majiayu000
- 75k skills
- 0 followers
- 567 repo stars
- 3 weeks ago last updated
- ▌ Ase Meta Proximity · majiayu000 bundleDetermine the conceptual proximity of a topic -- its parent topic, its most relevant sibling topics, and its most relevant child topics -- optionally grounded in Internet/Web facts and optionally navigable in an interactive loop. Use when the user wants to explore the conceptual neighborhood of a topic, or mentions "proximity" or "related topics".
- ▌ Autonomous Builder · majiayu000 bundleRun headless implementation from idea to artifact. Use when user says 'build in background', 'autonomous', 'headless', or wants hands-off execution.
- ▌ Bmad Agent Builder · majiayu000 bundleBuilds, edit or validate Agent Skill through conversational discovery. Use when the user requests to "Create an Agent", "Optimize an Agent" or "Edit an Agent".
- ▌ Claude Superpowers · majiayu000 bundleForce Claude Code to work like a senior developer: plan before coding, work in isolation, write tests first, and review its own output twice before presenting it. Use when asked to enable superpowers mode, activate the superpowers framework, or turn on superpowers for this session. Installs a 4-stage framework — Plan, Isolate, Test First, Double Review — that prevents Claude from sprinting into broken code.
- ▌ Continual Learning · majiayu000 bundleGuide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up learning infrastructure for agents.
- ▌ Curator Repo Learn · majiayu000 bundleLearn patterns from a specific GitHub repository. Clones, analyzes code structure, extracts patterns, and populates procedural memory. Use for: targeted learning from known quality repos, quick knowledge acquisition, specific pattern extraction. Triggers: /repo-learn, /curator-repo-learn, 'learn from repo'.
- ▌
- ▌ Langgraph Parallel · majiayu000 bundleLangGraph parallel execution patterns. Use when implementing fan-out/fan-in workflows, map-reduce over tasks, or running independent agents concurrently.
- ▌
- ▌ Nw Design Patterns · majiayu000 bundle7 agentic design patterns with decision tree for choosing the right pattern for each agent type
- ▌ Ralph Wiggum Codex · majiayu000 bundleUse when a coding task needs an objective-first long-running loop with fresh-context work and review phases, explicit acceptance criteria, resumable state, and real blocked handling.
- ▌ Request Classifier · majiayu000 bundleClassify any user request into a structured format for prompt generation. Use this skill whenever you need to understand what type of task a request represents, determine complexity, decide whether planning is needed, or route a request to the right skills and agent strategy. Trigger on: any request that needs to be analyzed before generating a Claude Code prompt, when someone says 'classify this', 'what kind of task is this', when the prompt-generator or prompt-router skills need input classification, or when deciding between solo agent vs subagent vs tmux team execution.
- ▌
- ▌ Spawn Investigator · majiayu000 bundleInvestigate a codebase question using an isolated subagent. Use when you need to read many files without bloating the main context.
- ▌ Spec Driven Agents · majiayu000 bundleCreate DevForgeAI-aware Claude Code subagents with structural anti-skip enforcement (Execute-Verify-Record pattern) across all 6 phases. Prevents token optimization bias through lean orchestration, per-phase reference loading, checkpoint persistence, and artifact verification. Use when user runs /create-agent command, requests custom subagent creation with framework integration, or says "create a subagent" or "generate an agent". Supports guided, template, domain, and custom spec modes. Do NOT use for skill creation (use skill-creator) or command creation (use manual workflow).
- ▌ Acm Observability · majiayu000 bundleAgent-actionable reference for ACM-AI's 6-tool observability stack. Teaches how to query traces, inspect graph state, debug Pydantic failures, and analyze costs programmatically.
- ▌ API AI Cohere Sdk · majiayu000 bundleOfficial Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, streaming, and model selection
- ▌ API AI Elevenlabs · majiayu000 bundleElevenLabs voice AI SDK patterns for TypeScript/Node.js -- text-to-speech, streaming, voice cloning, speech-to-speech, pronunciation control, and conversational AI
- ▌ API AI Llamaindex · majiayu000 bundleLlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in TypeScript
- ▌ API AI Openai Sdk · majiayu000 bundleOfficial OpenAI SDK patterns for TypeScript/Node.js — client setup, Chat Completions, Responses API, streaming, structured outputs, function calling, embeddings, vision, audio, and production best practices
- ▌ Authoring Prompts · majiayu000 bundleInvoke this skill first when authoring any AI agent instructions. Foundational principles for writing LLM instructions (skills, CLAUDE.md, rules, commands). Covers token economics, imperative language, formatting for LLM parsing, emphasis modifiers, terminology consistency, and common anti-patterns.
