majiayu000
- 75k skills
- 0 followers
- 567 repo stars
- 3 weeks ago last updated
- ▌ Creating Adts · majiayu000 bundleThis skill should be used when the user asks to "create an ADT", "scaffold a discriminated union", "add a tagged union", "create Effect Schema union", or needs to create algebraic data types following the ADT library pattern with proper member files and barrel exports.
- ▌ Starwave Creating Spec · majiayu000 bundleInitialize a new spec with requirements, design, and task planning. Orchestrates the entire spec-driven workflow from feature idea to actionable task list.
- ▌ Arcanea Creative Flow · majiayu000 bundleMaster the creative process from inspiration to completion. Navigate the phases of creation, manage creative energy, and build a sustainable practice that produces excellent work consistently.
- ▌ Credit System · majiayu000 bundleImplement and manage complex credit system with subscription credits, purchased credits, rollover logic, and atomic transactions. Use when working with credit deductions, refunds, subscriptions, and billing.
- ▌
- ▌ Creusot · majiayu000 bundleFormal verification of Rust code using Creusot and the Pearlite specification language. Use when the user wants to (1) add contracts/specifications to Rust functions, (2) prove correctness of Rust code, (3) write loop invariants, (4) use Creusot's Why3-based verification, (5) work with Pearlite syntax (requires, ensures, invariant, logic, predicate), or (6) debug failing Creusot proofs. Triggers include "verify this Rust", "prove", "Creusot", "add contracts", "formal verification", "loop invariant", "precondition", "postcondition", "Pearlite".
- ▌ Critical Echo · majiayu000 bundleGenerate constructive criticism reviews for popular tech articles. Use when asked to review, critique, or analyze trending tech articles from platforms like Qiita, Zenn, Hacker News, or Dev.to. (user)
- ▌ Critical Peer · majiayu000 bundleProfessional skepticism with pattern enforcement. Verify before agreeing, challenge violations, propose instead of asking. Concise output, research before asking, answer questions literally.
- ▌ Cross Context · majiayu000 bundle處理跨 Bounded Context 的依賴關係。當需求涉及多個限界上下文（如權限管理、付款、通知）時觸發，設計 Anti-Corruption Layer 和 Context Mapping。
- ▌ Cross Docking · majiayu000 bundleWhen the user wants to implement cross-docking operations, optimize transshipment, or reduce warehouse storage. Also use when the user mentions "crossdock," "transshipment," "flow-through distribution," "dock-to-dock," "consolidation center," or "break-bulk operations." For general warehouse design, see warehouse-design. For dock scheduling, see dock-door-assignment.
- ▌ Agentforge · majiayu000 bundleIndex skill for working in the AgentForge monorepo. Routes to runtime, CLI, dashboard, MCP, channels, testing, template sync, and Convex/Mastra skills.
- ▌ Aif Evolve · majiayu000 bundleSelf-improve AI Factory skills based on project context, accumulated patches, and codebase patterns. Analyzes what went wrong, what works, and enhances skills to prevent future issues. Use when you want to make AI smarter for your project.
- ▌ Axel Skill · majiayu000 bundleStructure of skill definition files - role, capabilities, enforcement, registry
- ▌ Buildskill · majiayu000 bundleClaude Code-specific features for skills. This supplements the generic skill conventions in SKILL.md.
- ▌
- ▌
- ▌ Edit Skill · majiayu000 bundleView, edit, or create Claude Code skills. Lists available skills, shows skill structure, and helps modify skill instructions.
- ▌
- ▌ Kit Agents · majiayu000 bundle(ePost) Use when creating, modifying, or auditing agents, skills, commands, hooks, or planning kit ecosystem changes
- ▌ Meta Apply · majiayu000 bundlePrivileged applier that LANDS meta-optimize / corpus-audit patches the user approved. The ONLY skill permitted to mutate the skill corpus from a self-modification proposal. Runs the cross-model jury AT LANDING (on the staged diff, not a producer-written claim), requires human approval, enforces author≠reviewer family, backs up, applies, stamps provenance, logs. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.
