majiayu000
- 75k skills
- 0 followers
- 567 repo stars
- 3 weeks ago last updated
- ▌ MCP Tool Discovery · majiayu000 bundleUse this skill when you need to discover MCP tool parameters, understand naming conventions, or debug tool call errors
- ▌ MCP Tool Generator · majiayu000 bundleGenerate new MCP tools for GitLab operations following the project's standardized pattern. Creates complete TypeScript files with imports, registration functions, Zod schemas, error handling, and format options. Supports simple CRUD operations, complex multi-action tools, and advanced patterns like discussion management. Use when "create mcp tool", "generate gitlab tool", "new tool for", "add tool to gitlab", or building new GitLab integration features.
- ▌ Reset Project · majiayu000 bundleRestore a project's .claude/ directory to the dotforge template from scratch, with backup and rollback option.
- ▌ Retro Resolve · majiayu000 bundleScan retro.md files across all skills, resolve open issues, and update retro entries.
- ▌ Short Publish · majiayu000 bundleEnd-to-end workflow for turning a local video into transcripts, burned subtitles, and scheduled multi-network posts via PostFlow CLI. Use when given a video path and publication date/time to transcribe, create copy for LinkedIn/X/IG/YouTube, upload the subtitled MP4, and schedule the content with `postflow`.
- ▌ Sop Generator · majiayu000 bundleA versatile skill for creating structured, executable Standard Operating Procedures (SOPs) from user input and context, applicable to general and ML-specific tasks.
- ▌ Sop Processor · majiayu000 bundleA general SOP for analyzing user requests based on offline conversation sources, extracting key questions as primary evidence, and providing structured, step-by-step outputs with action, checks, and fallbacks.
- ▌ Spec Executor · majiayu000 bundleExecute implementation specs with batched checkpoints. Follows specs exactly, stops on blockers, supports parallelization.
- ▌ Specsafe Done · majiayu000 bundleMark spec complete and archive. Moves spec from QA to COMPLETE stage.
- ▌
- ▌ Spool Archive · majiayu000 bundleArchive a completed change and update main specifications. Use when the user has finished implementing and wants to integrate the change into the main codebase.
- ▌ Sprint Status · majiayu000 bundleTrack parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.
- ▌ Swing Clarify · majiayu000 bundlePrevents premature execution on ambiguous requests. Analyzes request clarity using 5W1H decomposition, surfaces hidden assumptions, and generates structured clarifying questions before work begins. Use at the start of any non-trivial task, or when a request could be interpreted multiple ways. Triggers on "뭘 원하는건지", "요구사항 정리", "clarify", "what exactly", "scope", "requirements", "정확히 뭘", "before we start".
- ▌ Sync Template · majiayu000 bundleUpdate an existing project's Claude Code configuration against the current dotforge template, without losing local customizations.
- ▌ Task Complete · majiayu000 bundleComplete a beads task — mark done, create PR, merge, and clean up worktree. Use after all tests pass and verification is complete.
- ▌
- ▌ Transcription · majiayu000 bundleTranscribes audio and video files through case.dev with speaker diarization. Supports MP3, WAV, M4A, FLAC, OGG, WEBM, MP4 up to 5GB. Use when the user mentions "transcribe", "transcription", "deposition recording", "hearing audio", "speaker labels", or needs to convert audio/video to text.
- ▌ Vault Manager · majiayu000 bundleGeneral vault management operations. Organize files, clean up processed items, verify folder structure integrity, and manage the vault workflow. Use for vault maintenance, file organization, and workflow management tasks.
- ▌ Weekly Digest · majiayu000 bundleGenerate a weekly support digest and post it to [Slack](https://composio.dev/toolkits/slack)
- ▌ Work Pipeline · majiayu000 bundleTriggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.
- ▌ Workflow Auto · majiayu000 bundleExecute workflow-analyze → workflow-plan → workflow-execute → commit in sequence without intermediate approval (single commit). Use for small tasks that can be completed in one commit.
- ▌ Article Titles · majiayu000 bundleWrite titles for blog posts, deep dives, and hub articles. 15 proven formulas + 10 Commandments evaluation. Generate 10+ options, select best through systematic criteria.
