majiayu000
- 75k skills
- 0 followers
- 567 repo stars
- 3 weeks ago last updated
- ▌
- ▌ Sqlite Inspector · majiayu000 bundleПроверка консистентности данных в SQLite базах данных MikoPBX после операций REST API. Использовать при валидации результатов API, отладке проблем с данными, проверке связей внешних ключей или инспектировании CDR записей для тестирования.
- ▌ Supabase Testing · majiayu000 bundleTesting patterns for Supabase applications covering auth flow testing, Row Level Security policy testing, realtime subscription testing, and edge function testing
- ▌ Syncing Testlink · majiayu000 bundleSyncs test cases from a project folder into TestLink by creating test suites, importing test cases with HTML formatting, building a test plan, and assigning cases. Use when a QA engineer wants to sync TestLink, import to TestLink, upload test cases, or push test cases to TestLink.
- ▌ Terraform Module · majiayu000 bundleInspect Terraform module specs from cache when seeing module sources.
- ▌ Test Browsy Flow · majiayu000 bundleTest a URL with the browsy CLI and report page detection accuracy
- ▌ Test Consolidate · majiayu000 bundleConsolidate verbose test suites by replacing repetitive unit tests with property-based tests, parameterized tests (rstest), or fuzz tests. Less code to maintain, same or better coverage.
- ▌ Test Engineering · majiayu000 bundleUse when the Integrator is writing unit tests, e2e tests, designing test strategies, improving test coverage, creating test fixtures, or mocking dependencies. Activates for any testing-related work including TDD, test refactoring, or test debugging.
- ▌ Testing Patterns · majiayu000 bundleTesting patterns and standards for this codebase, including async effects, fakes vs mocks, and property-based testing.
- ▌ UI Component Doc · majiayu000 bundleYou are an expert technical writer specializing in UI component library documentation for the Medusa UI design system.
- ▌ Use Unity Editor · majiayu000 bundleRead and edit scenes and prefabs as you would in the Unity editor. You can't do anything in the Unity editor without this skill.
- ▌ Vcp Review Tests · majiayu000 bundleReview test quality against VCP testing standards. Checks for tautological tests, over-mocking, missing edge cases, and other anti-patterns.
- ▌
- ▌ Write Test Cases · majiayu000 bundleResearch and write test cases for a rule. Spawns a test-researcher to produce a coverage matrix, then test-case-writers (one per category) to create the files.
- ▌ Ce Release Task · majiayu000 bundleIdentify the next release task from RELEASE_PLAN_v1.md and vX.Y.Z_plan.md, plan implementation, execute it, and verify closure with tests and gates.
- ▌ Cleanup Project · majiayu000 bundleProject cleanup and pruning workflow. Use when removing unused guides, cleaning up stale components, or streamlining an Samuel installation to match actual project needs.
- ▌ Cognitive Modes · majiayu000 bundleGorev tipine gore dusunme modu secimi. 5 mod -- analytical (derin analiz), creative (yaratici cozum), systematic (adim adim), rapid (hizli aksiyon), debug (hata izleme). Her mod farkli prompt stratejisi ve karar agaci kullanir.
- ▌ Course Workflow · majiayu000 bundleOrchestrate course development workflow, track progress, and capture learnings.
- ▌ Create Workflow · majiayu000 bundleCreate new workflows with consistent structure and matching skill integration. Meta-workflow for formalizing patterns into trackable processes.
- ▌ Daily Synthesis · majiayu000 bundleAutomated end-to-end feedback pipeline that pulls new Supabase entries, enriches, classifies, routes to canvases, and generates a synthesis report.
- ▌ Done Retirement · majiayu000 bundlePipeline retirement protocol for completed work items. Implements a 7-stage validate-commit-push-submit-notify-cleanup-terminate pipeline with irreversibility after push. Done means gone.
- ▌ Dpia Assessment · majiayu000 bundleGDPR Art. 35 Data Protection Impact Assessment with threshold checking, risk registers, and EDPB criteria scoring. Use for DPIA evaluations.
- ▌ Gobby Workflows · majiayu000 bundleThis skill should be used when the user asks to "/gobby-workflows", "activate workflow", "workflow status". Manage step-based workflows - activate, deactivate, check status, and list available workflows.