- ▌ Meta Skill · majiayu000 bundle元技能 - 对话复盘与技能进化。在对话结束后分析：已用技能是否可优化、未形成技能的流程是否值得沉淀。当用户说"复盘"、"回顾对话"、"优化技能"、"沉淀经验"、"这个流程可以复用吗"、"技能体系复盘"、"技能健康检查"等关键词时触发，或用户显式调用 /meta-skill。
- ▌ Ppw Update · majiayu000 bundleSync local skills and references from the GitHub repo. Triggers on update skills, sync skills, 更新技能, 同步技能
- ▌ Staged Content Refinement · majiayu000 bundleConsolidate and refine extracted skills and docs from multiple projects into unified, project-agnostic patterns. Use when staging folder has content from multiple projects ready for consolidation. Triggers on "refine staged content", "consolidate staged skills", "process staging", "merge extracted patterns".
- ▌ Save Skill · majiayu000 bundle作業中に発見した汎用パターンを Claude Code スキルとして保存する。 「これスキルにして」「パターンを保存」「スキル化」などの依頼時に使用する。 既存スキルの修正・削除には使わないこと（手動で編集する）。
- ▌ Skill Meta · majiayu000 bundleInteractive system builder. Invoke for /meta command to create tasks for .claude/ system changes.
- ▌ Skill Plan · majiayu000 bundle[Tooling & Meta] Guide for creating effective skills, adding skill references, skill scripts or optimizing existing skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, frameworks, libraries or plugins usage, or API and tool integrations.
- ▌ Promptwar E S Agent Skill Specification · majiayu000 bundleLearn how to use SKILL by following this SKILL specification.
- ▌ Skills Hub · majiayu000 bundleUse this skill when the user wants to discover, inspect, install, or apply Skills Hub presets, kits, AGENTS.md policies, or skill packages for a project. It guides the agent to use the Skills Hub CLI to search presets, inspect their policy and selected skills, install them as kit artifacts, and apply them with optional temporary skill overrides after user confirmation.
- ▌ Office Cam · majiayu000 bundleMulti-camera surveillance system with motion detection, continuous monitoring (Overwatch), and AI analysis. Supports USB webcams, Wyze RTSP, and ESP32-CAM. Features random check-ins with GIF updates.
- ▌
- ▌ Screenshot · majiayu000 bundleCapture desktop screenshots from the terminal across macOS, Linux, and Windows. Supports full-screen, active-window, app-specific, pixel-region, and window-ID captures. Use when the user explicitly requests a system screenshot or when tool-specific capture (Playwright, Figma MCP) cannot reach the target content.
- ▌ Syswhisper · majiayu000 bundleServer health monitoring with plain language Telegram alerts. Tracks CPU, memory, disk, uptime, and custom metrics. Use when: running servers/VPS instances, monitoring app health, or need simple alerting. NOT for: enterprise-scale monitoring, complex distributed systems, or regulatory compliance logging.
- ▌ Bug Fixer · majiayu000 bundleDiagnose bugs through iterative investigation, apply a type-safe fix, and generate a regression test. Use when asked to fix a bug, debug an error, diagnose a crash, investigate a failing test, or resolve an exception.
- ▌ Debug E2e · majiayu000 bundleInteractive debugging for failed e2e tests. Orchestrates the debugging session but delegates log reading to subagents to keep the main conversation clean. Use for ping-pong debugging sessions where you want to form and test hypotheses together with the user.
- ▌ Dojo Test · majiayu000 bundleWrite tests for Dojo models and systems using spawn_test_world, cheat codes, and assertions. Use when testing game logic, verifying state changes, or ensuring system correctness.
- ▌ E2e Debug · majiayu000 bundleAnalyze and fix failing E2E tests. Includes CI auto-repair mode for GitHub Actions failures. Triggers: 「テストが失敗」「CIが落ちている」「テストをデバッグ」「test failed」「flaky test」 Use when: E2E tests are failing, tests are flaky/unstable, error messages need investigation. Outputs: Fixed Page Object and spec files, error analysis reports.
