AI & ML

deepgram Skill

Use when writing or reviewing Python code in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers `client.agent.v1.connect()`, `AgentV1Settings`, `send_settings`, `send_media`, event handling, and function/tool calling. Full-duplex STT + LLM + TTS with barge-in. Use `deepgram-python-text-to-speech` for one-way synthesis, `deepgram-python-speech-to-text` / `deepgram-python-conversational-stt` for transcription only. Triggers include "voice agent", "agent converse", "full duplex", "interactive assistant", "barge-in", "agent.v1", "function calling", "AgentV1Settings".

deepgram Skill

Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribe_url` / `transcribe_file` (REST) and `client.listen.v1.connect` (WebSocket). Use this skill for basic ASR; use `deepgram-python-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-python-conversational-stt` for turn-taking v2/Flux, and `deepgram-python-voice-agent` for full-duplex assistants. Triggers include "transcribe", "live transcription", "speech to text", "STT", "listen endpoint", "nova-3", "listen.v1".

deepgram Skill

Use when writing or reviewing Python code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST (`client.speak.v1.audio.generate`) and streaming WebSocket (`client.speak.v1.connect`). Also covers the in-repo `deepgram.helpers.TextBuilder` for incremental text assembly before synthesis. Use `deepgram-python-voice-agent` when you need full-duplex STT + LLM + TTS with barge-in. Triggers include "TTS", "speak", "synthesize voice", "aura", "text to speech", "speak.v1", "TextBuilder".

deepgram Skill

Use when writing or reviewing Python code in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.connect(...)`, Flux models, end-of-turn detection. Use `deepgram-python-speech-to-text` for standard v1 ASR, `deepgram-python-voice-agent` for full-duplex interactive assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", "listen.v2", "flux-general-en", "flux-general-multi".

pluginagentmarketplace Bundle

Data engineering, machine learning, AI, and MLOps. From data pipelines to production ML systems and LLM applications.

superhuman Skill

Welcome and onboard a new user to Superhuman Mail MCP. Use when the user is new to Superhuman Mail, asks what Superhuman Mail can do, wants a guided tour, setup walkthrough, first actions, examples for email or calendar workflows, help adding accounts, client-specific tool approval settings, Gmail/Outlook/app options, or says they want to get started with Superhuman Mail.

tjhop Skill

Health-check the Prometheus server and its targets. Use for status, uptime, or is-monitoring-OK questions; reviews readiness, active alerts, target health, TSDB stats, and runtime info.

tjhop Skill

Review and tune Prometheus configuration and performance. Use for scrape interval, retention, storage, relabeling, flag, and capacity questions, or when Prometheus itself is slow or resource-hungry; recommends concrete config changes.

tjhop Skill

Investigate elevated error rates and failing requests. Use when errors or 5xx/gRPC failures spike, SLOs burn, or an error alert fires; quantifies error ratios with rate(), compares to baseline, and isolates affected jobs and instances.

tjhop Skill

Audit and improve recording and alerting rules. Use when reviewing alert coverage or rule health, drafting new alerts or recording rules, investigating flapping or noisy alerts, or speeding up slow dashboards with pre-computed expressions; produces complete rule-group YAML.

tjhop Skill

Find and reduce high-cardinality metrics and labels. Use when series counts or memory grow, queries slow down, or tsdb_stats shows label explosions; pinpoints offending labels and proposes relabeling, dropping, and aggregation fixes.

tjhop Skill

Diagnose missing metrics, absent series, or scrape gaps. Use when queries unexpectedly return empty, a metric stopped reporting, a target is down or unscraped, or dashboards show no data; walks target health, metadata, and config checks.

datawhalechina Bundle

本 Skill 支持基于股票选股条件，如行情指标、财务指标等，筛选满足条件的股票；可查询指定行业 / 板块内的股票、上市公司，以及板块指数的成分股；同时支持股票、上市公司、板块 / 指数推荐等相关任务，采用此skill可避免大模型在选股时使用了过时信息。

datawhalechina Bundle

妙想提供的股票模拟组合管理系统，支持持仓查询、买卖操作、撤单、委托查询、历史成交查询和资金查询等功能。通过安全认证的API接口实现真实交易体验。

datawhalechina Bundle

本skill基于东方财富妙想搜索能力，基于金融场景进行信源智能筛选，用于获取涉及时效性信息或特定事件信息的任务，包括新闻、公告、研报、政策、交易规则、具体事件、各种影响分析、以及需要检索外部数据的非常识信息等。避免AI在搜索金融场景信息时，参考到非权威、及过时的信息。

datawhalechina Bundle

妙想自选管理skill，基于东方财富通行证账户数据及行情底层数据构建，支持通过自然语言查询、添加、删除自选股。

datawhalechina Bundle

Activates Warren Buffett's complete investment thinking system. The following scenarios must trigger it: analyzing any stock or company, evaluating investment opportunities, interpreting financial reports/annual reports/shareholder letters, assessing business moats or competitive advantages, evaluating management quality and integrity, making buy/hold/sell decisions, understanding core value investing concepts (compounding/intrinsic value/margin of safety/circle of competence/Mr. Market), analyzing any industry (insurance/banking/consumer/media/energy/railroads/technology), handling capital allocation/buybacks/dividends questions, assessing market sentiment and macro risks, exploring when to sell, analyzing institutional imperative or management behavior. Even if the user does not mention "Buffett," proactively trigger whenever the topic involves investment analysis, business quality assessment, or investment decision-making.