- ▌ Handle Approval · majiayu000 bundleManage human-in-the-loop approval workflow for sensitive actions like payments, email sending, social media posts, and file operations. Creates structured approval requests, monitors approval status in /Approved and /Rejected folders, executes approved actions safely, and maintains complete audit logs. Use when any action requires approval, user mentions "check approvals", "pending approval", "approve this", "what needs approval", or before executing sensitive operations like payments, emails, or social posts.
- ▌ Kata Move Phase · majiayu000 bundleMove a phase between milestones or reorder phases within a milestone. Triggers include "move phase", "move phase to milestone", "reorder phase", "reorder phases".
- ▌ Kol Engager Icp · majiayu000 bundleFind ICP-fit leads from KOL audiences on LinkedIn. Given a list of KOLs, scrapes their most relevant high-engagement post from the last 30 days, extracts engagers (reactors + commenters), pre-filters by position, enriches top profiles, and ICP-classifies. Cost-controlled: 1 post per KOL. Use when someone wants to "find leads from KOL audiences" or "scrape engagers from influencer posts" or after running kol-discovery.
- ▌ Nw Fast Forward · majiayu000 bundleFast-forwards through remaining waves end-to-end without stopping for review between waves.
- ▌
- ▌ Patent Pipeline · majiayu000 bundleFull patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says "写专利", "patent pipeline", "专利申请", "draft patent", "写权利要求书", or wants to draft a complete patent application.
- ▌ Pipeline Rnaseq · majiayu000 bundleExecute ENCODE RNA-seq pipeline from FASTQ to gene quantification and signal tracks. Child of pipeline-guide. Provides Nextflow execution with Docker and cloud deployment. Use when processing RNA-seq data with STAR alignment, RSEM/Kallisto quantification, or generating expression matrices. Trigger on: RNA-seq pipeline, gene expression, STAR alignment, RSEM quantification, transcript quantification, TPM, FPKM, RNA processing, run RNA-seq.
- ▌ Babysitter Project Install · majiayu000 bundleSet up a project for babysitting. Research the codebase, build project profile, install tools.
- ▌ Quick Interview · majiayu000 bundleForce quick interview depth for this session. Use when user says '/quick-interview' or 'quick interview mode'.
- ▌ Ralph Preflight · majiayu000 bundleCheck all MCP servers and services before workflow execution. MUST pass before any Ralph command proceeds.
- ▌ Rapid Iteration · majiayu000 bundleOptimizes for fast version cycling. Minimal questions, maximum output. Auto-diffs between versions and accepts terse feedback. Use when you need to iterate quickly on designs, code, or content. Ship-feedback-next loop.
- ▌ Recipe Assembly · majiayu000 bundleRecipe-based context assembly and deployment using slice architecture. Use when building compilation pipelines, extracting documentation slices, or deploying context to multiple targets.
- ▌
- ▌ Sales Call Prep · majiayu000 bundlePre-sales-call intelligence composite. Deep dives on the person AND their company before a sales call, then maps findings to your product to generate talking points, objection prep, and a call strategy. Goes beyond generic attendee research — this is sales-specific intelligence that helps SDRs, AEs, and founders walk into calls with a plan. Tool-agnostic — works with any CRM, research source, and calendar.
- ▌
- ▌
- ▌ Session Handoff · majiayu000 bundleGenerate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resume work. Use when ending a session, saying "continue later", "save progress", "session summary", or "pick up where I left off".
- ▌ Session History · majiayu000 bundleAccess session history to continue work, see what happened, or search past sessions. Use this instead of relying on memory - the raw data is always more accurate.
- ▌ Status Reporter · majiayu000 bundleCORE SKILL - Must be called by ALL other skills to update project status. Maintains global project state, feature progress, and action log. Triggers on "Show status", "Project status", "What's the status".
- ▌ Sync Migrations · majiayu000 bundleUse when creating dotfiles migrations for one-time cleanup on existing machines (removing old tools, uninstalling replaced packages, cleaning deprecated files). Also use when a migration fails and user needs help diagnosing or recovering.
- ▌ Tasker To Beads · majiayu000 bundleTransform Tasker task definitions into rich, self-contained Beads issues. Bridges ephemeral execution units with persistent planning artifacts.
- ▌ Template Update · majiayu000 bundleUpdates template files in metasaver-marketplace as the source of truth before applying changes elsewhere. Use when standardizing configs across repos - updates template FIRST, then uses it for remediation. For config skills and domain skills with templates.
- ▌
- ▌ Update Py Notes · majiayu000 bundleUpdate dendron module notes for changed Python files. Checks staged files first, then falls back to modified (unstaged) files. Appends dated sections and stages updated notes. Run before /update-tasks-weekly and /commit.