- ▌ Bluebook Audit · majiayu000 bundleThis skill should be used when the user asks to 'audit footnotes', 'check Bluebook formatting', 'audit citations', 'run footnote audit', 'check my footnotes', 'bluebook audit', or needs systematic Bluebook compliance checking of a law review manuscript.
- ▌ Book Co Author · majiayu000 bundleStrategic thought-leadership book collaborator for founders, experts, and operators turning voice notes, fragments, and positioning into structured first-person chapters.
- ▌ Case Study Doc · majiayu000 bundleFormat a client result into a shareable case study document. Structure follows Client Background → The Challenge → What We Did → The Results → Key Takeaways. 500-800 words. Professional, results-focused, quotable. Use when user needs a "case study", "client success story", "results document", or "portfolio piece".
- ▌ Compose Digest · majiayu000 bundleCompose a formatted news digest from analyzed articles and trends. Uses memory search to retrieve articles and LLM to generate formatted output.
- ▌ Course Outline · majiayu000 bundleCreate a full course structure from a topic and transformation goal. Output includes course name, tagline, target student, prerequisites, module-by-module breakdown (3-7 modules), lessons per module (3-5 each), learning objectives per lesson, and estimated completion time. Use when user wants to "outline a course", "structure a course", "plan a curriculum", or "build a course".
- ▌ Dialogue Craft · majiayu000 bundleUse when writing or refining dialogue, establishing character voice, or layering subtext.
- ▌ Essay Pipeline · majiayu000 bundleUse when collaboratively writing a science blog essay through interactive thesis development, essay structuring, argument development, and paragraph writing with tiered fact-checking and voice matching.
- ▌ Newsroom Style · majiayu000 bundleEnforce AP Style and newsroom conventions for journalism writing. Use when writing news articles, editing drafts, creating headlines, or converting notes into publishable copy. Ensures professional standards for attribution, numbers, dates, and formatting.
- ▌ Rule Expertise · majiayu000 bundleWrite effective instructions and prompts. Use when creating documentation, writing guidelines, establishing project rules, or crafting any directional communication. Keywords: instructions, guidelines, prompt engineering, documentation, rules. Not for code implementation, debugging, or non-instructional writing.
- ▌ Speech Writing · majiayu000 bundleSpeech writing is the art and craft of creating content specifically designed to be delivered orally to an audience.
- ▌ Voice And Tone · majiayu000 bundleDefines brand voice persona and tone calibration using persona and positioning data to produce a reusable meta-prompt for copywriting.
- ▌ Voice Generate · majiayu000 bundleGenerates text in a learned writing voice. Use when drafting content that must match a specific author's style profile extracted by voice-extract.
- ▌ Writing Review · majiayu000 bundleThis skill should be used when the user asks to 'review my writing', 'check document structure', 'find issues in draft', 'review transitions', or needs hierarchical document review that produces REVIEW.md for /writing-revise.
- ▌ Writing Revise · majiayu000 bundleThis skill should be used when the user asks to 'revise writing', 'fix review issues', 'polish draft', 'apply review feedback', 'complete writing workflow', or after /writing-review produces REVIEW.md with issues to fix.
- ▌ Youtube Script · majiayu000 bundleWrite YouTube video scripts that sound human, not AI-generated. Creates hook-driven scripts with conversational delivery, pattern interrupts, and authentic voice. Use when user needs a "YouTube script", "video script", or wants to write content for YouTube that doesn't sound generic.
- ▌ Ac Commit Manager · majiayu000 bundleManage git commits for autonomous coding. Use when committing feature implementations, creating descriptive commits, managing git workflow, or handling version control.
- ▌ Agent Development · majiayu000 bundleThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
- ▌ Agent Implementer · majiayu000 bundleImplementation guidance for creating individual agents in the Arcanea system with proper structure, capabilities, and integration.
- ▌ Agent Reliability Safety · majiayu000 bundleDesign reliable, safe, and trustworthy agent systems that fail gracefully and operate within bounds. Use when building guardrails, handling edge cases, preventing harmful outputs, monitoring for failures, implementing safety constraints, or designing error recovery. Covers failure modes, constraint systems, oversight mechanisms, and safety validation.
- ▌ Agentic Framework · majiayu000 bundleInfinite Improvement Framework: Move from Probabilistic Agents to Deterministic Workflows.
