AI & ML

emasoft Bundle

Use when the user wants to query the PSS index, search/list/inspect elements, run lifecycle or history queries, build a plugin from a profile, or anywhere a `pss …` CLI command is needed. Loaded by pss-agent-profiler.

emasoft Bundle

Use when running benchmark competitions or improving scoring accuracy. Used by pss-agent-profiler. Trigger with /pss-benchmark.

emasoft Bundle

Use when creating an agent that orchestrates several skills, choosing between ALL-IN-ONE, ONE-FOR-ALL and PLUGIN-OMNI, or deciding whether to preload skills into an agent's frontmatter. Covers the preload-vs-access distinction and the `fork` terminology trap. Trigger with /pss-make-agent.

emasoft Bundle

Use when augmenting an .agent.toml with project requirements. Loaded by pss-agent-profiler. Trigger with /pss-change-agent-profile --requirements.

emasoft Bundle

Use when improving categorization, scoring, or matching accuracy via parallel experimentation. Used by pss-agent-profiler. Trigger with /text-categorization-improver.

dimonier Bundle

Author and improve a Domain Principle Framework (DPF) or Local Practices Framework (LPF) directly in Agent-skill form (SKILL.md + references/). Use when creating, revising, or maintaining a DPF/LPF as a skill, or when the user mentions "pattern language as agent skill".

garfield-bb Bundle

使用明道云 HAP V3 接口搭建页面和操作数据的专业技能。**立即触发条件**：用户提到"HAP V3"、"HAP API"、"接口调用"、"数据接口"、"Appkey"、"Sign"、"接口鉴权"、"Filter 筛选"、"查询数据"、"创建记录"。提供完整的 API 使用指南：鉴权配置、接口调用、筛选器使用、数据操作等。如果用户已配置 HAP MCP，AI 应该自动从 MCP 配置中提取鉴权密钥。

pinmeto Skill

Step-by-step checklist for adding a new tool to this PinMeTo MCP server, covering naming, schemas, handler wiring, and registration. Use when adding or modifying an MCP tool.

davidmosiah-withingsmcp Skill

Unofficial Withings data for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Withings data or actions through an agent.

davidmosiah-ouramcp Skill

Unofficial Oura Ring data for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Oura data or actions through an agent.

jtchien0925 Skill

Programmable crowdfunding for AI agents. Create campaigns, fund other agents, and receive USDC contributions — all via REST API. Multi-chain payments settled on Base.

fallomai Bundle

Agent payment service via CrowPay — gives your agent a wallet to pay for APIs and services. Use this skill whenever the agent needs to handle HTTP 402 Payment Required responses, pay for an API, buy credits or subscriptions, pay a merchant with a credit card, set up an agent wallet, or manage spending rules. Also use when the user mentions CrowPay, Crow, agent payments, USDC, x402, or buying anything on the internet for the agent — even if they don't say "Crow" by name.

stevenwang112 Skill

Reviews code changes or existing files for bugs, design issues, style, and performance.

aeoess Bundle

Find people through your agent. Tell your agent who you're looking for and Mingle helps find the right person through their agent.

liuhedev Bundle

无 API key 时的网页版批量生图：搜参考图 → 驱动已登录的豆包/即梦/千问「图生图」重画 → 落本地图库，批量生成风格统一的套图。当用户要「批量生成一套图 / 参考图重绘 / 照着这些图重画 / 给这些角色画套图 / 做套贴纸打卡卡」，且没有图模型 API key，或指定用豆包/即梦/千问网页版时用。 有 key 或单张图走 lh-image-gen；构造创意 prompt 走 lh-inline-diagram / lh-cover-image。

proyecto26 Bundle

Autonomous LLM training optimization with GPU support. Runs 5-minute training experiments, measures val_bpb, keeps improvements or reverts — repeat forever. Use this skill when the user asks to "train a model autonomously", "optimize LLM training", "run ML experiments", "autoresearch with GPU", "optimize val_bpb", "autonomous ML training", "LLM pretraining loop", "setup ML autoresearch", "set up ML autoresearch on my GPU", "GPU training experiments", "pretrain from scratch", "speed up training", "lower my loss", "GPU optimization", "CUDA training", or mentions "train.py", "prepare.py", "bits per byte", "val_bpb", "NVIDIA GPU training", "RTX 3090/4090/5090 training", "H100 training", "autonomous model training", "consumer GPU training", "low VRAM training". Always use this skill when the user wants to autonomously optimize any ML training metric.

yuwanpai2004-create Bundle

Collect a verified person, creator, brand, or organization's self-authored public Xiaohongshu, Douyin, and Weibo posts into a local, traceable Markdown dataset with source URLs and provenance. Use for public-content archiving, personal knowledge bases, search/RAG ingestion, content audits, writing-style analysis, portfolio migration, research datasets, or consented AI persona/training preparation. Includes user-local setup, Chrome login guidance, verified account mapping, collection, and review; excludes private content and unverified authorship.

rahulsub Skill

Write failing tests before implementation. Enables LLM self-correction through feedback loops. Use for new features and bug fixes.