- ▌ Auto Consultation · majiayu000 bundleClaude Code自動相談システム。行き詰まった時にSonnet/Opus APIに相談する。2回失敗で自動提案、ハイブリッドエスカレーション。
- ▌ Benchmark Fetcher · majiayu000 bundleFetch benchmark performance data from 6 leaderboard websites using Playwright MCP and update model manifests with the latest scores. Supports SWE-bench, TerminalBench, SciCode, LiveCodeBench, MMMU, MMMU Pro, and WebDevArena benchmarks.
- ▌ Prompt Coach · majiayu000 bundleAnalyze your Claude Code session logs to improve prompt quality, optimize tool usage, and become a better AI-native engineer.
- ▌ Elevenlabs Voices · majiayu000 bundleHigh-quality voice synthesis with 18 personas, 32 languages, sound effects, batch processing, and voice design using ElevenLabs API.
- ▌ Enhancing Prompts · majiayu000 bundleAnalyze prompt quality, classify task type, and enhance with optimized templates while preserving original intent. Provides transparent feedback showing what was enhanced and why.
- ▌ Friction Detector · majiayu000 bundleDetect friction signals; graduate patterns into rules. Use for session retrospectives.
- ▌ Gemini Specialist · majiayu000 bundleUse Gemini CLI for massive context tasks (1M-2M tokens). Orchestrator evaluates safety and directs usage patterns intelligently.
- ▌ Image Nano Banana · majiayu000 bundleGenerate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
- ▌ Langgraph Routing · majiayu000 bundleLangGraph conditional routing patterns. Use when implementing dynamic routing based on state, creating branching workflows, or building retry loops with conditional edges.
- ▌ Microsoft Foundry · majiayu000 bundleUse this skill to work with Microsoft Foundry (Azure AI Foundry): deploy AI models from catalog, build RAG applications with knowledge indexes, create and evaluate AI agents, manage RBAC permissions and role assignments, manage quotas and capacity, create Foundry resources. USE FOR: Microsoft Foundry, AI Foundry, deploy model, model catalog, RAG, knowledge index, create agent, evaluate agent, agent monitoring, create Foundry project, new Foundry project, set up Foundry, onboard to Foundry, provision Foundry infrastructure, create Foundry resource, create AI Services, multi-service resource, AIServices kind, register resource provider, enable Cognitive Services, setup AI Services account, create resource group for Foundry, RBAC, role assignment, managed identity, service principal, permissions, quota, capacity, TPM, deployment failure, QuotaExceeded. DO NOT USE FOR: Azure Functions (use azure-functions), App Service (use azure-create-app), generic Azure resource creation (use azure-create-app).
- ▌ Multi AI Research · majiayu000 bundleParallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says "多 AI 调研", "交叉验证", "独立共识", "三脑调研", "multi-ai research", "parallel research", "cross-validate", or needs deep research that benefits from internal data + external 2026 consensus. NOT for quick factual Q&A, pure code reasoning, or tasks needing deep project context.
- ▌ Persona Detection · majiayu000 bundleIntelligent project persona identification using priority chain detection with LLM and heuristic fallback
- ▌ RAG Hybrid Search · majiayu000 bundleHybrid search combining semantic and keyword retrieval for RAG pipelines. Implement BM25 + dense vector search with fusion strategies.
- ▌ AI Local Model Ops · majiayu000 bundleRuns local and self-hosted LLM workflows with Ollama, LM Studio, MLX, Open WebUI, llamafile, and adapters. Use when operating private model stacks.
- ▌ AI Ml Data Science · majiayu000 bundleEnd-to-end data science patterns (modern best practices): problem framing -> data -> EDA -> feature engineering (with feature stores) -> modelling -> evaluation -> reporting, plus SQL transformation (SQLMesh). Emphasizes MLOps integration, drift monitoring, and production-ready workflows.
- ▌ AI Toolkit Trainer · majiayu000 bundleTrain custom LoRAs with ostris AI-Toolkit — covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to train a WAN or Z-Image LoRA; covers local + RunPod setup, dataset prep, key params, and using the result in a ComfyUI workflow.