pulsemcp Skill

Create a valid MCP Registry server.json file for an MCP server. Use when the user wants to generate, scaffold, or write a server.json for any MCP server project.

pulsemcp Skill

Generate or update a Claude Code .mcp.json file from the project's mcp-servers/mcp.json. Use when the user wants to configure Claude Code's MCP servers from the trusted server set.

joelmeaders Bundle

A meta-skill that converts Agent Zero skills, agents, and prompts into GitHub Copilot compatible formats. Use when: exporting skills for Copilot use, creating Copilot custom agents from Agent Zero, converting prompts between systems, generating MCP server configurations. This skill enables interoperability between Agent Zero and GitHub Copilot.

joelmeaders Skill

A skill for managing kanban boards, projects, columns, cards, and comments via MCP. Use when: user needs to create or manage tasks, organize work items, track project progress, manage to-do lists, create kanban boards, move tasks through workflow stages, add comments to tasks, or perform batch operations on multiple cards at once.

joelmeaders Skill

Always-active skill that applies MiniMax M2.5 prompt engineering best practices. Automatically enriches prompts with additional context, asks for clarification when needed, and ensures clear instructions. Use when processing any user request to optimize prompt clarity and effectiveness.

taisukeoe Bundle

Guides evaluation-driven development (EDD) process for agent skills. Use when setting up skill testing workflows, creating skill evaluation scenarios, or establishing Claude A/B feedback loops for skill validation. Provides development methodology, not content guidance.

ai4curation Bundle

Run citation-bearing deep research with deep-research-client across OpenAI, Perplexity, Edison/Falcon, Cyberian, and site-specific providers such as OpenScientist. Use when a user asks for research reports, literature reviews, source-backed synthesis, or provider/model trade-off guidance.

ai-service-incubator Skill

Agent Builder - 에이전트 생성, 분할, 팀 구성을 위한 빌더 시스템. 에이전트를 프로그래밍 방식으로 관리합니다.

ndif-team Skill

Core nnsight concepts for neural network interpretability. Use when setting up models, tracing activations, saving values, or making basic interventions on model internals.

mrenaiagent Skill

Use when designing tests, implementing test cases, running tests, analyzing test coverage, or fixing test failures. Apply when user mentions testing, test cases, TDD, coverage, or asks to run tests. Use proactively after implementation is complete to ensure adequate test coverage.

mrenaiagent Skill

Use when researching AI agents, LLMs, hosting solutions, OCR technologies, video generation models, or evaluating technology stacks. Apply when user asks to research, compare, evaluate, or investigate technologies, frameworks, models, or tools. Use proactively when technical decisions require research backing.

dortort Skill

Generate and edit raster images using Nano Banana (the Gemini CLI nanobanana extension). Use this skill whenever the user wants to create, generate, make, draw, design, restore, or edit an actual image/visual asset — blog featured images, YouTube thumbnails, banners, app icons, favicons, rendered diagrams/flowchart images, seamless patterns/textures, illustrations, photos, comic/story panels, or any picture or artwork. Do NOT use it for code-based or editable diagrams (Mermaid, ASCII, SVG/markup), or for data-driven charts plotted from a dataset — those need a different tool.

agentlayer-io Skill

Submit an agent execution trajectory for human review, correction, and learning

noahjenkins Skill

Iterative prompt improvement loop (Karpathy autoresearch pattern). One iteration per invocation — run → score → hypothesize → apply → re-test → commit if improved, revert if regressed. Human-supervised; designed for single-turn skills.

googlecloudplatform-generative-ai Bundle

Holds canonical source and target environment parameters and verified DataStore mappings.

sipeed Skill

Browser automation via agent-browser CLI. Use when the user needs to navigate websites, fill forms, click buttons, take screenshots, extract data, or test web apps.

sipeed Skill

Configure, extend, debug, or contribute to PicoClaw itself. Use when the task is about PicoClaw CLI commands, config.json, gateway, auth, models, skills, MCP servers, cron, routing, sessions, self-evolution, built-in slash commands, or repository internals. Use PicoClaw-native workflows, terminology, paths, and configuration.

nvidia-nemo-datadesigner Skill

Maintain the NeMo Data Designer Fern docs site under fern/. Use for any documentation change. Triggered by: "edit docs", "add doc page", "update docs", "rename page", "fix broken link", "add redirect", "preview docs", "publish docs", "regenerate notebooks", "update dev note", any request that touches `fern/`.

octo-patch Bundle

Track AI model leaderboard rankings over time and detect rank/score changes between snapshots