- ▌ Agents Md Manager · majiayu000 bundleThis skill should be used when creating, auditing, or maintaining AGENTS.md files and Codex CLI configuration for any project—including initializing AGENTS.md for cross-agent compatibility (Codex, Cursor, Copilot, Devin, Jules, Amp, Gemini CLI), generating config.toml or .rules files, scaffolding .agents/skills/, converting CLAUDE.md to AGENTS.md, or auditing existing agent configs for bloat and staleness. Complementary to codex-orchestrator (which executes subagents; this skill creates the config files they consume).
- ▌
- ▌ Aget Enhance Spec · majiayu000 bundleGuide through the 7-phase specification enhancement lifecycle (Phases 0-6 from L622). Governs creating, updating, wiring, and validating AGET specifications.
- ▌ Cfn Agent Tooling · majiayu000 bundleAgent development tools - generation and validation. Use when creating new agent templates from scaffolding, or validating and linting existing agent profiles for correctness and completeness.
- ▌ Covenant Patterns · majiayu000 bundleApply covenant principles as design constraints across all core systems. Use when building agents, prompts, recipes, artifacts, or multi-agent architectures.
- ▌ Deepagents Memory · majiayu000 bundle在 Deep Agents 中实现长期内存，使用 StoreBackend、CompositeBackend 和 InMemoryStore 进行跨会话的持久化数据存储。
- ▌ Deepagents Skills · majiayu000 bundle在 Deep Agents 中创建和使用自定义技能，实现渐进式披露、SKILL.md 格式和 Agent Skills 协议。
- ▌ Developing Agents · majiayu000 bundleThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
- ▌
- ▌ Improve Agents Md · majiayu000 bundleGenerate and update AGENTS.md (CLAUDE.md) for projects using a single template with dynamic per-type tooling injection. Auto-detects project type and renders the appropriate Environment & Tooling section. Triggers on keywords: improve agents, generate agents.md, update agents.md, setup claude.md, bootstrap agents
- ▌ Ralph Specum Help · majiayu000 bundleThis skill should be used only when the user explicitly asks to use `$ralph-specum-help`, or explicitly asks Ralph Specum in Codex for help or command guidance.
- ▌ Ralph Wiggum Loop · majiayu000 bundleMulti-step autonomous plan execution with bounded iteration (max 10), state persistence, dependency checking, error retry with exponential backoff, and human escalation on failure. The "Ralph Wiggum loop" enables AI agents to execute complex multi-step plans autonomously while maintaining safety bounds and progress tracking. Includes MCP action invocation, step dependency validation, graceful error recovery, and comprehensive audit logging. Use when: (1) implementing autonomous multi-step task execution, (2) building plan execution engines with retry logic, (3) creating bounded loops with state persistence, (4) handling step dependencies in workflows, (5) implementing human escalation patterns for blocked tasks.
- ▌ Tool Use Patterns · majiayu000 bundlePatterns for Claude tool use including tool definition schemas, multi-tool orchestration, parallel tool calls, error handling, and result formatting. Use when the user is defining tools for Claude, building agentic workflows with tool calling, handling tool errors, or implementing multi-step tool pipelines.
- ▌ Add Image Vision · majiayu000 bundleAdd image vision to NanoClaw agents. Resizes and processes WhatsApp image attachments, then sends them to Claude as multimodal content blocks.
- ▌ Adversarial Spec · majiayu000 bundleIteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree. Use when user wants to write or refine a specification document using adversarial development.
- ▌ API AI Langchain · majiayu000 bundleLangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing
- ▌ API AI Promptfoo · majiayu000 bundleTesting and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation
- ▌ API AI Replicate · majiayu000 bundleReplicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training
- ▌
- ▌ Discover Updates · majiayu000 bundleDiscover Claude and Claude Code CLI updates, improvements, tools and best practices from official sources and community. Use when user asks "what's new?", "/discover-updates", or explicitly requests Claude/CLI updates.
- ▌ Exps Performance · majiayu000 bundleDocumentation for the main LLM performance experiments (exps_performance)
- ▌ Function Calling · majiayu000 bundleLLM function calling and tool use patterns. Use when enabling LLMs to call external tools, defining tool schemas, implementing tool execution loops, or getting structured output from LLMs.