- ▌ Benchmark Datasets · majiayu000 bundleStandard datasets and benchmarks for evaluating AI security, robustness, and safety
- ▌ Ce Factual Explain · majiayu000 bundleGenerate factual CE explanations and select the correct guarded versus standard factual workflow.
- ▌ Fetch Arxiv Papers · majiayu000 bundleFetch recent AI/ML research papers from arXiv RSS feeds and store them in memory. Uses RSS tool for fetching and memory MCP for storage and deduplication.
- ▌ Genetic Algorithms · majiayu000 bundleGenetic Algorithms for AI optimization - EvoPrompt, hyperparameter tuning, evolutionary strategies.
- ▌ Hugging Face Paper Publisher · majiayu000 bundlePublish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
- ▌ Monitor Experiment · majiayu000 bundleMonitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.
- ▌ RAG Accuracy Skill · majiayu000 bundleMeasure RAG answer quality through three core metrics: Faithfulness (accuracy to context), Relevance (retrieval quality), and Answer Quality (overall usefulness).
- ▌ Sprint Outcomes Pikarobot · majiayu000 bundleReal sprint results in PikaRobot: velocity, completed work, blockers, team performance, process changes impact. Triggers: sprint, velocity, sprint result, sprint outcome, sprint retrospective, sprint review, productivity, completion rate
- ▌ Strategy Sprint · majiayu000 bundleCreate product strategy in 1 day, 1 week, or 1 month timeframes. Progressive strategy development framework.
- ▌ Support Runbook · majiayu000 bundleWrite a support runbook for handling a recurring issue type consistently. Use when asked to write a support runbook, a troubleshooting playbook for agents, a handling guide for a common issue, or a tier-1 response procedure. Produces a runbook — issue identification, triage/severity, step-by-step diagnosis & resolution, decision tree, when/how to escalate, and the customer-comms templates — so any agent resolves it the same way.
- ▌ Team Prioritize · majiayu000 bundleOrder backlog items using data-driven prioritization frameworks.
- ▌ Vision Document · majiayu000 bundleCreates vision documents through structured 5-phase discovery process. Guides through problem discovery, solution exploration, user needs analysis, future & scope planning, and document generation. Use when user wants to create a vision document for a feature, needs to define strategic context and high-level goals, or is starting feature development and needs to establish the "why" and "what" before technical details. Follows established feature development process with lean, focused documents (100-150 lines max) that flow from general problems to specific scope.
- ▌ Wsl Screenshots · majiayu000 bundleView Windows screenshots from WSL. Use when user mentions screenshot, screen capture, or asks to look at an image they just took.
- ▌ Add Workiq · majiayu000 bundleAdds Work IQ (M365 Copilot Search) to a Power Apps code app via the Work IQ Copilot MCP connector (shared_a365copilotchatmcp), then wires up a production-ready McpSession wrapper for AI-powered, knowledge-grounded search and chat. Use when integrating Microsoft 365 Copilot search/chat. The CopilotChat tool searches internal Microsoft 365 content (documents, emails, chats, sites, files) across your organization — prefer workload-specific tools (SharePoint, OneDrive, Teams, Mail) when the workload is explicit; do not use it for general knowledge, news, public web, or external information.
- ▌ AI Standup · majiayu000 bundleUse when preparing daily standup notes or summarizing recent PR and commit activity for team updates.
- ▌
- ▌ Compdf Ocr · majiayu000 bundleRecognize and extract text from scanned PDFs and images with ComPDF OCR workflows. Use for OCR, searchable PDF generation, text recognition, table recognition, and scanned-document extraction requests.
- ▌ Getterdone · majiayu000 bundleHire a human gig worker via USD bounty for tasks you cannot complete yourself—either because they require physical presence (storefront photos, on-site verification, deliveries, errands) or specialized human skill (writing, proofreading, design, translation, video). The worker submits photo/text proof; you approve to release payment. See §0 for the full list of trigger phrases.
- ▌ Neat Freak · majiayu000 bundleEnd-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots. 会话结束后对项目文档和记忆进行洁癖级审查与同步。MUST trigger when the user says: "sync up", "tidy up docs", "update memory", "clean up docs", "/sync", "/neat", "同步一下", "整理文档", "整理一下", "更新记忆", "梳理一下", "收尾", "这个阶段做完了", "新人能直接上手", or any phrase suggesting a dev milestone where knowledge needs reconciliation. Also trigger when the user reports stale docs, conflicting memories, or wants a clean handoff to teammates or other agents. Bare "整理" / "tidy" with prior dev context counts — do not under-trigger. Cross-platform: works on Claude Code, OpenAI Codex, OpenCode, and OpenClaw.