- ▌ Update Workflow · majiayu000 bundleSync workflow documentation between projects - CLAUDE.md and .claude/workflow/ files. TRIGGER when: user wants to sync workflow docs ("update workflow from X", "sync workflow", "pull workflow from framework", "push workflow to project"). DO NOT TRIGGER when: user wants to update pillars/rules/skills (use respective update-* skills), or just wants to read workflow docs.
- ▌ Synapse Upload Workflow · majiayu000 bundleUse when user mentions "upload", "data collection", "file specifications", "data units", "organize files", "map files to specs", "bulk upload", "s3 upload", "cloud storage", "multi-path", "excel metadata".
- ▌ Vow Enforcement · majiayu000 bundleClassifies and enforces constraints via soft vows, hard vows, and Nen Court layers. Use when designing or auditing enforcement mechanisms for project rules.
- ▌ Workflow Debate · majiayu000 bundleStructured adversarial debate between AI councillors using Agent Teams to evaluate ideas, plans, or decisions. ALWAYS use when the user says "council", "debate this", "evaluate this idea", "challenge my plan", "stress-test", "devil's advocate", "multiple perspectives", "évaluer cette idée", "débattre", "challenger mon plan", "tester cette décision", or when the user wants rigorous multi-perspective analysis of a proposal, architecture decision, or strategic choice. Each councillor (visionary, critic, pragmatist, innovator, ethicist, domain expert) represents a distinct perspective and they challenge each other through cross-examination and peer exchange, producing a nuanced verdict (PROCEED / PROCEED WITH CONDITIONS / RECONSIDER / DO NOT PROCEED). Do NOT use for divergent brainstorming or idea generation — use workflow-brainstorm instead.
- ▌ Workflow Finish · majiayu000 bundleCleanup branch after PR is merged. Use when user says /workflow finish or /workflow-finish.
- ▌ Writing Handoff · majiayu000 bundleCreate structured handoff document for writing workflow session pause/resume.
- ▌ Youtube Publish · majiayu000 bundleEnd-to-end YouTube publishing workflow using ordered scripts: prepare/concat video, upload draft, transcribe with Parakeet, generate copy with the calling model, render thumbnails, update YouTube metadata, then schedule socials (PostFlow) 15 minutes after publish.
- ▌ Abstract Trimmer · majiayu000 bundleCompress academic abstracts to meet strict word limits while preserving key information, scientific accuracy, and readability. Supports multiple compression strategies for journal submissions, conference applications, and grant proposals.
- ▌ Academic Writing · majiayu000 bundleAcademic writing, research methodology, and scholarly communication workflows. Use when writing papers, literature reviews, grant proposals, conducting research, managing citations, or preparing for peer review. Essential for researchers, graduate students, and academics across disciplines.
- ▌ AI Writing Detox · majiayu000 bundleEliminate AI-generated writing patterns that erode reader trust. Activate when writing articles, documentation, press releases, or any content where AI patterns would undermine credibility. Essential for journalists using AI assistance who need human-sounding output.
- ▌ Content And Copy · majiayu000 bundleWrite or edit website copy, blog content, and editorial pieces with attention to voice, structure, and goal. Use this skill whenever the user wants to write an article, draft website copy, edit existing content for clarity or voice, write a blog post, or produce general editorial content. Triggers on write a blog post, draft an article, write copy for, edit this, rewrite this, write content, write a guide, draft a how-to, write web copy. Also triggers when content has been outlined and now needs to be written, or when existing content needs voice or clarity edits.
- ▌
- ▌ Korean Humanizer · majiayu000 bundle한국어 AI 생성 텍스트 패턴 감지 및 수정. description, docstring, CHANGELOG 등 한국어 텍스트 품질 개선.
- ▌ Landing Copy Cta · majiayu000 bundleUse whenever `landing-copywriter` drafts the CTA/close — the final ask, or any mid-page section `landing-sequencer` assigned the CTA. Trigger when a section carries the token system's CTA styling intent, distinct from every other archetype (which build the case, not make the ask).
- ▌ Motion New Trial · majiayu000 bundleDrafts a post-verdict Motion for New Trial in criminal defense cases. Structures arguments around recognized grounds (weight-of-evidence, newly discovered evidence, prosecutorial misconduct, juror misconduct, IAC, judicial error) with record citations. Use when filing a motion for new trial, post-conviction motion, or requesting the court set aside a criminal verdict.
