materialofair
- 112 skills
- 0 followers
- 12 repo stars
- last month last updated
- ▌ E2e 2 · materialofairPlaywright end-to-end orchestration for critical user journeys, artifact capture, flaky-test isolation, and CI-ready reporting.
- ▌ Test Gen 2 · materialofairPost-change intelligent test generation workflow that detects stack, analyzes changed files, and produces acceptance plus regression tests.
- ▌ Conductor 2 · materialofairUse when user wants durable Context->Spec->Plan->Implement tracks ('conductor', 'structured workflow', 'track this', 'context then plan'). Creates and governs `.omc/conductor/` artifacts for OpenCode multi-session delivery.
- ▌ Start Dev 2 · materialofairAdaptive development workflow that runs discover -> research -> plan -> implement -> verify with explicit quality gates.
- ▌ Skill Tester 2 · materialofair bundleTest a OpenCode skill with prompt scenarios, invocation checks, negative cases, and execution validation.
- ▌ AI Commenting 2 · materialofairAI-native code annotation protocol that encodes intent, risk, dependencies, constraints, and test expectations in machine-parseable comments.
- ▌ Bdd Generator 2 · materialofairGenerate and maintain BDD scenarios and step definitions using Gherkin plus playwright-bdd with a one-scenario-at-a-time TDD loop.
- ▌
- ▌ Test Coverage 2 · materialofairAnalyze coverage, prioritize untested risk hotspots, generate missing tests, and verify threshold improvements.
- ▌ Skill Debugger 2 · materialofair bundleDiagnose why a OpenCode skill is under-triggering, over-triggering, undiscoverable, or misconfigured.
- ▌ Electron Driver 2 · materialofair bundlePlaywright-based E2E driving for Electron applications using launch mode or attach mode with robust window selection and runtime inspection.
- ▌ Prompt Optimizer 2 · materialofair bundleAnalyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". Specially handles short Chinese bug reports (the dominant real-world use case): runs Bug Report Triage to extract repro/expected/actual/environment, asks up to 3 clarifying questions if ≤ 2 fields are present, and inserts systematic-debugging as a hard prerequisite before any code change. DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization (unless the user exp
- ▌ Quick Init Project 2 · materialofairUse when the user wants to "quick init project", "bootstrap a new project", "recommend fullstack vs frontend vs backend", "initialize monorepo", "generate project scaffold", "project setup recommendation", or asks "快速初始化项目", "初始化 monorepo", "生成项目脚手架方案"
- ▌ Planning With Files 2 · materialofair bundleFile-based planning workflow for complex tasks. Create and maintain task_plan.md, findings.md, and progress.md as persistent working memory.
- ▌ Skill Quality Analyzer 2 · materialofair bundleAnalyze the quality of a OpenCode skill across discovery, structure, safety, examples, and maintainability.
- ▌ Swiftui Expert Skill 2 · materialofair bundleUse when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management, view composition, performance, Liquid Glass adoption, or Instruments `.trace` capture/analysis for hangs, hitches, CPU hotspots, or excessive view updates.
- ▌ Swiftui Expert Skill · materialofair bundleUse when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management, view composition, performance, Liquid Glass adoption, or Instruments `.trace` capture/analysis for hangs, hitches, CPU hotspots, or excessive view updates.
- ▌ Mle Workflow · materialofair bundleProduction machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
- ▌ Tdd Workflow 2 · materialofair bundleUse this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
- ▌ Cancel · materialofairCancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
- ▌
- ▌ Frontend UI UX 2 · materialofairDeprecated compatibility shim for frontend UI/UX work; use $design or $visual-ralph
- ▌
- ▌ Configure Notifications · materialofairConfigure OMX notifications - unified entry point for all platforms
- ▌ Eli5 · materialofairExplain a topic like I'm a 5 year old. Use when the user types /eli5 [topic] or asks for a dead-simple picture explainer of how something works.
- ▌ Analyze · materialofairDeep analysis and investigation for bugs, architecture issues, and risk hotspots. Use when the user asks to analyze, investigate, debug, or explain why something is failing.