- ▌ Rune Tasks · majiayu000 bundleManage hierarchical task lists using the rune CLI tool. Create, update, and organize tasks with phases, subtasks, and status tracking.
- ▌ Shopaholic · majiayu000 bundle专为希望借助 AI 在中国大陆主流电商平台（淘宝、天猫、京东、拼多多、抖音电商等）进行理性消费的用户打造的循证购物决策顾问。遵循“先证据后观点、先澄清后推荐、先排除后排序”原则，支持需求澄清、分层比对、全网劝退与候选终审四种模式，输出包含底层原理科普、硬件用料对比、避坑清单与多方信源佐证的决策报告。
- ▌ Vault Tasks · majiayu000 bundleGet all tasks from the vault with filtering options. Triggers on "all tasks", "task list", "show tasks", "find tasks".
- ▌
- ▌ Tasks File · majiayu000 bundleThis skill should be used when managing the file-based task tracking system in the tasks directory. It provides workflows for creating tasks, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
- ▌ Tasks Load · majiayu000 bundleThis skill should be used when loading tasks from a project directory into the current Claude Code session. It reads task JSON files from session subdirectories, recreates them in the current session, and sets the active project marker.
- ▌ Tasks Sync · majiayu000 bundleThis skill should be used when syncing current session tasks to a project directory. It exports all tasks from the current Claude Code session to JSON files in the project's tasks directory, enabling persistence across sessions.
- ▌ Todoist Rs · majiayu000 bundleTodoist: tasks, projects, labels, filters, reminders, Karma, API, IFTTT/Zapier integration
- ▌ 1k Code Quality · majiayu000 bundleCode quality standards — lint (eslint/oxlint), type check (tsc), pre-commit hooks, and comment conventions. All comments must be in English.
- ▌ Agent Benchmark · majiayu000 bundleFramework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when evaluating agent changes, auditing quality, or establishing performance baselines.
- ▌ Ase Meta Review · majiayu000 bundlePerform a holistic, human-reviewer-style critique of the currently staged Git changes and emit an approve/reject verdict with prioritized, severity-tagged, line-cited findings. Use when the user wants the staged diff "reviewed", "critiqued", or "code-reviewed" before committing.
- ▌ Audit Architect · majiayu000 bundleArchitecture audit — layer separation, ES consistency, dependency direction, branching readiness
- ▌ Audit Claude Md · majiayu000 bundleAudit and refactor CLAUDE.md files to eliminate bloat, enforce context engineering best practices, and create folder-level CLAUDE.md files for complex domain-specific instructions.
- ▌ Ce Plugin Audit · majiayu000 bundleAudit plugin implementations for registry trust rules, metadata validity, and ADR contract compliance.
- ▌ Gsd Code Review Fix · majiayu000 bundleAuto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.
- ▌ Code Review Web · majiayu000 bundleReview web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug, build error, broken, not working, why is X failing, check this code, security check, PR review, audit code, refactor. Also triggers when investigating 4xx or 5xx errors, deploy failures, environment variable issues, and CMS integration problems.
- ▌ Codebase Review · majiayu000 bundleHolistic read-only codebase health review to find architecture drift, dead code, test gaps, and doc gaps.
- ▌ Convex Reviewer · majiayu000 bundleReview Convex code for security, runtime correctness, performance, schema design, and AgentForge-specific architectural boundaries.
- ▌ Compact Reviewer Critical Issues · majiayu000 bundleUse when reviewing Compact contracts for bugs, logic errors, assertion issues, type mismatches, dead code, unreachable paths, or control flow problems.
- ▌ Dehallucination · majiayu000 bundleUse when verifying that claims, references, or assertions are grounded in reality rather than fabricated. Triggers: 'does this actually exist', 'is this real', 'did you hallucinate', 'verify these references', 'check if this is fabricated', 'reality check', 'ground truth'. Also invoked as quality gate by roundtable feedback, the Forged workflow, and after deep-research verification.
- ▌ Dev Docs Review · majiayu000 bundleReview all project documentation for staleness — READMEs, skills, plans, CLAUDE.md, project structure trees
- ▌ Dry Walkthrough · majiayu000 bundleValidate an implementation plan by tracing through each change without implementing. Use when user says dry walkthrough, drywalkthrough, validate plan, or check plan. Identifies gaps, fixes the plan directly, and reports changes to terminal.
