AI & ML

yalishevant Bundle

Diagnose Kotlin + Spring failures from stack traces, startup logs, runtime logs, and related metric anomalies, then separate root cause from wrapper exceptions and propose safe next steps. Use when the application fails to start, an endpoint crashes, logs are noisy or deeply nested, or the agent must produce both a quick mitigation and a proper long-term fix without guessing.

yalishevant Bundle

Inspect a Kotlin + Spring repository before making changes or answering implementation, debugging, build, architecture, or review questions. Use when the agent must map modules, Spring Boot/Kotlin/Gradle/JDK versions, compiler plugins, profiles, dependencies, runtime stack, and architectural boundaries so later advice stays compatible with the real project.

yalishevant Bundle

Model Kotlin persistence code correctly for Spring Data JPA and Hibernate, including entity design, relationships, fetch plans, repository queries, lazy loading, and common performance traps. Use when creating or reviewing entities and repositories, diagnosing N+1 or `LazyInitializationException`, placing indexes and uniqueness rules, or preventing Kotlin-specific ORM bugs such as `data class` entities and broken `equals` or `hashCode`.

smit1980 Bundle

Combined Avito listing optimization skill that orchestrates two MCP backends: `elchin92/avito-mcp` for official Avito API access to the user's own account, listings, stats, chats, and controlled write actions; and `Ascard/mcp-avito` for browser-based public-market research across competitor listings. Use when Codex needs to audit Avito ads, find stronger keywords from live search results, compare competitors, rewrite titles and descriptions, suggest price and promotion changes, guide MCP setup, or apply approved listing updates. Especially useful for service offers such as AI and neural-network training, corporate workshops, ChatGPT and AI implementation, and business automation services.

nisar999 Skill

Develops ML, MLOps, RAG, and LLM applications with reproducible experiments and production serving. Use when building models, RAG pipelines, prompt engineering, evaluation, or model deployment.

yalishevant Bundle

Design and implement consistent API validation and error-handling behavior for Kotlin plus Spring services. Use when defining error payloads, mapping framework and domain exceptions, standardizing HTTP status codes, adding `@ControllerAdvice`, preventing internal-detail leakage, or ensuring clients can rely on stable machine-readable error semantics across endpoints.

ccc007ccc Bundle

Generate, edit, validate, render, visually inspect, animate, import, and export AgentPaint APX/APXA pixel-art source files with style-aware pixel-art guidance. Use when an agent needs to create layered pixel art at the exact requested resolution, import low-color raster pixel art or GIFs into APX/APXA, create point-upscaled previews for AI visual inspection, create GIF animation from APXA frames, choose a pixel-art style or era, convert a pixel-art idea into APX JSON, repair APX validation errors, render APX to PNG, export layered PSD, export RGBA JSON, or make local pixel edits with rows/chunks instead of raw RGBA arrays.

eavn Skill

当用户明确要求“归档”“整理上下文并归档”“提取本次任务有用内容写入记忆”“写归档笔记”“收尾归档”“archive this session”或把本次任务沉淀为长期记录时使用。作为唯一用户入口/facade，一次完成 Obsidian engineering note、agent-brain wiki、必要 ad-hoc memory note，并自动做轻量相关旧记忆检查；不要因普通复杂任务自动触发。若用户只要求整理/清理/压缩旧记忆，改用“记忆治理”。

eavn Skill

当用户明确要求“整理旧记忆”“清理记忆”“删除过期记忆”“压缩记忆”“shrink MEMORY.md”“memory cleanup”“memory governance”“去重记忆”“修正旧记忆”“清理旧 skill/旧 prompt 记忆污染”，或归档流程发现大量冲突/重复/过期记忆需要完整治理时使用。负责审计 Codex memory/ad-hoc notes/相关旧来源并写新增、修正、删除请求；不要直接编辑 MEMORY.md 或历史 rollout summary。

may215 Skill

Group skill: AI/LLM application — provider selection, app patterns, RAG, agents, prompts, evaluation, safety, and monitoring.

may215 Skill

Group skill: Healthcare/medical app — compliance, data model, health analysis, PHI protection, dashboards, reports, and audit.

arn-nj Skill

Analyze requirements and codebase together, then always generate a complete architecture package with a primary Architecture and Design Document, diagrams, workflows, data model docs, open questions, image prompts, and playbook-applied output.

arvincreator Bundle

<SkillModule path="src/skills/modules/multi-agent/skill.md">

pimenov Skill

Runs an adversarial review gate for non-trivial or high-stakes decisions before they stand. Use when Codex is about to claim something is safe, correct, reversible, production-ready, scalable, idempotent, secure, or compliant; when work touches production, auth, permissions, secrets, billing, public APIs, migrations, irreversible cleanup, customer data, external agent CLIs, or unfamiliar code with meaningful blast radius; or when a confident answer would be cheaper to challenge now than to debug later.