- ▌ Merge Review · materialofair bundleMANUAL ONLY. Run a structured pre-MR review when the user explicitly requests merge-review via /merge-review, $merge-review, merge-review, or natural language such as 执行 merge-review. Produces impact analysis report, merge readiness checklist, regression self-check, code quality audit, and changelog for the current branch against origin/main.
- ▌ Prompt Pilot · materialofairOptimize a rough prompt with an independent subagent, present several CONCISE ready-to-run variants for the user to pick or edit, then EXECUTE the chosen prompt directly in the current session. Unlike prompt-optimizer (advisory only — it just hands back text), prompt-pilot closes the loop: optimize → choose → run. TRIGGER when the user wants both optimization AND execution: "优化并执行", "优化提示词后直接做", "优化指令然后执行", "帮我把这个需求优化好再做", "optimize and run my prompt", "improve this prompt then do it", "refine my prompt and execute it", or when the user explicitly invokes /prompt-pilot. DO NOT TRIGGER when the user only wants advice/text back with no execution ("优化prompt", "改进prompt", "rewrite this prompt", "how to write a prompt for") — that is prompt-optimizer. DO NOT TRIGGER for "优化代码" / "优化性能" / "optimize this code" / "optimize performance" — those are refactoring or performance tasks. DO NOT TRIGGER when the user says "直接做" / "just do it" with no request to optimize — execute the task normally without this skill.
- ▌ H5 To Swiftui · materialofair bundleConvert an H5 / web app's source into a native SwiftUI iOS app by native rewrite (NOT a WebView shell, NOT a transpiler). Use when the user wants to port, re-implement, or migrate a web/H5 frontend to native SwiftUI with high visual fidelity, asks to "turn this web app into a real iOS app", or wants a measured render-diff convergence loop against a browser baseline. Auto-detects the web stack (v1: vanilla + React; other stacks are detected then gated, not guessed), extracts design tokens, calibrates a cross-renderer fidelity floor, rewrites per component, and drives a bounded render→diff→correct loop that reports a quantified visual residual plus an independent judge verdict. It does NOT promise literal pixel-identity: cross-renderer differences impose a measured floor it reports honestly. Triages canvas/WebGL/complex-animation/3rd-party-SDK/backend surfaces instead of silently emitting wrong code.
- ▌ Skill Creator · materialofair bundleCreate new skills, modify and improve existing skills, and evaluate whether they route and behave correctly in OMC. Use when users want to create a skill from scratch, edit an existing skill, improve skill triggering, or iterate on a skill with prompt-based tests.
- ▌ Tdd Generator · materialofairTest-driven workflow for unit, component, and E2E testing. Enforces Red-Green-Refactor and generates the right test type for changed code.
- ▌ Conductor Distill · materialofair bundleDistill methodology from superpowers and BMAD-METHOD docs into the active conductor track's spec.md / plan.md / review.md as intent-layer overlays. Use when user asks to "distill superpowers into conductor", "把 superpowers/bmad 提炼到 conductor", "import method docs to track", "seed conductor with brainstorming/TDD/verification gates", or "feed BMAD PRD/architecture/story/QA principles into the track". Writes only inside marker blocks so it never competes with code-derived facts and re-runs cleanly. DO NOT use for general superpowers invocation, code refactors, or to summarize this codebase.
- ▌ Swift Concurrency Expert · materialofair bundleSwift Concurrency review and remediation for Swift 6.2+. Use when asked to review Swift Concurrency usage, improve concurrency compliance, or fix Swift concurrency compiler errors in a feature or file. Concrete actions include adding Sendable conformance, applying @MainActor annotations, resolving actor isolation warnings, fixing data race diagnostics, and migrating completion handlers to async/await.
- ▌ Guideline Optimizer · materialofairMaintainer-only workflow for semantically optimizing OMC guideline sources into a concise canonical .local/guidelines/CLAUDE.md output. Use when curating external prompt-guideline repos such as andrej-karpathy-skills.
