AI & ML

strands-agents-agent-sop Bundle

Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.

reddinft Skill

Build a cost-efficient LLM evaluation ensemble with sampling, tiebreakers, and deterministic validators. Learned from 600+ production runs judging local Ollama models.

chengzhongwei Bundle

Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.

chronista-club Bundle

creo-memories = 外部脳。context が尽きても、session / machine / model / 人をまたいで続きができる場所。書くのは「次に拾う誰かのため」、読むのは「自分が始めた気になる前」。

proskillsmd Bundle

Encrypted GitHub backup and restore for any OpenClaw agent system. Creates branch-per-night backups with smart retention (7 daily, 8 weekly, 12 monthly branches). Backs up openclaw.json (AES-256 encrypted), agent memories, SOUL/IDENTITY files, cron jobs, and custom skills to a private GitHub vault. Each backup auto-generates a human-friendly README.md inside the vault with purpose, full contents table, branch structure, step-by-step restore instructions, and Avenger agent commands. Triggers on phrases like "avenger backup", "backup system", "push to vault", "sync vault", "avenger restore", "restore from vault", "setup avenger", "avenger status", "avenger init", "configure backup", "set up backup". Also auto-runs after any critical config change.

portkey-wallet-ca-agent-skills Bundle

Portkey Contract Account wallet registration, authentication, verifier codes, recovery, guardians, CA identity, assets, transfers, approval proofs, chain readiness, contract calls, and encrypted keystore workflows on AElf. Use when CA hash, guardian, registration, recovery, or manager-forward behavior is required; use the EOA skill for mnemonic or direct private-key wallet lifecycle workflows.

yiweisi-bot Bundle

OpenClaw 老板 v8.0 - LLM 自主检索通用版！默认纯文本报告，仅当用户说 ASCII 图时才显示卡片。不预设数据源，LLM 自主检索用户数据，通用适配所有场景。锐评前置、数据驱动、个性化锐评。

drivly Bundle

Use when working with Auto.dev APIs, vehicle data, VIN decoding, car listings, vehicle photos, specs, recalls, payments, interest rates, taxes, OEM build data, plate-to-VIN, CLI commands, MCP tools, or SDK methods for any automotive data task

bitrefill Bundle

Buy or browse Bitrefill — 1,500+ gift cards, mobile top-ups, eSIMs, 180+ countries. Capability routing: probe harness (exec, egress, MCP), pick touchpoint (Bitrefill MCP, x402 REST via Base MCP, CLI, API, browse), wallet (balance, x402, send). Favors autonomous purchase, minimal HITL. Triggers: Bitrefill, gift cards, mobile top-up, eSIM, crypto, Lightning, USDC, x402.

comprono Skill

Connect Codex to local Antigravity 2.0 through a CLI-first low-RAM bridge, plus desktop UI setup checks, model limits, project/chat inspection, and safe conversation handoff when UI state is needed.

acczdy Bundle

Agent 自我学习与记忆更新技能。分析对话历史，提取关键信息，自动更新配置文件和学习记录，实现 Agent 持续自我成长。 融合自学习 (配置文件更新) + 自改进 (学习记录系统) 双引擎。 Use this skill when: - 需要整理和更新 Agent 记忆 (MEMORY.md, IDENTITY.md 等) - 对话中产生了新的配置信息或用户偏好 - 用户纠正 Agent 或发现错误时 (记录到 .learnings/) - 定期执行 Agent 自我优化 - 清理过时的配置和记忆 Triggers: 自我学习、记忆更新、配置优化、Agent 成长、整理记忆、记录学习、纠正错误

bryant24hao Bundle

End-to-end workflow for publishing agent skills to GitHub, ClawdHub, and skills.sh. Handles repo creation, topic tagging, ClawdHub publish, skills.sh index request, and installation verification. Use when: "publish skill", "上架 skill", "发布技能", "submit to skills.sh", "submit to clawhub", "skill 上架流程".

paulieb14-substreams-search-mcp Bundle

Search, inspect, and analyze Substreams packages from the substreams.dev registry — module graphs, protobuf types, and sink deployment commands.

tuejon Bundle

WebMCP agent skill for curated core coverage or route-by-route parity — inventory an existing web app, integrate approved tools, then verify and heal them in a real browser. Use for "webmcpify", "add WebMCP", or "expose app actions to AI agents".

d-yuva Skill

Learn and answer questions from any framework documentstion website quickly and accurately. Crawls a docs site from a seed URL, builds a lightweight URL index (titles/headings/snippets), BM25-ranks pages for a user's question, then fetches and converts only the top-k pages to clean markdown for grounded answers with source links. Use when a user shares a docs URL and asks "how do I..", "where is..", "explain..", "OAuth/auth", "errors", "configuration" or "API usage"

songjiayang Bundle

Generate professional AI-enhanced photos using ByteDance Seedream 4.5 model. Use when users want to, (1) Create portraits with various styles, (2) Generate couple or family group photos, (3) Take photos with movie characters, (4) Edit images (change clothing, background, material, style), (5) Merge multiple photos (outfit fusion, person-scenery fusion, brand design), (6) Create series of related images (seasons, character states, story sequences), (7) Design posters (movie, event, product), or (8) Use custom prompts with full creative control.

haasonsaas Bundle

Security testing and red-teaming for LLMs using NVIDIA's garak vulnerability scanner. Use when probing AI models for jailbreaks, prompt injections, data leakage, toxic content generation, or other failure modes. Triggers on "test LLM security", "red team model", "run garak", "LLM vulnerability scan", "jailbreak testing", or "prompt injection test".

wolfe-jam-grok-faf-mcp Skill

Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, CLAUDE.md bi-sync, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.