- ▌ E2e Tests · majiayu000 bundleCreate and maintain Playwright E2E tests following project patterns. Use when adding new tests, debugging test failures, or understanding test structure.
- ▌ E2e Write · majiayu000 bundleCreate new E2E tests using Playwright with Page Object Model pattern and semantic locators. Triggers: 「E2Eテストを書いて」「テストを作成して」「新機能のテストが必要」「E2E test」「create test」 Use when: Creating E2E tests for new pages or components, after implementing new features. Outputs: Page Object files (frontend/e2e/pages/) and spec files (frontend/e2e/*.spec.ts)
- ▌ Fix Tests · majiayu000 bundleUse when tests are failing, test quality issues were identified, or user wants to fix/improve specific tests. Accepts green-mirage-audit reports, general instructions, or can run tests and fix failures automatically. Lighter-weight than implement-feature, focused on test remediation.
- ▌
- ▌ Hive Test · majiayu000 bundleIterative agent testing with session recovery. Execute, analyze, fix, resume from checkpoints. Use when testing an agent, debugging test failures, or verifying fixes without re-running from scratch.
- ▌ Jest Unit · majiayu000 bundleJest unit testing patterns for this Next.js application. Covers test structure, mocking strategies, React component testing, hook testing, and coverage targets. Use this skill when writing unit tests for services, hooks, utilities, or components.
- ▌ Jira Sync · majiayu000 bundleSync SpecWeave increments with JIRA epics/stories. Content flows SpecWeave→JIRA, status flows JIRA→SpecWeave. Activates ONLY when user asks questions about JIRA integration or needs help configuring JIRA sync. Does NOT activate for slash commands. For syncing, use /sw-jira:sync command instead. Coordinates with jira-mapper agent.
- ▌ Mock Data · majiayu000 bundleGenerate realistic mock data for testing using factories, fixtures, and Faker.js. Use when seeding test databases, creating test fixtures, or mocking API responses.
- ▌
- ▌ React Tdd · majiayu000 bundleUse when implementing React + Vite + TypeScript features or bugfixes with Vitest + React Testing Library tests, before writing implementation code.
- ▌ Reproduce · majiayu000 bundleDebug a user's bug by instrumenting their code with clog log statements, having them reproduce the issue, then analyzing the logs to find root cause
- ▌ Senior QA · majiayu000 bundleComprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications. Includes test suite generation, coverage analysis, E2E testing setup, and quality metrics. Use when designing test strategies, writing test cases, implementing test automation, performing manual testing, or analyzing test coverage.
- ▌ Seoulsemi · majiayu000 bundleSeoul Semiconductor LED MPN encoding patterns, series identification, package extraction, and color decoding. Use when working with Seoul Semi LEDs or SeoulSemiHandler.
- ▌ Vault Path · majiayu000 bundleFind the shortest path of links between two notes. Triggers on "path between", "how do X and Y connect", "connection chain", "link path".
- ▌ Tdd First · majiayu000 bundleEnforce strict test-first discipline — no implementation code before a failing test exists
- ▌ Project Orchestrator Test Lead · majiayu000 bundleOrchestrates browser test execution — serial agent spawning, result collection, living state doc updates.
- ▌ Test Only · majiayu000 bundleMulti-platform Test Only mode. Reads platform-context.json and routes to the correct test framework guidance (Swift Testing for iOS, Jest/Vitest for Node.js, cargo test for Rust, pytest for Python, go test for Go).
- ▌ Test Site · majiayu000 bundleTests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
- ▌
- ▌ Aif Loop · majiayu000 bundleRun a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an artifact until quality gates pass or iteration limits are reached. Use when user asks for iterative refinement, quality-gated generation, or "generate -> critique -> refine" loops.
- ▌ CLI Just · majiayu000 bundleThis skill should be used when the user asks to "create a justfile", "write just recipes", "configure just settings", "add just modules", "use just attributes", "set up task automation", mentions justfile, just command runner, or task automation with just.