- ▌ Semiconductor Intelligence Monitor · materialofair bundle面向长鑫 DRAM 后道部门领导生成半导体情报日报、周报或临时专题,覆盖关键物料成本、BCP供应链风险、三星/SK海力士/美光动态、长鑫国内舆情及半导体AI落地实践。在用户要求扫描、跟踪或汇总这些信息时使用。
- ▌ Autopilot · materialofair[OMX] Strict autonomous loop: $deep-interview -> $ralplan -> $ultragoal (+ $team if needed) -> $code-review -> $ultraqa
- ▌ Ultragoal · materialofairCreate and execute durable repo-native multi-goal plans over Codex goal mode artifacts.
- ▌
- ▌ Deep Interview · materialofairSocratic deep interview with mathematical ambiguity gating before execution
- ▌
- ▌
- ▌ Autoresearch Goal · materialofairDurable professor-critic research workflow over Codex goal mode without reviving deprecated omx autoresearch
- ▌ Prometheus Strict · materialofair bundle[OMX] Clean-room interview-driven planner: Metis clarifies, Momus challenges, Oracle synthesizes, then hands off to $ultragoal/$team.
- ▌ Best Practice Research · materialofair[OMX] Bounded best-practice research wrapper using official/upstream evidence first
- ▌
- ▌
- ▌ Drawio · materialofair bundleProfessional diagramming and architecture visualization using Draw.io MCP server. Create, modify, and manage system diagrams, flowcharts, and technical documentation visuals programmatically.
- ▌
- ▌ Verify · materialofairUse this skill to run deterministic project verification (build, types, lint, tests, security, git status) with mode-based command sets.
- ▌
- ▌
- ▌
- ▌ Research · materialofairUse this skill for multi-stage, evidence-based research with parallel investigation, source ranking, verification, and synthesis.
- ▌
- ▌ Test Gen · materialofair bundleUse this skill after code changes to generate or update targeted tests, acceptance coverage, and regression checks with stack-aware verification.
- ▌
- ▌ Conductor · materialofair bundleUse when the user explicitly asks for Conductor, wants track/spec/plan/review artifacts on disk, or needs long-lived project context management. Prefer start-dev for small or one-off tasks. If Conductor is not configured in the project, start with setup.
- ▌
- ▌
- ▌ Start Dev · materialofairIntelligent adaptive workflow with automatic pattern library loading, codebase exploration, and multi-approach architecture. Auto-detects frontend/backend tasks and loads relevant patterns.
- ▌
- ▌ Ask Gemini · materialofairDeprecated compatibility stub. Prefer Codex-native multi-agent research, consensus, thinkdeep, or architect-planner.
- ▌
- ▌
- ▌
- ▌ Eval Harness · materialofairFormal evaluation framework for Codex sessions implementing eval-driven development (EDD) principles
- ▌ Intelligent Log Analysis · materialofairAnalyze browser console logs with 90% noise filtering. Debug web apps, check console errors, analyze JavaScript issues efficiently.
- ▌
- ▌ Skill Tester · materialofair bundleTests Codex skill functionality with TDD approach, verifying skills work correctly through automated test scenarios and validation
- ▌ Tdd Workflow · materialofair bundleUse this skill for test-first implementation of new features, bug fixes, and refactors with RED-GREEN-REFACTOR discipline and explicit verification gates.
- ▌ AI Commenting · materialofairAI-native code annotation protocol that encodes intent, risk, dependencies, constraints, and test expectations in machine-parseable comments.
- ▌ Bdd Generator · materialofair bundleBehavior-Driven Development assistant using playwright-bdd. Generates Gherkin features and step definitions with full TDD Guard integration.
- ▌ De AI Writing · materialofair bundleUse when the user asks to remove AI tone, humanize a draft, or polish text written (or smelling) like an LLM. Trigger phrases include "去 AI 味"、"去ai味"、"降低机器感"、"改得像真人写的"、"不要 AI 腔"、"humanize"、"de-ai"、"remove AI tone". Default optimized for Chinese; supports zh/en mixed text. Always cross-checks output against the Wikipedia "Signs of AI writing" taxonomy before delivery.