- ▌ Ppw Cover Letter · majiayu000 bundleGenerate submission-ready cover letters from paper content and target journal requirements. Includes contribution statement, data availability, conflict of interest, and contact block. 生成投稿信,包含贡献声明、数据可用性、利益冲突声明和联系方式。
- ▌ Research Writing · majiayu000 bundleResearch writing conventions for academic and professional contexts. Covers the research process (question formation, literature review, methodology, evidence evaluation), academic genres (research paper, literature review, annotated bibliography, thesis/dissertation, conference paper), citation and attribution (MLA, APA, Chicago, IEEE, in-text vs. footnote, bibliography construction), source evaluation (CRAAP test, peer review, primary vs. secondary, bias detection), research argument construction (hypothesis-driven, question-driven, thesis as evolving claim), and ethical research practices (plagiarism, paraphrase integrity, IRB considerations, data transparency). Use when writing research papers, evaluating sources, constructing academic arguments, or teaching research methodology.
- ▌ Resonance Engine · majiayu000 bundleUse when writing is structurally clear but emotionally flat—adds turning points, sensory metaphors, and change hooks using Storr's brain-change model and Hopkins' specificity techniques.
- ▌ Revision Editing · majiayu000 bundleRevision and editing strategies for all writing forms. Covers the revision hierarchy (structural revision, paragraph-level revision, sentence-level editing, proofreading), structural revision techniques (reverse outline, cut test, resequencing, scope audit), paragraph and sentence editing (coherence check, topic sentence audit, sentence combining, deadwood removal, passive voice audit), the workshop model (Calkins Writers Workshop, peer feedback protocols, conferencing, response letters), self-editing techniques (read-aloud test, print-and-mark, time gap, checklist protocols), and common error patterns with diagnostic fixes. Use when revising drafts, editing for clarity, running workshops, or teaching the revision process.
- ▌ Story Long Write · majiayu000 bundle长篇网文写作。从大纲到正文,辅助长篇网络小说的创作,包括世界观、人物、情节线管理。 触发方式:/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」
- ▌ Xe Writing Style · majiayu000 bundleTransform unstructured notes into polished blog posts in Xe Iaso's voice. Use when the user provides a brain dump or outline and wants it organized into a cohesive post with Xe's technical, opinionated, and candid tone. Also use when editing or reviewing prose that should match Xe's style.
- ▌ Aget Create Project · majiayu000 bundleCreate research projects with context-aware scaffolding. Reads AGET identity, searches prior work, pre-populates Due Diligence. Use when starting any formal AGET project.
- ▌
- ▌ Cc Harness Patterns · majiayu000 bundleHarness Engineering 設計模式 — 基於 Claude Code 原始碼逆向分析的 12 條可遷移原則。Use when: 設計 agent 系統架構、實作 tool orchestration、設計 context 管理策略、建構 agent loop。
- ▌ Cobuilder Heartbeat · majiayu000 bundleBehavioral specification for the CoBuilder Heartbeat teammate. Loaded as prompt when spawning the Haiku work-finder agent within the session-scoped cobuilder-live-{hash} team. Defines the heartbeat loop scanning for actionable work (beads, orchestrator failures, git staleness, stale tasks, idle orchestrators, GChat replies) and reporting findings to CoBuilder via SendMessage.
- ▌ Collaboration Style · majiayu000 bundleAI-human collaboration norms — friction cases, coding style preferences, behavioral guidelines. Use when: calibrating communication style, deciding when to ask vs act, or adjusting response detail level.
- ▌ Communication Style · majiayu000 bundleOutput rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.
- ▌ Convex Agents Files · majiayu000 bundleHandles file uploads, image attachments, and media processing in agent conversations. Use this when agents analyze images, process documents, or generate files.
- ▌ Deepagents Overview · majiayu000 bundle理解 Deep Agents 框架 - 它们是什么、如何使用 createDeepAgent 创建,以及 agent harness 架构,包括内置的规划、文件系统和子代理中间件。
- ▌ Deepagents Todolist · majiayu000 bundleUsing TodoListMiddleware for task planning and tracking progress with the write_todos tool in Deep Agents for complex multi-step workflows.
- ▌ Design Agent Native · majiayu000 bundleBuild applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
- ▌ Hosted Agents V2 Py · majiayu000 bundleBuild hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition. Use when creating container-based agents that run custom code in Azure AI Foundry. Triggers: "ImageBasedHostedAgentDefinition", "hosted agent", "container agent", "create_version", "ProtocolVersionRecord", "AgentProtocol.RESPONSES".
