Art & Design

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries for plugin ordering and availability metadata, or update an existing local plugin during development with the CLI-driven cachebuster and reinstall flow.

Craft-first interface design for dashboards, admin panels, SaaS apps, tools, settings pages, data interfaces, and interactive products. Use when designing, building, reviewing, auditing, or refining product UI where visual craft, layout hierarchy, tokens, states, visual direction, or design-system consistency matter. Not for marketing pages, landing pages, campaigns, or brand-only work.

Use when deploying to Kubernetes or Azure Kubernetes Service (AKS), configuring cloud secrets, setting up progressive rollout/canary, per-PR ephemeral environments, or k8s health probes. Keywords — Kubernetes, AKS, Key Vault, Argo Rollouts, Flagger, canary, blue-green, liveness, readiness, PodDisruptionBudget, HPA, rollback, GHCR.

Use when an existing repository has messy commit history that needs to conform to conventional commits before adopting release-please, or when intermediate WIP/fixup/merge commits need to be cleaned up.

Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains.

Use when writing or refactoring code, structuring a commit or PR, or deciding whether to abstract duplication. Symptoms — mixing reorg with logic changes, a PR doing several things at once, a file growing large, the second copy of similar code, or unsure whether to DRY something up.

Round-based context alignment before execution. Use when the human, project agent, WebGPT, scillm, ask, dogpile, memory, or project-knowledge may each hold different facts about a task; especially before ambiguous design, infographic, product workflow, high-stakes implementation, plan-iterate, project-infographic, or multi-review work.

Turn a client brief, zip bundle, directory, or single requirements file into a typed acceptance-contract bundle with extracted requirements, acceptance checks, open questions, an immutable-goal draft, and a create-report-backed decision report. Use when users say acceptance contract, brief to requirements, freeze the goal, create immutable goal, amend immutable goal, build a Battle requirements bundle, or extract requirements from this bundle.

Conventions for native iPhone app development — SwiftUI + SwiftData local-first apps, XcodeGen project generation, CLI-only build/test/deploy loops (simulator by default, signed device deploys via devicectl), XCTest with visible coverage, and the free-personal-team signing gotchas. Use when creating an iOS/iPhone app, adding iOS targets or Makefile loops to a project, debugging Xcode signing/provisioning/deploy problems, or porting an existing app's logic into a native Swift client.

Scaffold persona-based UX testing agents for a web app — project-scoped .claude/agents/<persona>-ux.md files that drive a real browser via Playwright, walk user journeys as a specific persona, and report tagged friction findings. Use when setting up UX review automation, when the user asks what a specific user segment would think of the app, or after the user accepts an offer to add persona testing.

Publish Markdown as an immutable web page with a shareable URL via Mote. Use when the user asks to publish or share a Markdown document or AI-generated content online. Local preview, reading, and editing alone do not require publishing.

Dasel v3 query patterns for InstallAnywhere .iap_xml installer definitions — use when querying action sequences, discovering variables, resolving platform conditions, navigating panels, or comparing installer variants. Files are 2.5+ MB, 65,000+ lines — too large for context reads, requires structural dasel queries.

This skill should be used when the user asks to "test bash script", "write shell tests", "use shunit2", "use shellspec", "create test suite for bash", or mentions unit testing, test frameworks, mocking, or test-driven development for shell scripts.

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or when users request help with ideation, marketing, and strategic planning. Explores user intent, requirements, and design before implementation using research-validated prompt patterns.

WPS Office CLI — JSON数据驱动PPT自动生成 + 命令行操控WPS文字/表格/演示文稿

Bash 5.3 release features and improvements with practical examples. Use when working with Bash 5.3 features, new command substitution, GLOBSORT, loadable builtins, or when user asks about Bash 5.3 changes, new features, or version-specific capabilities.

Guides C++ code toward modern idioms (C++20/23/26). Use when writing new C++ code, modernizing legacy patterns, or working on security-critical C++. Replaces raw pointers with smart pointers, SFINAE with concepts, printf with std::print, error codes with std::expected.

Turn a user-authorized corpus into a dated, evidence-calibrated, explicitly partial and revisable whole-person working model. Use when Claude Code, Codex, or another compatible agent is asked to understand, capture, or reconstruct a person; create a personal operating manual, master document, digital-twin or proxy bootstrap; extract worldview, values, taste, communication style, decisions, tensions, or tacit patterns; enrich a person with public research; or combine structured Soulscrape source packets from Peopleblade or Message Like Me with notes, messages, posts, documents, repositories, and other evidence.

Turn a user-authorized corpus into a dated, evidence-calibrated, explicitly partial and revisable whole-person working model. Use when Codex is asked to understand, capture, or reconstruct a person; create a personal operating manual, master document, digital-twin or proxy bootstrap; extract worldview, values, taste, communication style, decisions, tensions, or tacit patterns; enrich a person with public research; or combine structured Ensoul source packets from Peopleblade or Message Like Me with notes, messages, posts, documents, repositories, and other evidence.

Find and rank professional people for recruiting, partnerships, sales, or research from user-provided data, public web sources, an authenticated search session, or a connected provider. Use for people discovery, LinkedIn or Sales Navigator search design, profile-list ranking, or provider filter translation.

Build evals for an AI agent that already does real work. Use when someone asks "how do I know my agent is right", wants to test an agent before trusting it, compare models on cost versus quality, or turn production failures into tests. Walks from first tasks and yes/no verifiers, to isolated environments, to a trace-driven improvement loop.

Audit a command-line tool for user-friendliness — clear situation / next-step / options in every output, colour-highlighted runnable commands, no raw jargon, no silent hangs. Invoke for "CLI UX audit", "review my CLI", "is this CLI intuitive", or before any CLI release.

Analyze academic papers and research PDFs. Use this skill when the user uploads or pastes a research paper and wants to understand it. Triggers: 'analyze this paper', 'read this PDF', 'summarize this research', 'paper summary', 'research paper breakdown', 'explain this study', 'paper critique', 'academic paper analysis', '论文分析', '帮我看这篇论文', '解读这篇文章', '这篇 paper 讲什么', '帮我分析这个 PDF', '论文解读', '文献分析', '读一下这篇论文', '帮我总结这篇文章', '这篇论文的创新点', '论文方法分析', '论文结果', '帮我准备组会汇报', '生成 PPT 大纲'. Do NOT use for non-academic PDFs, spreadsheets, or general document tasks.

Builds an evidence-backed Visual Brand DNA package from a public website using Firecrawl. Use when the user asks to extract a site's brand colors or fonts, analyze visual identity, create a brand style guide, reverse-engineer a website's design system, or says "build Visual Brand DNA" for a URL.