- ▌ Quality Check · materialofair bundleThis skill should be used when the user asks to "check code quality", "score this code", "find quality hotspots", "prioritize refactoring", "analyze technical debt", "run CodeDNA", or assess maintainability, complexity, modularity, tests, documentation, and best practices.
- ▌ Tdd Test Generator · materialofair bundleAI-powered test-driven development assistant. Generates unit tests (Vitest), component tests (React Testing Library), and E2E tests with Playwright Test Agents integration.
- ▌
- ▌ UI UX Pro Max · materialofair bundleUI/UX design with 50+ styles, palettes, fonts for React/Vue/Next.js/SwiftUI. Builds responsive components, handles accessibility, animations, and design systems.
- ▌ Writer Memory · materialofair bundleAgentic memory system for writers - track characters, relationships, scenes, and themes
- ▌
- ▌ Frontend UI UX · materialofairDesigner-developer workflow for UI/UX work using Codex-native frontend design, local project conventions, and optional read-only review agents.
- ▌
- ▌ Skill Debugger · materialofair bundleDebugs why Codex skills are not triggering when expected, analyzing descriptions, trigger conditions, installation paths, discovery, and skill conflicts
- ▌
- ▌ Patent Workflow · materialofair bundle三阶段专利撰写workflow(Research → Plan → Implement),借鉴AutoPatent架构,通过 Codex CLI 原生 spawn_agent 派发 explorer/reviewer child agent 协作,确保专利质量和授权率;也用于整理或优化已有 DOCX 专利交底书、保留图片和版式资源并生成新版 Word 文档
- ▌ Project Analyze · materialofair bundleThis skill should be used when the user asks to "analyze project structure", "explain this codebase", "show dependencies", "find high-risk files", "assess refactor impact", "understand architecture", or run ProjectMind for local codebase analysis.
- ▌
- ▌ Backend Patterns · materialofairBackend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
- ▌ Coding Standards · materialofairUniversal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
- ▌ Prompt Optimizer · materialofair bundleAnalyze raw prompts, identify intent and gaps, inventory the current oh-my-codex skill catalog across local/upstream sources, choose the best-fit skill chain, and output a ready-to-paste optimized prompt for Codex. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.
- ▌
- ▌ Frontend Patterns · materialofairFrontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
- ▌ Skill Development · materialofair bundleCreate effective Codex skills with specialized knowledge, workflows, and tool integrations. Covers structure and documentation.
- ▌ Verification Loop · materialofair bundleUse this skill for iterative verify-fix cycles across build, type, lint, test, and security gates until completion or explicit stop conditions.
- ▌ Exa Search · materialofair bundleNeural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
- ▌ Local Skills Setup · materialofairSet up and manage local skills for automatic matching and invocation
- ▌ Quality Validation · materialofair bundleValidate ResearchPacks and Implementation Plans with scoring rubrics and quality gates. Prevents garbage-in-garbage-out scenarios.
- ▌ Quick Init Project · materialofairThis skill should be used when the user asks to "快速初始化项目", "根据需求推荐全栈还是前端/后端", "初始化 monorepo", "生成项目脚手架方案", "project bootstrap recommendation", or "fullstack vs frontend vs backend decision".
- ▌ Architecture Review · materialofair bundleReview software architecture using repository evidence, with focused design, change, and system modes. Use when evaluating an architecture proposal before implementation, verifying a completed feature or refactor for boundary and dependency regressions, or performing a milestone/periodic architecture health review. Focus on layering, dependency direction, module boundaries, cohesion, coupling, extensibility, information hiding, testability, change amplification, migration risk, and architecture drift. Trigger for architecture review requests such as 架构审查, 架构评审, 分层检查, 解耦分析, 扩展性审查, or 架构健康检查. Do not use for ordinary line-level code review or for creating a new architecture from scratch.
- ▌ Iterative Retrieval · materialofairPattern for progressively refining context retrieval to solve the subagent context problem
- ▌ Pattern Recognition · materialofairIdentify, capture, document reusable patterns from implementations. Enables automatic learning and knowledge-core.md updates.