- ▌ Grill AI Mastery · majiayu000 bundleHybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on AI", "stress-test my Claude usage", "evaluate this candidate's AI engineering", or otherwise asks for an AI-collab skill assessment. User-only — never auto-invoke.
- ▌ Langchain Models · majiayu000 bundleInitialize and use LangChain chat models - includes provider selection (OpenAI, Anthropic, Google), model configuration, and invocation patterns
- ▌ Langfuse Strands · majiayu000 bundleIntegrate Langfuse observability with AWS Strands Agents for comprehensive tracing, monitoring, and debugging of AI agent applications. Use when building Strands agents that need production observability, when debugging agent behavior, when tracking costs/latency/token usage, or when setting up OpenTelemetry-based tracing for Strands.
- ▌ Langgraph Python · majiayu000 bundleDesign and build AI agents with LangGraph. Use when building ReAct agents, multi-agent systems, workflow orchestration, human-in-the-loop patterns, or state machine workflows.
- ▌
- ▌ Paper Autoraters · majiayu000 bundleRun the four paper-quality autoraters from PaperOrchestra (arXiv:2604.05018, App. F.3) — Citation F1 (P0/P1 partition + Precision/Recall/F1), Literature Review Quality (6-axis 0-100 with anti-inflation rules), SxS Overall Paper Quality (side-by-side), and SxS Literature Review Quality (side-by-side). TRIGGER when the user asks to "score this paper draft", "evaluate against the benchmark", "compare two papers", or "run the autoraters".
- ▌ Prompt Architect · majiayu000 bundleCreate and enhance prompts, system instructions, and principle files. Capabilities: transform verbose prompts, add patterns/heuristics, optimize token usage, structure CLAUDE.md principles, improve agent/persona definitions, apply prompt engineering techniques (CoT, few-shot, ReAct). Actions: create, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, system prompt, CLAUDE.md, principle files, instruction optimization, agent prompt, persona prompt, token efficiency, prompt structure, workflow prompts, rules, constraints, few-shot, chain-of-thought. Use when: creating new prompts, enhancing principle files, improving system instructions, optimizing CLAUDE.md, restructuring verbose prompts, adding patterns to workflows, defining agent behaviors.
- ▌
- ▌ Semantic Caching · majiayu000 bundleRedis semantic caching for LLM applications. Use when implementing vector similarity caching, optimizing LLM costs through cached responses, or building multi-level cache hierarchies.
- ▌ Smart Pole Instructor · majiayu000 bundleUse when a user provides a vague prompt and needs structured clarification to produce a precise master prompt.
- ▌ Battery Electrode · majiayu000 bundleComputational workflows for battery electrode characterization: voltage profiles, ion transport, and electrochemical stability.
- ▌ Ce Classification · majiayu000 bundleHandle CE classification workflows for binary and multiclass prediction semantics and class-focused explanation behavior.
- ▌ Cellxgene Context · majiayu000 bundleGuide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when users need cell-type-specific expression context for ENCODE regulatory data, want to deconvolve bulk ENCODE signals, or validate regulatory elements at single-cell resolution. Trigger on: CellxGene, single-cell atlas, cell type expression, Census, cell type specificity, single-cell context, scRNA-seq atlas.
- ▌ Create Classifier · majiayu000 bundleTrain task-specific classifiers for the extractor pipeline. Supports vision, text, and hybrid classifiers with GRPO training and execution feedback. Includes data collection, confidence-based routing, and shadow deployment.
- ▌ Create Intent Map · majiayu000 bundleTrain LoRA adapters for converting natural language queries into structured QuerySpec JSON.
- ▌ Haystack Pipeline · majiayu000 bundleHaystack NLP pipeline configuration for document processing and QA
- ▌ Minicoil Training · majiayu000 bundleminiCOIL v1 sparse neural retrieval model training methodology: per-word linear layer training with triplet loss, word vocabulary from frequency-filtered English words, sparse retrieval with jina-embeddings-v2-small-en encoder, sparse embedding training pipelines, OpenWebText sentence extraction for self-supervised training, semi-hard triplet mining, and evaluation on BEIR benchmarks. English-only miniCOIL v1 (jina-embeddings, 30k words, mxbai-embed-large-v1 mining). Reference for building, training, and deploying sparse neural retrieval models compatible with inverted indexes and Qdrant.
