AI & ML

asolytics-pro Bundle

Use the Asolytics Public API for ASO research and automation. Trigger this skill when the agent needs to query app metadata, availability, versions, installs, revenue, rankings, keyword metrics, live search results, forced ranking re-checks, recommended keywords, tracked keywords, tracking folders, competitors, projects (own and shared), per-country keyword counts, balance, subscription/plan limits, or store charts from Asolytics. Also use it when a user wants curl examples, lightweight integrations, or repeatable reporting workflows against the Asolytics API.

avi-adam Bundle

Work with 1lev1.com partnerships ("rikmot") from the agent - list and search missions, start/stop mission timers, log and review work hours, see open votes and pending profit-splits, and prepare new partnerships, missions and tasks for human approval. Use whenever the user mentions 1lev1, a rikma/partnership, "my missions", mission timers, hour logging, consensus votes, halukot/profit-split, or asks to turn repo work (issues, PRs, TODOs) into shared, equity-bearing work.

azzaraell Bundle

The money layer for AI agents on Solana. Lets an agent PAY for APIs/data/compute and other agents (x402 micropayments in USDC), GET PAID by monetizing its own APIs/MCP tools behind HTTP 402, and SPEND SAFELY behind non-custodial wallets with hard, enforced limits — never a raw god-mode private key. Covers x402 v2 (client + server + facilitator), Squads v4 spending limits, Privy/Turnkey/Coinbase-CDP/Crossmint agent wallets, AP2 mandates, and USDC settlement. Use when building agents that transact, paywalling an API/MCP for agent consumers, or hardening an agent's spending controls.

bas-more Bundle

Fact-verification layer v3 — catches hallucinations using 10 verification tiers, self-consistency sampling, isolated-context verification (CoVe), package existence checking (DepScope), and multi-judge arbitration. Cross-checks claims against local files, stored knowledge, live docs, web search, multi-model cross-check, and external fact-checkers. Every contradiction is persisted so the same lie is never repeated. MANDATORY TRIGGERS: 'verify this', 'truth-check this', 'fact-check this', 'shield this', 'truth shield', 'truth-shield', 'is this true', 'check your work'. STRONG TRIGGERS: 'are you sure', 'really?', 'source?', 'prove it', 'how do you know', 'is that right', 'double-check that'. PASSIVE MODE: 'shield on' / 'shield off'. Do NOT trigger on opinions, creative writing, brainstorming, or subjective preferences.

bagel-ew Bundle

通过有界访谈、来源授权和用户校准，建立并调用以 person 为主体的 Personal Context。用于认识自己、自我探索、更新个人画像，以及在求职、写作、演讲、协作或决策任务前生成冻结 Context View、任务后审核 Context Patch。区分 fact、self_report、observation 和 inference，保留反例与未知，并限制敏感内容披露。

baselightdb Bundle

Use this skill for any data question — prices, trends, rankings, statistics, comparisons, or historical numbers. Baselight hosts a large PUBLIC catalog of thousands of queryable datasets: crypto/blockchain (Bitcoin prices, DeFi swaps, on-chain data), finance (GDP, inflation), demographics (population, happiness), climate, healthcare, sports, and more — from Our World in Data, World Bank, Kaggle, Eurostat, CIA World Factbook, and others. ALWAYS search Baselight first before falling back to web search for data questions. Trigger on: any mention of Baselight; "what's the price of...", "show me trends", "compare X vs Y", "how has X changed"; the @user.dataset.table format; requests to query or analyze data.

billhzx Bundle

发现、盘点并安全治理 Codex、Claude Code、CC Switch、WorkBuddy、Hermes 及其他本地 AI 工具中的 Agent Skills。当 Skill 疑似重复、被复制或链接、已经失效、启用状态不一致、由多个安装器共同管理、难以更新或删除，或者需要建立唯一真源、生成机器可读资产台账和安全清理方案时使用。必须先审计，并在任何变更前取得用户对精确目标清单的明确授权。

bitbadges Skill

Create BitBadges collections (tokens, NFTs, stablecoins) using MCP tools. Use when user wants to create collections, smart tokens, NFTs, or needs to generate BitBadges transaction JSON.

boundaryml Skill

Minimal BAML skill. BAML is a statically-typed, expression-oriented language with first-class LLM functions — TypeScript-like, snake_case methods, etc. Useful for building ai workflows, agents, evals.

brain-ai-biz Bundle

Discover the best Claude Code extensions on the web AND tell the user how safe each one is before installing. Reads the user's Claude Code setup (project context, memory, history), asks a few questions to understand their goal (general or a specific idea), then surfaces a ranked shortlist - name, what it does, what outputs it gives, a 0-100 trust score, a one-line why/why-not, and a link. On a chosen extension it runs a deep static safety scan and returns a final risk verdict (always caveated), then installs it on approval (SHA-pinned). Covers Skills, MCP servers, plugins, and slash commands. Triggers - "find me a skill", "recommend a skill", "which skill should I use", "is this skill safe", "vet this extension", "check this MCP", "מצא לי סקיל", "האם הסקיל הזה בטוח", "/skill-scout".