antonbabenko Skill

Guidelines for adding new agent skills: always register in AGENTS.md, and prefer deterministic scripts with unit tests over pure SKILL.md for repeatable workflows.

nvidia Skill

Helps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input, output, retrieval, dialog, execution, Colang, or catalog-based guardrails. Trigger keywords - create guardrails, build guardrails, scaffold config, write rails, create config.yml, add input rails, add output rails, Colang flow, guardrails config, test guardrails.

sparklingneuronics Bundle

Route a task to Google Antigravity's `agy` CLI — the multi-model successor to gemini-cli. Use this skill ANY time the user names agy, antigravity, OR gemini, or types `/agy` or `/gemini` — even for routine work. Runs multiple models (Gemini 3.x, Claude 4.6, GPT-OSS): 'gemini' picks a Gemini model, 'agy'/'antigravity' the default or one you name ('with Claude Opus'). The intent: 'ask agy/gemini', 'have agy review/refactor this', 'check/validate with agy', 'see what gemini thinks', 'second opinion', 'use agy/gemini to create an image', 'continue/resume with agy'. Covers coding (review, refactoring, debugging), non-coding (emails, docs, decisions, research), and generating or editing images natively on the Google subscription. Keeps a separate agy conversation per topic. Do NOT use when the request delegates only to codex (if it names both, both skills run — handle the agy part here), when no tool is named, or when the user wants Claude itself to do the work. Companion to `/codex`.

chaoschain Bundle

Evaluate and track AI coding agent performance on real engineering tasks using ChaosChain Engineering Studio. Use this skill when a completed pull request or coding task should be evaluated for quality, when verifying another agent's submitted work, or when checking the performance history of an AI coding agent. Requires a ChaosChain gateway URL.

azure-samples-get-started-with-ai-chat Bundle

Creates an azd environment, checks prerequisites (RBAC, model quota), provisions the AI chat app infrastructure via `azd up`, and health-checks the deployed app.

hexdaemon Bundle

Structured memory database for AI agent identity, tasks, events, lessons, and persistent continuity. Use whenever the user says remember this, log this, track this, what should I do next, recap, summarize, what changed, or when you need to store/retrieve decisions, incidents, fleet ops notes, reminders, TODOs, goals, values, or facts about people/systems/projects across sessions.

bagwatcher Skill

Trade Solana tokens via Jupiter DEX with auto-execution and safety limits

echennells Skill

Use a Spark Bitcoin L2 wallet proxy for AI agents via HTTP API. Check balances, send payments, create invoices, pay L402 paywalls — all without holding the mnemonic. Use when user mentions "Spark proxy," "wallet API," "L402," "proxy payment," "bearer token auth," or wants secured Bitcoin capabilities for an agent.

zscole-bagman-skill Bundle

Secure key management for AI agents. Multi-backend support (macOS Keychain, 1Password, encrypted file, env vars). Use when handling private keys, API secrets, wallet credentials, or when building systems that need agent-controlled funds.

sagargupta16 Bundle

Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.

flosrn Bundle

Orchestrate any high-cost frontier model (Fable, Opus) on codebase-heavy or token-heavy work - delegate research, coding, and testing to cheaper subagents, write self-contained handoffs, pick and escalate delegate models, and vet delegated output before relying on it. Hard routing gates, binding whether or not this skill is loaded: never Haiku; anything user-facing (UI, copy, API design) goes to opus-5, fable-5, or gpt-5.6-sol, never grok-4.5 or a cheaper tier; when axes conflict on something that ships, intelligence > taste > cost; opus-5 is the session default. Load this skill for the model table and escalation policy before routing anything else.

bx33661 Bundle

Analyze pcap/pcapng files directly with tshark in a terminal when the user chooses CLI execution or MCP is unavailable. Build reproducible queries, preserve scan and field semantics, and keep raw output out of Agent context.

bx33661 Bundle

Investigate pcap/pcapng captures with Wireshark MCP to answer traffic, security, and network troubleshooting questions. Select bounded queries, verify packet evidence, and report what the capture can and cannot establish. Use the CLI skill when the user chooses direct tshark execution.

portainer Bundle

How to cut a portainer-mcp release that bumps the embedded Portainer OpenAPI spec to a new Portainer minor (e.g. 2.41.x → 2.42.x). Walks through finding the upstream patch target, regenerating the spec, recounting ops/tags per profile, refreshing the orphan-tag inventory, bumping version pins across the README and distribution docs, promoting CHANGELOG entries, committing, pushing, merging to main, and tagging — in that order. Trigger this skill whenever the user mentions cutting a release, bumping the Portainer version target, supporting a new Portainer minor, regenerating the spec, running `make specs` for a new minor, or any phrasing like "let's update for Portainer X.Y" — the spec regen is only the first step of a multi-file release and the model should consult this skill before touching anything.

avivsinai Bundle

Coordinate coding agents through AMQ. Use for agent messages, inboxes, receipts, sessions, wake delivery, cross-project routing, managed launches, or AMQ diagnostics. Use amq-spec for collaborative design; do not use this for general message queues or single-agent work.

ooples Skill

Use the token-optimizer MCP tools to reduce context/token usage when reading, searching, or editing files, or when the context window is filling up. Trigger when reading large files, re-reading files already seen, searching a big/unknown tree, making edits to large files, or when you need to store bulky output out-of-context.

njbrake Skill

Use when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.

lanyijianke Skill

作为所有工作流的"破冰"入口。当用户要求你做特定任务（如前端设计、API 集成、文本处理、调用外部 MCP）而你本地没有这些技能时，必须优先查阅并加载云端 AnySkill 技能系统。也支持将云端全部技能批量下载到当前项目，或将本地技能发布到云端仓库。支持 skills/ 目录下的分类文件夹管理。