- ▌
- ▌ Load Pickle Persona · majiayu000 bundleActivates the Pickle Rick persona. Use this ONLY when the user explicitly requests to start the "Pickle Rick" mode or loop. DO NOT use this for general greetings (e.g., "hi") normal assistance.
- ▌ User Input Protocol · majiayu000 bundleStructured checkpoint format for requesting human input. When an agent needs a decision, it must stop, present context, show options, and wait. Activate when delegating to subagents, running background tasks, or hitting any decision point that requires human judgment.
- ▌ Alphaear Sentiment · majiayu000 bundleAnalyze text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial texts.
- ▌ Anti Hallucination · majiayu000 bundleComplete methodology for preventing AI hallucinations. Use when accuracy is critical and you need Claude to verify before claiming, cite before asserting, and admit uncertainty instead of guessing.
- ▌ API AI Mistral Sdk · majiayu000 bundleOfficial Mistral AI TypeScript SDK patterns — client setup, chat completions, streaming, function calling, structured outputs, embeddings, vision, Codestral FIM, and production best practices
- ▌ API AI Together AI · majiayu000 bundleTogether AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function calling, embeddings, image generation, fine-tuning, and OpenAI-compatible endpoints
- ▌ Convex Agent · majiayu000 bundleBuild AI agents with persistent threads, tool calling, and streaming on Convex. Use when implementing chat interfaces, AI assistants, multi-agent workflows, RAG systems, or any LLM-powered features with message history.
- ▌ Gemini Masterpiece · majiayu000 bundleElite strategies for leveraging Gemini 3.0 Pro to its maximum creative and technical potential in 2026.
- ▌
- ▌ Langchain Patterns · majiayu000 bundleImplement Retrieval-Augmented Generation (RAG) systems with LangChain4j. Build document ingestion pipelines, embedding stores, vector search strategies, and knowledge-enhanced AI applications. Use when creating question-answering systems over document collections or AI assistants with external knowledge bases.
- ▌ Lora Trainer Guide · majiayu000 bundleUse when helping users configure LoRA training — select presets, understand parameters, and pick the right settings for their model type. Covers SD1.5, SDXL, SD3, and Flux1 with real-world presets.
- ▌ Orchardcore AI MCP · majiayu000 bundleSkill for configuring Model Context Protocol (MCP) in Orchard Core using the CrestApps MCP module. Covers MCP client connections (SSE and Stdio transports), MCP server setup to expose Orchard Core as an MCP endpoint, MCP resources, authentication, and custom resource types.
- ▌ Prompt Engeneering · majiayu000 bundleUniversal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic systems that need structured prompts.
- ▌ Pydantic AI Agents · majiayu000 bundleBuild and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, or dynamic prompts, (4) Integrate OpenRouter for multi-model access, (5) Add Logfire for debugging/observability, (6) Structure agent architecture with dependency injection.
- ▌ RAG Infrastructure · majiayu000 bundleBuild and operate Retrieval-Augmented Generation (RAG) infrastructure with vector stores, embedding pipelines, and hybrid search. Covers ingestion, chunking strategies, reranking, and production deployment patterns.
- ▌ Refine Prompt Plan · majiayu000 bundleIteratively review and revise a prompt plan until no new findings survive evaluation. Runs /review-prompt-plan, /evaluate-findings, /apply-findings, then re-runs itself until stable. Use when the user asks to "refine the prompt plan", "refine this prompt plan", "iterate on the prompt plan", "tighten the prompt plan", or "improve the prompt plan".
- ▌ Sharpening Prompts · majiayu000 bundleUse when reviewing LLM prompts, skill instructions, subagent prompts, or any text that will instruct an AI. Triggers: "review this prompt", "audit instructions", "sharpen prompt", "is this clear enough", "would an LLM understand this", "ambiguity check". Also invoked by instruction-engineering, reviewing-design-docs, and reviewing-impl-plans for instruction quality gates.
- ▌
- ▌ Algebraic Rewriting · majiayu000 bundleCategory-theoretic graph rewriting with DPO, SPO, and SqPO pushouts for C-Sets. Declarative transformation of acset data structures.
- ▌ Arize Observability · majiayu000 bundleArize AI skill for production ML monitoring, embedding drift, and performance analysis.