rahulsub Skill

Define success criteria instead of step-by-step instructions. Enables autonomous LLM iteration toward testable goals.

zhaoxuanzzz Bundle

Generate and optimize prompts for various AI use cases. This skill provides specialized prompt templates for structured data parsing, complex multi-step tasks, and markdown-formatted outputs with sections, content, and visual elements. Use this when users need help crafting, refining, or adapting prompts for different scenarios.

comfy-org Skill

Reference skill cited by comfy-build. Read it with `comfy skills show comfy-build-authoring` when authoring a comfy-build.yaml definition by hand — the user has no ComfyUI install to scan, or you are editing a spec's models and customNodes directly. Covers searching the node registry, resolving model filenames to public sources, choosing the directory a weight lands in, and every field of the definition schema.

ninihen1 Skill

Govern Power Automate flows and Power Apps at scale using the FlowStudio MCP cached store. Classify flows by business impact, detect orphaned resources, audit connector usage, enforce compliance standards, manage notification rules, and compute governance scores — all without Dataverse or the CoE Starter Kit. Load this skill when asked to: tag or classify flows, set business impact, assign ownership, detect orphans, audit connectors, check compliance, compute archive scores, manage notification rules, run a governance review, generate a compliance report, offboard a maker, or any task that involves writing governance metadata to flows. Requires a FlowStudio for Teams or MCP Pro+ subscription — see https://mcp.flowstudio.app

ninihen1 Skill

Pro+ subscription required. Tenant-wide Power Automate monitoring using the FlowStudio MCP cached store: failure rates, run-health trends, maker/app inventory, inactive owners, and compliance/health reports. Use only for aggregated tenant views. For one environment, one flow, run control, or root-cause debugging, use power-automate-mcp, power-automate-debug, or the server monitor-flow bundle. Requires FlowStudio for Teams or MCP Pro+.

acnlabs Bundle

Financial management for AI agents. Track LLM inference costs, record confirmed income, manage multi-provider crypto wallets, and compute a Financial Health Score. Use when you need to check your balance, record a cost or expense, report financial health, manage your wallet, or assess economic sustainability.

airweave-ai Bundle

Set up and integrate Airweave into applications. Use when the user wants to install Airweave, create collections, connect data sources, configure MCP servers, or set up the SDK to integrate Airweave into their app. For developers building with Airweave.

bigsy Skill

Install, set up, and manage MCP servers using the mcpmu CLI. Use when the user wants to install mcpmu, register it as an MCP server, add/remove/list MCP servers, manage namespaces, set tool permissions, manage server-level denied tools, or expose servers via serve mode.

gongyu0918-debug Bundle

Review your installed agent skills to see what you actually use, what overlaps, and what may no longer be worth keeping.

justin-delano Bundle

Meta-agent system for generating, refining, and self-improving specialist agents through multi-source interviews, agent deliberation, and triangulated critique. Inspired by Virtual Lab (Nature 2025). Load when creating new agents or improving existing ones.

mossaka Bundle

Guide for creating effective agent skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.

mossaka Skill

Trigger and monitor smoke tests for a gh-aw PR. Use when: (1) User wants to run smoke/integration tests on a PR, (2) User says 'run smoke tests' or 'trigger smoke', (3) Validating that gh-aw changes don't break basic workflows, (4) Need to verify MCP server connectivity and agent behavior in workflows.

mossaka Bundle

Debug GitHub Agentic Workflow runs using gh-aw CLI tools to investigate failures, analyze logs, identify MCP server issues, and troubleshoot workflow execution problems. Use when: (1) Investigating workflow run failures or unexpected behavior, (2) Analyzing workflow execution logs, (3) Debugging MCP server connectivity or tool availability issues, (4) Creating issues to document workflow problems, (5) Understanding why a successful workflow didn't produce expected results, (6) Examining firewall blocks or network issues in workflows

advanced-security Bundle

Upgrade the CodeQL CLI version and synchronize all ql-mcp-* pack dependencies to maintain compatibility. Use this skill when a new CodeQL CLI version is released and the MCP server needs to be updated to use it.

advanced-security Bundle

Add first-class support for a new CodeQL-supported language to the CodeQL Development MCP Server. Use this skill when CodeQL adds support for a new language (e.g., Rust) and the MCP server needs to provide tool queries, prompts, and resources for that language.

advanced-security Skill

Validate that the CodeQL Development MCP Server reliably returns non-empty AST, CFG, and CallGraph data from the bundled tools queries. Use this skill to ensure the `codeql_query_run` tool properly executes PrintAST, PrintCFG, CallGraphFrom, and CallGraphTo queries for any supported language.

flashinfer-ai-flashinfer-bench Skill

Track popular/new open-source LLMs and update docs/model_coverage.mdx with their kernel support status. Use when discovering new models to add to the coverage tracker, checking if a specific model is covered, or refreshing model coverage documentation.

flashinfer-ai-flashinfer-bench Skill

Discover candidate LLMs and produce a kernel inventory — required definitions, classified as existing/new and fi_supported/fi_missing — for onboarding. Use as Phase 1 of /onboard-model, or standalone to plan onboarding work.