- ▌ External Review · majiayu000 bundleExternal AI code review using Codex or Gemini. Reads project.yaml to determine which provider to use for frontend vs backend tasks. Includes hallucination detection to avoid blindly applying AI suggestions.
- ▌ Factcheck Guard · majiayu000 bundleUse this skill when making any factual claim about the codebase — existence, absence, or behavior. Converts the claim-verification rule into a systematic action protocol that prevents false assertions from grep-only results.
- ▌
- ▌ Fec Code Review · majiayu000 bundleUse when the user asks for general frontend code review, PR review, merge-readiness assessment, architecture maintainability, type-safety, rendering/state risks, style consistency, testability gaps, or a cross-cutting review summary. Delegate deep security, accessibility, E2E, or performance investigations to their specialized skills; Chinese triggers include 代码审查, 代码评审, review.
- ▌ Fix Review Code · majiayu000 bundleCorriger automatiquement les problemes identifies par /code-review en se basant sur les regles et conventions evan-workflow.
- ▌ Giving Feedback · majiayu000 bundleTurn a vague concern into specific, kind, actionable feedback. Use when asked to give feedback, write a feedback note, prepare to tell someone something hard about their work, or coach a report/peer. Produces ready-to-deliver feedback structured on situation–behaviour–impact, separating observation from judgement, with the change requested and an opening line — calibrated to praise or constructive.
- ▌ Installer Packs · majiayu000 bundleUse when installing a model family from an installer pack, or when building/deriving a new pack from an upstream installer or a workflow JSON. Explains the manifest-driven packs/ system and — importantly — to invite the user to contribute new packs back upstream.
- ▌ Linting Go Code · majiayu000 bundleLint and format Go code. Use when you need to run linters, fix lint errors, format code, or understand why a linter is complaining.
- ▌ Lp Do Factcheck · majiayu000 bundleVerify the accuracy of statements in markdown documents by auditing the actual repository state. Directly fix inaccuracies in-place rather than producing a separate report.
- ▌ Paranoid Review · majiayu000 bundleParanoid staff-engineer code review. Finds the bugs that pass CI but blow up in production. Reads the diff like someone who has been paged at 2am and is determined to never be paged again.
- ▌ Pre Push Checks · majiayu000 bundleRun all required checks before pushing code. Use before committing or when validating that changes are correct.
- ▌ Verification Quality Assurance · majiayu000 bundleComprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
- ▌ Bio Read Qc Quality Reports · majiayu000 bundleGenerate and interpret quality reports from FASTQ files using FastQC and MultiQC. Assess per-base quality, adapter content, GC bias, duplication levels, and overrepresented sequences. Use when performing initial QC on raw sequencing data or validating preprocessing results.
- ▌ Reality Checker · majiayu000 bundleStops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness
- ▌ Resolve Dispute · majiayu000 bundleResolves stuck review findings via a put-up-or-concede exchange. Invoked by the facilitator when a finding survives arbitration without new evidence.
- ▌ Review Artifact · majiayu000 bundle[Code Quality] Review artifact quality before handoff. Use to verify PBIs, designs, stories meet quality standards.
- ▌ Review Deferred · majiayu000 bundleReview deferred verification items. Use when you want to check or clear the deferred review queue without waiting for project completion.
- ▌ Review Document · majiayu000 bundleThis skill should be used to refine brainstorm or plan documents before proceeding to the next workflow step. It applies when a brainstorm or plan document exists and the user wants to improve it.
- ▌ Review Findings · majiayu000 bundleAddresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification. Delegates to the Forja (Dev) agent.
- ▌ Review Remix V2 · majiayu000 bundleComprehensive Remix v2 code review with optional parallel agents. Detects Remix v2 in package.json, loads relevant review skills, runs verification protocol.
- ▌ Review Rust All · majiayu000 bundleRun all review-rust* skills as a comprehensive code review. Applies review-rust-code (best practices, type-driven design, error handling), review-rust-async-patterns (tokio concurrency, cancellation safety, channels), and review-rust-memory (allocation reduction, data layout, Feather-Flow-specific patterns). Use after completing a feature or before opening a PR.
- ▌ Skill Stocktake · majiayu000 bundleUse when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.