pimenov Skill

Reviews code changes across correctness, tests, readability, architecture, security, and performance before they are merged, shipped, or called done. Use when the user asks for a code review, when reviewing a PR/diff/commit/agent-produced code, after implementation or bugfix before final confidence, when deciding whether a change is ready, or when large/unclear changes need findings with severity and verification gaps.

arvincreator Bundle

<SkillModule path="src/skills/modules/image-prompt/skill.md">

tf-worldone Bundle

Run a selectable multi-model independent answer panel and synthesize the results. Use when the user asks for multiple top models, a model council, parallel opinions, GPT 5.5 Pro plus Opus/DeepSeek/GLM/Gemini comparison, or a single final answer produced from independent model outputs without a debate/discussion round. Supports model selection, available-model filtering, partial success, retries, cost/token logging, and configurable synthesizers.

tf-worldone Bundle

Run a selectable multi-model panel with explicit discussion rounds before final synthesis. Use when the user asks multiple AI models to give independent opinions, then debate, discuss, critique, reconsider, or refine each other's views before final output. Supports model selection, available-model filtering, partial success, retries, cost/token logging, and configurable synthesizers.

majinabhinav-gif Bundle

Manage the advisor trade lifecycle from order entry through settlement, covering block trading, allocation, pre-trade compliance, custodian routing, and error correction. Use when the user asks about designing an OMS for an RIA, executing model portfolio changes across many accounts, structuring block trades with fair allocation, configuring pre-trade compliance rules or restricted lists, routing orders to multiple custodians, handling trade errors or corrections, managing cash in trading workflows, or evaluating OMS platforms. Also trigger when users mention 'block trade', 'trade allocation', 'order management system', 'iRebal', 'Orion Trading', 'Tamarac Trading', 'best execution', 'trade error', 'mutual fund vs ETF orders', or 'audit trail'.

valtterimelkko Bundle

Convert Word documents to structured markdown for LLM-assisted editing, then convert back to Word with preserved formatting. Make sure to use this whenever the user wants to work on, revise, draft, fill in, or collaboratively edit a .docx and then produce a final .docx again. Prefer this over markitdown or docx-to-markdown whenever round-trip editing fidelity matters.

valtterimelkko Bundle

Convert PowerPoint presentations to structured markdown for LLM-assisted editing, then convert back to PowerPoint with preserved formatting and layout. Use when you need to draft, edit, or work on .pptx files interactively.

valtterimelkko Bundle

COMPREHENSIVE top-tier research for topics where breadth, source quality, and auditable methodology matter. Use when the user needs 40+ sources, publication-grade synthesis, due diligence, policy or market analysis, or any high-stakes research where missing key dimensions would materially weaken the answer. This skill is especially valuable when the prompt has multiple dimensions that must all be covered faithfully. NOT for quick or medium-depth briefs; prefer gpt-research or native web_search/web_fetch for those.

valtterimelkko Bundle

Search YouTube videos by query or within specific channels. Supports date filtering, sort ordering, and duration filters to exclude YouTube Shorts. Returns LLM-optimized JSON with video details.

valtterimelkko Skill

Build MCP channel plugins that push external events into a running Claude Code interactive session and bridge bidirectional communication. Use when: building a custom channel plugin for Claude Code, bridging Claude Code to a web UI or chat platform, understanding the channels protocol (notification format, reply tools, sender gating, permission relay), integrating Claude Code with external systems via WebSocket or HTTP, replacing claude -p with interactive Claude Code for better subscription quota, wrapping Claude Code in a custom interface, or working with @modelcontextprotocol/sdk for Claude Code channel plugins. ALWAYS use when the user mentions Claude Code channels, --channels, channel plugins, channel reference, push events into Claude Code, Claude Code WebSocket bridge, or wants to connect an external app to a live Claude Code session.

majinabhinav-gif Skill

Determine when a product, platform, or communication crosses the regulatory line from education into investment advice requiring investment adviser registration. Use when the user asks about the definition of investment advice under Advisers Act Section 202(a)(11), whether a fintech feature or AI chatbot constitutes advice, the publisher's exclusion for newsletters or model portfolios, the broker-dealer solely incidental exclusion, adviser registration thresholds and exemptions, or DOL education vs advice safe harbors. Also trigger when users ask 'do I need to register as an investment adviser', 'does this app give investment advice', 'is this tool just education or advice', 'robo-adviser registration', or 'disclaimer language for financial content'. (For what triggers a 'recommendation' under Reg BI, use reg-bi.)