- ▌ Ml Model Training · majiayu000 bundleTrain ML models with scikit-learn, PyTorch, TensorFlow. Use for classification/regression, neural networks, hyperparameter tuning, or encountering overfitting, underfitting, convergence issues.
- ▌ Protein Phylogeny · majiayu000 bundleProtein (gene) phylogeny inference pipeline: generates a .qmd analysis script that performs alignment, optional trimming, and tree building. Use when building phylogenetic trees from protein sequences, aligning protein families, running IQ-TREE or MAFFT for phylogenetics, or when the user says "gene tree" or "protein tree." Covers single domains, whole proteins, and multi-domain proteins across deep evolutionary distances (sponges, animals, eukaryotes). Do NOT load for nucleotide-only phylogenies, species trees from concatenated matrices, or tree visualization (use tree-formatting skill for that).
- ▌ Review Richtlinie · majiayu000 bundlePruefung: Internationaler Bezug und Schnittstellen im Plugin ki governance; schärft Rollen, Belege, Fachnormen, Risiken, Gegenargumente und nächsten verwertbaren Schritt statt austauschbarer Standardprüfung: eigenständiges Prüffeld mit Norm-/Quellencheck, Risikoampel und verwertbarem Output.
- ▌ Self Optimization · majiayu000 bundleSONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.
- ▌ Peak Calling · majiayu000 bundlePerform peak calling for ChIP-seq or ATAC-seq data using MACS2, with intelligent parameter detection from user feedback. Use it when you want to call peaks for ChIP-seq data or ATAC-seq data.
- ▌ Aeo Data Guide · majiayu000 bundleHow to think about AirOps AEO data — interpreting metrics, handling ambiguous asks, routing to the right agent.
- ▌ Aitask Explain · majiayu000 bundleExplain files in the project: functionality, usage examples, and code evolution history traced through aitasks.
- ▌
- ▌ Analyze Skills · majiayu000 bundleAnalyze ~/.claude session files to find unused agent skills and reduce context token waste. Scans subagent JSONL files for injected skills and cross-references with agent responses.
- ▌ Analyzing Gaps · majiayu000 bundleCompare user expectations (UTCs) with code reality to identify gaps. Use when you need to understand discrepancies between what users expect and what code actually does.
- ▌
- ▌ Audit Coverage · majiayu000 bundleAudit MVP component, platform mechanism, and advanced mechanism coverage for analyzed agents, identifying gaps and suggesting next steps
- ▌ Audit Friction · majiayu000 bundleScan Claude Code project logs for friction patterns — repeated failures, approach loops, tool errors, misunderstanding cycles, and stuck workflows. Categorizes and counts friction events to surface what causes the most resistance. Use when user says "audit friction", "find friction", "friction audit", or "what keeps going wrong".
- ▌ Batch Analysis · majiayu000 bundleGuide for multi-experiment batch operations: QC screening, batch download, comparison, and report generation across many ENCODE experiments simultaneously. Use when users need to process 5+ experiments together, create experiment comparison tables, perform batch quality checks, or generate summary reports. Trigger on: batch analysis, multiple experiments, bulk processing, experiment comparison, batch QC, multi-sample, batch download, experiment table, summary report, collection analysis.
- ▌ Calendar Stats · majiayu000 bundleShow calendar statistics — meeting volume, hours in meetings, busiest days, top calendars, and meeting load by day of week. Use when user asks how many meetings they have, how busy they are, or wants a time audit.
- ▌ Changelog Scan · majiayu000 bundleScan Claude Code changelog for new versions, features, and changes. Fetches official docs, parses release notes, and generates structured update report.
- ▌ Convo Analysis · majiayu000 bundleAnalyze conversation flows for behavioral patterns. Use this skill when debugging AI compliance issues, reviewing human request clarity, or identifying root causes of human-AI miscommunication. Produces sanitized reports safe to share.
- ▌ Customer Brief · majiayu000 bundleGenerate a concise, executive-ready digest of internal touchpoints and external intelligence for a named customer.
- ▌ Workflow Plan · majiayu000 bundleGenerate implementation plan with commit-level tasks. Use after workflow-analyze to create detailed, vertically-sliced commit plan.