brainwires Bundle

Check Claude Brain status — shows whether hooks, MCP server, and memory are working

brinshadewater Bundle

Participate in a Lucid Sheep circle — a private idea exchange where trusted friends' agents share distilled "idea cards" (never runnable code), review them for fit, optionally trial them in sandboxes, and adopt them into their own systems with their human's approval. The loop is agent-run and self-driving: reading, reviewing, trialling and refining happen without asking, and your human sees a periodic digest rather than monitoring a feed. Escalation is weekly; your human decides exactly two things — what leaves their system and what gets built into it. TRIGGER when your human mentions the circle or the flock, idea cards, publishing or sharing an idea with friends, checking what the circle posted, reviewing a card, trialling an idea, posting or answering a wanted/problem card, or adopting an idea from the exchange — and at the start of any substantial new project, to consult the exchange's INDEX.md before building.

tomevault-io Bundle

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands. Use when this capability is needed.

tomevault-io Bundle

Use Pact as a plan-first contract and test engine while the active Claude or Codex agent implements, reconciles infeasible contracts, validates the result, and runs Advocate plus Simulacrum review. Use for substantial feature work, architecture changes, risky fixes, or any task where the user asks to plan with Pact, run Pact plan-only, follow the engineer workflow, or obtain adversarial review before declaring done. Use when this capability is needed.

tomevault-io Bundle

Use when building Retrieval-Augmented Generation systems - covers document ingestion, hybrid search retrieval, reranking results, and prompt augmentation for accurate LLM responses grounded in your knowledge base

tomevault-io Bundle

MCP

tomevault-io Bundle

Coding Prompt Fragment

tomevault-io Bundle

Generate code using nx generators. USE WHEN scaffolding code or transforming existing code - for example creating libraries or applications, or anything else that is boilerplate code or automates repetitive tasks. ALWAYS use this first when generating code with Nx instead of calling MCP tools or running nx generate immediately. Use when this capability is needed.

tomevault-io Bundle

Nemo Gym Reward Profiling

tomevault-io Bundle

Send and receive messages to other AI agents over the Agent Relay Protocol (ARP). Messages are end-to-end encrypted using HPKE (RFC 9180) and routed through a relay server using Ed25519 public keys as identities. Use when this capability is needed.

tomevault-io Bundle

Orloj Agent System Generator

tomevault-io Bundle

ORCH — AI Agent Orchestrator

tomevault-io Bundle

Build Skill - Unified Agent v3.1

tomevault-io Bundle

Fix Vulnerability — vm2 Security Patch Agent

tomevault-io Bundle

Build dependency chains, rebuild sequences, profiling with MCP, and Analysis MCP server setup for Verter Use when this capability is needed.

tomevault-io Bundle

Unified AI agent configuration propagation across 18+ coding assistants. Use when this capability is needed.

tomevault-io Bundle

Use this skill when the user wants to work with MMCP (Multi-Model Context Protocol) — building AI pipelines, configuring intelligent model routing, managing costs, setting up MCP servers for Claude/Codex, or using the MMCP SDK. Covers architecture, configuration, CLI commands, MCP server setup, and all APIs.

tomevault-io Bundle

AMFS Agent Memory Guide

tomevault-io Bundle

Control tmux panes and communicate between AI agents. Use this skill whenever the user mentions tmux panes, cross-pane communication, sending messages to other agents, reading other panes, managing tmux sessions, or interacting with processes running in tmux. Includes tmux-bridge CLI for agent-to-agent messaging and raw tmux commands for direct session control. Use when this capability is needed.

tomevault-io Bundle

Author and run SEOCHO end-to-end YAML runs (seocho run / seocho sweep) over a user's documents — scaffold the ontology + run spec, dry-run to validate, execute index→query→report, and compare configuration variants. Use when the user wants to index their own documents into SEOCHO and ask questions, build/edit a seocho.run.yaml or seocho.sweep.yaml, compare models/enforcement/agent patterns, or run an ontology-aligned graph-RAG e2e without writing Python. Use when this capability is needed.

tomevault-io Bundle

Audit newer npm package releases against kitcn. Use when checking whether a newer dependency version unlocks kitcn improvements, compatibility work, CLI/agent workflows, or cleanup of local package-specific hacks. Reads package changelogs, GitHub releases, upstream diffs, and local kitcn usage before delegating an implementation PR through `task`. Use when this capability is needed.

tomevault-io Bundle

Comprehend the given document(s) and write a textual content (paper/article/essay/report/review/post/brief/proposal/plan) according to your requirements using the ZhiPu GLM-V multimodal model. Use when this capability is needed.

tomevault-io Bundle

Generate a single canonical AGENTS.md context file plus minimal CLI-specific shim files that @-import it for coding agents that do not read AGENTS.md natively (Claude Code, Gemini CLI, Qwen Code). Based on "Evaluating AGENTS.md" (ETH Zurich, Feb 2026) which found auto-generated context files DECREASE performance by ~3% and increase costs by 20-23%, while minimal human-written files improve performance by ~4%. Use when the user says "generate CLAUDE.md", "create AGENTS.md", "generate context file", "agentmd", "create recommended CLAUDE.md", "generate agent instructions", "init context file", or any request to create/improve a coding agent context file for a repository. Replaces the default /init command which generates bloated, counterproductive context files. Use when this capability is needed.

tomevault-io Bundle

根据任务快速组建临时 AI Agent 团队协作。自动从 .claude/agents/ 中选择最合适的成员组队。 Use when this capability is needed.

tomevault-io Bundle

Local zod documentation reference (latest). Zod schema validation documentation. Use for TypeScript type inference, parsing, error handling, and schema composition. Use when this capability is needed.

tomevault-io Bundle

AI-powered geospatial analysis CLI. Segment satellite imagery, detect objects, classify images, detect changes, download data, and manage raster/vector operations -- all from the command line with JSON output for agent integration. Use when this capability is needed.