- ▌ Cncsetup · majiayu000 bundleGenerate standardized CNC setup sheets for MNMUK machine shop. Covers DMG MORI mills/lathes, CITIZEN Swiss, MITSUBISHI EDM, and Haas machines. USE WHEN user says 'setup sheet', 'create setup', 'job setup', 'machine setup', 'tooling list', 'fixture setup', or 'new job' for any CNC operation.
- ▌
- ▌ Detector · majiayu000 bundleDetects SpecWeave context (.specweave/ directory exists) and provides workflow documentation. Explains available slash commands and workflow. Keywords slash commands, /sw:increment, /increment, /sw:do, /sw:progress, /sw:validate, /sw:done, specweave commands, workflow help, specweave folder.
- ▌ Df Build · majiayu000 bundleUnified command to plan and execute an objective in one flow. Collapses plan→execute→verify into a single pipeline. Use when the user wants to build something, implement a feature, or work on an objective end-to-end. Triggers on: "build this", "build objective", "let's build", "implement this", "ship this", "make this work", "build the", "work on objective", "start building", "let's implement"
- ▌ Df Quick · majiayu000 bundleExecute a quick task with DevFlow guarantees (atomic commits, state tracking) but skip optional agents. Use when the user wants to do something small, quick, or ad-hoc without full objective ceremony. Triggers on: "quickly do", "just do this", "small task", "quick change", "quick fix", "can you just"
- ▌ Esper Go · majiayu000 bundleAdvance the current work stage. If in spec mode, derives an increment plan. If in increment mode, begins implementation.
- ▌
- ▌
- ▌ L Thread · majiayu000 bundleLong-duration autonomous task with checkpoints and verification. Use when: - User says "overnight", "long running", "autonomous task" - User mentions "l-thread", "extended task" - Task will consume significant context window - Multi-phase implementation requiring persistence across interruptions
- ▌ Maintain · majiayu000 bundleWorkspace maintenance with health checks, index rebuilding, task sync, memory gap detection, archival, inbox processing, and reference file updates
- ▌ Nean Kit · majiayu000 bundleStartup runbook for NEAN projects. Establishes stack decisions, scaffolds the project, configures GitHub security, and confirms governing constraints.
- ▌
- ▌ Nw Spike · majiayu000 bundleRuns a timeboxed PROBE to validate one core assumption, then optionally PROMOTES the probe into a walking skeleton — the first e2e thin slice of the feature, committed and demo-able. Use after DISCUSS when the feature involves a new mechanism, performance requirement, or external integration.
- ▌ Offboard · majiayu000 bundleWalk through the Designer/Developer wrap-up checklist for offboarding a client engagement — conversationally, one item at a time.
- ▌
- ▌
- ▌ Unfreeze · majiayu000 bundleClear the freeze boundary set by /freeze, allowing edits to all directories again. Use when you want to widen edit scope without ending the session. Use when asked to "unfreeze", "unlock edits", "remove freeze", or "allow all edits".
- ▌ Hungarian · majiayu000 bundleWrite Hungarian that sounds human. Not formal, not robotic, not AI-generated.
- ▌
- ▌ Ppw De AI · majiayu000 bundleDetect and rewrite AI-generated patterns in English academic text. Two-phase workflow: scan with risk tagging, then batch rewrite. Triggers on "de-AI", "降AI", "reduce AI traces", "AI检测".
- ▌ SEO Audit · majiayu000 bundleAudit any URL against 17-point technical SEO checklist + algorithmic authorship rules. Uses /browse if available, falls back to checklist-based audit.
- ▌ Agent Estate · majiayu000 bundlePerpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.
- ▌
- ▌ Agile V Core · majiayu000 bundleFoundational values, directives, and context engineering rules for all Agile V agents. Load this skill first in any Agile V session. For pipeline orchestration, multi-cycle lifecycle, or compliance protocols, load the corresponding agile-v-* skill on demand.
- ▌
- ▌ Codex Worker · majiayu000 bundleDelegates implementation tasks to Codex as a Worker. Use when user mentions 'Codex に実装させて', 'Codex Worker', 'Codex に作らせて', or '実装を依頼'. Do NOT load for: 'Codex レビュー', 'セカンドオピニオン', 'Codex の意見', 'Codex でレビュー', 'Codex セットアップ'.
