTest-to-MTP filter translation. DO NOT USE directly — loaded by run-tests, mtp-hot-reload, and migrate-vstest-to-mtp when they need filter syntax.

QDK programming guide for Q#, OpenQASM, and the qsharp/qdk Python API. Use when: writing or editing Q# or OpenQASM code, running quantum programs, resource estimation, circuit generation, noisy simulation, Azure Quantum submission, Qiskit/Cirq/PennyLane interop, or Q# testing and standard library usage.

Build direct Bluetooth Low Energy workflows with Core Bluetooth. Use when implementing BLE central or peripheral GATT communication, scanning or connecting with CBCentralManager, discovering services and characteristics, reading/writing/subscribing with CBPeripheral, publishing local services with CBPeripheralManager, handling Bluetooth authorization, background BLE modes, state restoration, write flow control, or CBUUID-based workflows. For privacy-preserving accessory setup/picker flows, use accessorysetupkit first and return here for post-setup GATT communication.

Read and write NFC tags using CoreNFC. Use when scanning NDEF tags, reading ISO7816/ISO15693/FeliCa/MIFARE tags, writing NDEF messages, handling NFC session lifecycle, configuring NFC entitlements, or implementing background tag reading in iOS apps.

Tokenize, tag, and analyze natural language text using Apple's NaturalLanguage framework and translate between languages with the Translation framework. Use when adding language identification, sentiment analysis, named entity recognition, part-of-speech tagging, text embeddings, or in-app translation to iOS/macOS/visionOS apps.

Apply modern Swift language patterns and idioms for non-concurrency, non-SwiftUI code. Covers if/switch expressions (Swift 5.9+), typed throws (Swift 6+), result builders, property wrappers, opaque and existential types (some vs any), guard patterns, Never type, Regex builders (Swift 5.7+), basic Codable shaping (CodingKeys, custom decoding, nested containers), modern collection APIs (count(where:), contains(where:), replacing()), basic FormatStyle usage, and string interpolation patterns. Use when writing core Swift code involving generics, protocols, enums, closures, or modern language features; route deep Codable to swift-codable, detailed formatting/localization to swift-formatstyle, and API naming to swift-api-design-guidelines.