majinabhinav-gif Bundle

Select, configure, and operate portfolio management systems for advisory firms, covering model portfolios, UMA/sleeve management, drift monitoring, rebalancing, and custodian data feeds. Use when the user asks about choosing a PMS platform, building or distributing model portfolios, implementing UMA or sleeve-based management, setting drift monitoring thresholds, aggregating held-away assets, reconciling PMS with custodian records, configuring PMS-based billing, or troubleshooting custodian feed issues. Also trigger when users mention 'portfolio management system', 'Orion', 'Black Diamond', 'Tamarac', 'Addepar', 'Advent APX', 'model portfolio', 'sleeve management', 'rebalancing engine', 'custodian feed', or 'PMS migration'.

majinabhinav-gif Skill

Integrate financial planning engines with the advisor technology stack — data flows between planning tools, CRM, PMS, custodians, and aggregation platforms; capital market assumption (CMA) governance and synchronization; plan-to-IPS-to-model linkage; and governed tax reference parameters in planning tools. Use when the user asks about connecting eMoney, MoneyGuidePro, or RightCapital to CRM or portfolio systems, eliminating manual re-entry between systems, keeping plan and portfolio assumptions consistent, mapping plan outputs (required return, risk capacity, withdrawal schedule) into the IPS and model assignment, or establishing plan update cadence and data-freshness rules. Also trigger on 'plan-to-IPS linkage', 'assumption synchronization', 'CMA governance', or 'planning tool integration'. For planning methodology itself — Monte Carlo modeling, Roth conversion strategy, Social Security claiming, retirement projections — use financial-planning-workflow instead.

edge-city Bundle

Edge Esmeralda's Index Network bundle. Surfaces opportunities, drafts introductions, and prunes stale signals. Read when surfacing opportunities, drafting introductions, onboarding a user who has expressed social intent, or handling anything backed by the Index Network MCP (server `index`).

code-shock Bundle

Rapidly file one or more well-structured, agent-friendly GitHub issues in the current repo. Use to quickly capture bugs or tasks as issues or when the user runs /qa.

valtterimelkko Skill

Transcribe audio files to text using a local Whisper ASR service. Use when: the user wants to transcribe an audio file to text, convert speech to text from an audio recording, extract text from voice recordings, or needs transcription of podcasts/interviews/voice notes. Only works for English language audio. The skill saves the transcription to a text file in the agent's local folder.

valtterimelkko Bundle

Scrape Amazon UK (amazon.co.uk) product pages to check availability, Prime eligibility, delivery estimates (UK), GBP price, and full technical specifications. Use this skill whenever an agent needs to: look up Amazon UK product listings, check if a computer part or product is in stock on Amazon UK, compare product specs across multiple ASINs, find product model numbers to look up on other sites, research GPU/CPU/RAM/SSD or any hardware for compatibility, verify Prime delivery eligibility, or search Amazon UK and return structured product data. Always use this skill for any Amazon UK product research, price checking, availability verification, or parts-comparison task.

chendaiwei-99 Bundle

Audit an Obsidian LLM knowledge base and personal note space for structure, links, stale summaries, duplicate concepts, weak citations, unresolved contradictions, project-note consistency, and human/agent ownership violations. Use when checking workspace health, reviewing whether personal notes and sources are consistent, preparing cleanup work, or finding issues that should be added to knowledge-base/wiki/review.md.

chendaiwei-99 Bundle

Answer questions from an Obsidian LLM knowledge base and personal note space using raw-source records, wiki synthesis, and human notes with citations and preserved source links. Use when the user asks about knowledge stored in knowledge-base or personal-notes, wants a research answer grounded in sources, or asks for more detail that may require following preserved website links.

chendaiwei-99 Bundle

Ingest one external source at a time into an Obsidian LLM knowledge base by creating raw-source markdown records for PDFs, literature, GitHub repositories, web pages, or text files. Use when adding raw data to knowledge-base/raw, summarizing a PDF into knowledge-base/raw, documenting a GitHub repo with preserved links and commit context, or updating the LLM wiki after ingestion.

chendaiwei-99 Bundle

Create and evolve human-friendly Obsidian workspace schemas with an assistant-maintained LLM knowledge base and a human-owned personal note space. Use when setting up or changing AGENTS.md, knowledge-base raw/wiki folders, fleeting/projects/permanent note folders, project note templates, or ownership rules that prevent agents from overwriting the user's own notes.

chendaiwei-99 Bundle

Maintain Obsidian LLM knowledge-base index, log, review queue, and advisory-report registry files. Use when adding raw-source records, filing synthesis pages, recording KB maintenance actions, appending unresolved contradictions to knowledge-base/wiki/review.md, or keeping knowledge-base/wiki/index.md navigable.