- ▌ Custom Agent · majiayu000 bundle[AI & Tools] Create, verify, or enhance Claude Code custom agents (.claude/agents/*.md). Triggers on: create agent, new agent, agent schema, audit agent, verify agent, review agent, enhance agent, refactor agent, agent quality, custom agent.
- ▌ Elnora Agent · majiayu000 bundleThis skill should be used when the user asks about "Elnora agent capabilities", "what can the agent do", "agent tools", "web search", "academic search", "PubMed", "ArXiv", "Exa", "Tavily", "Perplexity", "Valyu", "ToolUniverse", "scientific tools", "agent memory", "code execution", "sandbox", "search papers", "search literature", "drug discovery", "protein analysis", "clinical trials", "file operations", "agent skills", or any question about what the Elnora AI Agent can do when you send it a task.
- ▌ Gobby Agents · majiayu000 bundleThis skill should be used when the user asks to "/gobby-agents", "spawn agent", "start agent", "list agents". Manage subagent spawning - start, cancel, list, and check results of autonomous agents.
- ▌ Lead Project · majiayu000 bundleAutonomous technical lead. Takes commander's intent and drives a project to completion through an OODA loop over implementation, refactoring, review, and bug-hunting skills. Has broad authority — creates tickets, commits, invokes any skill — and only escalates via andon cord for irreversible actions, public releases, or genuinely blocking decisions. User acts as product owner; skill acts as tech lead.
- ▌ Lore Writing · majiayu000 bundleExtract lore and narrative device entities from text. Use when analyzing codex entries, bestiary entries, journals, dreams, nightmares, memories, secrets, foreshadowing, and plot devices.
- ▌
- ▌ Chat Format · majiayu000 bundleFormat prompts for different LLM providers with chat templates and HNSW-powered context retrieval
- ▌ Chatgpt Pro · majiayu000 bundleSend prompts to ChatGPT Pro via Playwriter browser automation. Use for cross-validation, second opinions, or leveraging GPT-5.2 Pro's research-grade intelligence.
- ▌ Doublecheck · majiayu000 bundleThree-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.
- ▌ Eval Runner · majiayu000 bundleRun eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria, record metrics.
- ▌ Evaluations · majiayu000 bundleUse when evaluating AI model outputs, prompts, and LLM application quality in .NET. Covers Microsoft.Extensions.AI.Evaluation for scoring, reporting, and automated test pipelines. USE FOR: evaluating LLM response quality, measuring prompt effectiveness, automated AI output scoring, building evaluation pipelines for chat applications, comparing model performance across providers DO NOT USE FOR: unit testing non-AI code (use xunit/nunit), load testing HTTP APIs (use k6 or NBomber), monitoring production metrics (use OpenTelemetry), training ML models (use mlnet)
- ▌
- ▌ Gpt Atelier · majiayu000 bundleOpenAI GPT Image generation and editing (gpt-image-2, 1.5, 1, mini). Text-to-image, mask-based inpainting, multi-reference composition, multi-turn conversational editing via Responses API, streaming with partial images. This skill should be used when generating or editing images via OpenAI's image models, when near-perfect text rendering in images is needed, when mask-based region-aware editing is required, when multi-turn conversational image editing is desired, or when streaming progressive image delivery is needed. Complements nano-banana-pro (Gemini) as a parallel image generation backend.
- ▌ Grok Oracle · majiayu000 bundleDeep reasoning oracle leveraging Grok's 2M context window. Dump massive context, get deep synthesis. Collision: context-engineering x pattern-synthesis x perspective-aggregation.
- ▌ Iso 24495 1 · majiayu000 bundleCore Plain Language standard (ISO 24495-1:2023). Governs all user-facing responses to ensure clear, structured, findable, understandable, and actionable output.
- ▌ LLM Caching · majiayu000 bundleImplement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching. Reduce API costs by 30–70%, cut latency, and improve throughput using Redis, GPTCache, and provider caching APIs.
- ▌