AI & ML

prathamdby Bundle

Use when seeding, refreshing, or expanding `.pr-agent/*.mdc` repo policy rules; when asked to help the PR Agent catch more codebase-specific bugs via review policy; when exploring this repo to author Cursor-style `.mdc` preference memory; or when tempted to dump conventions into AGENTS.md, CONVENTIONS.md, README, or a `pr-agent/` (no-dot) folder instead.

punitarani Skill

Guidance for installing and using Fli correctly as a CLI and MCP server. Use when: setting up Fli with pipx, running `fli` flight searches, configuring Claude Desktop with `fli-mcp`, using the HTTP MCP server, or troubleshooting Fli command availability and common usage mistakes.

prebid Bundle

Install and use Chrome DevTools MCP's experimental third-party developer tools to inspect a live Prebid.js page. Use when an agent needs to configure chrome-devtools-mcp for Prebid.js, discover the Prebid.js DevTools tool group, diagnose auctions, bids, no-bids, wins, floors, TTL/cache eligibility, event timing, installed modules, runtime configuration, or multiple Prebid instances, and correlate that runtime state with browser console and network evidence.

qqyule Bundle

Use when an agent must act as 世界杯预测机 for World Cup prediction, 2026 世界杯模拟, 世界杯胜平负概率, 90-minute match probabilities, champion or qualification probability explanation, audited offline input checks, completed-result tournament continuation, or cautious China football lottery 3/1/0 reference lists.

qtqtericchiu Bundle

无限暖暖（Infinity Nikki）综合管理工具集。提供 Steam 版本管理（SteamDB 检测、ACF 反更新、骨架化空间清理、网络诊断）与奇想手账工具集（体力提醒、美鸭梨挖掘进度、抽卡记录查询、探索进度查询）。适用于 OpenClaw、WorkBuddy、Marvis、QClaw 等 AI Agent 平台。所有用户数据持久化通过 \<AGENT_USERDATA_DIR\> 变量注入，不硬编码平台或用户路径。

prism-php Bundle

Guide for developing with Prism PHP package - a Laravel package for integrating LLMs. Activate or use when working with Prism features including text generation, structured output, embeddings, image generation, audio processing, streaming, tools/function calling, or any LLM provider integration (OpenAI, Anthropic, Gemini, Mistral, Groq, XAI, DeepSeek, OpenRouter, Ollama, VoyageAI, ElevenLabs). Activate for any Prism-related development tasks.

psylch Bundle

Architectural routing layer over agent-browser CLI: picks the right tool (agent-browser fresh Chromium / agent-browser shared real-Chrome / camofox-browser anti-detect) for each task, and adds login-watch, CAPTCHA/automation-block detection, per-domain site experience, and parallel multi-tab via CDP proxy. Triggers: 'parallel browse', 'open multiple tabs', 'batch scrape', 'captcha check', 'automation blocked', 'site pattern', 'better browser', 'cdp proxy', 'parallel tabs', 'login watch', 'cloudflare blocked', 'datadome', 'anti-detect scrape'.

pygent-ai Bundle

Build, query, test, and optimize a local agent memory CLI where durable memories are represented as retrieval unit tests. Use when the user asks Codex to create, maintain, inspect, or improve a memory-cli project; when a workspace already contains a memory-cli, .memory, or memories project; or when Codex must add, update, retire, or validate durable memory records through a CLI contract.

quanru Bundle

Run a cross-review using the opposite CLI reviewer for proposal review and change assessment. Use when the user asks for cross review, 交叉 review, 交叉评审, second-opinion review, Codex-vs-Claude review, or wants the current host agent to ask the other reviewer whether a design or code change is reasonable, what risks it creates, and whether there is a simpler or stronger alternative.

pyqcm-project Bundle

Assists with pyqcm, the Python/C++ library for quantum cluster methods (CPT, VCA, CDMFT) used to study strongly correlated electron models like the Hubbard model. Use this whenever the user is writing or debugging a pyqcm script (defining clusters, lattice models, operators, parameters, running model_instance calculations), interpreting pyqcm output (spectral functions, Green's functions, self-energy, order parameters, ground state averages, phase diagrams), or reading/modifying the pyqcm source itself (the src_ed exact-diagonalization solver, the src_qcm lattice/CPT-VCA-CDMFT engine, or the src_python nanobind bindings). Also trigger on mentions of cluster perturbation theory, exact diagonalization impurity solver, Lanczos, Lehmann representation, or the qcm_wed/pyqcm-project repository, even if the user doesn't say "pyqcm" by name.

quantskills Bundle

Use when an agent needs to neutralize or orthogonalize a quantitative factor against industry, size, style exposures, or an existing factor library before evaluating, combining, or accepting the signal.

quantskills Bundle

Use when a general-purpose AI agent needs to find A-share stocks or futures with similar K-line patterns from natural-language descriptions, K-line screenshots, or hand-drawn trend images. Supports daily and 60-minute timeframes, 30/60/120 BAR windows, hosted MCP tools, and a direct helper script for platforms without MCP. Standard template words such as strong trend continuation, bottom reversal, W-bottom, trend pullback, range consolidation, and M-top must route to server radar templates before any generated drawing. Image attachments must route through image search directly. Also covers user-facing result formatting and routing users to the PatternCatcher website for saved patterns and daily Feishu/WeCom subscriptions.

qwaitcrypto Skill

Use whenever the task involves project documentation, architecture, design decisions, implementation plans, specs, worklogs, project memory, or any durable knowledge that should live in the repo. This includes reading or writing docs, querying prior decisions, checking doc health, reviewing history, updating AGENTS.md / CLAUDE.md / ARCHITECTURE.md, or organizing project knowledge. If the repo has AGENTS.md, CLAUDE.md, or .harnesskit/, treat HarnessKit as the default documentation workflow: read the entrypoint first, then use the CLI when query, context, checks, indexing, or history are useful.

quentintou Bundle

Autonomous browser automation for AI agents. Two tools: agent-browser (CLI Playwright for step-by-step control) and browser-use (Python autonomous agent that decides what to do on pages). Navigate, click, fill forms, scrape data, manage sessions, and run complex multi-step browser tasks.

qwwiwi Bundle

Senior full-stack architect for educational SaaS platforms (Teachable/Thinkific/Kajabi level). Provides decision frameworks, stage-aware stack recommendations, architecture patterns, AI/LLM integration, agent-native design, security threat modeling, testing strategies, and MCP integration guidance. Triggers: /senior-brainstorm, "brainstorm", "architecture", "how to build", "stack selection", "tech choice", "architectural decision", "design this", "senior brainstorm", "platform stack". NOT for: simple CRUD tasks, non-EdTech projects, single-framework questions without product context.

qwwiwi Skill

Search, evaluate, and recommend agent skills from the skills.sh directory. Use when: (1) user asks to find/search a skill for X, (2) "есть скилл для...", (3) "skill for zoom/notion/stripe/...", (4) "поищи на skills.sh", (5) "нужен плагин/расширение/скилл для...", (6) "как подключить X к Claude Code", (7) any mention of skills.sh, (8) "найди скилл", (9) "find skill", (10) user shares a skills.sh link for review.

rajveer-mahida Bundle

Multi-agent workflow orchestrator for software projects. Use when the user says spidy, implement using spidy, plan with spidy, spidy new project, spidy debug, or asks to run any spidy workflow. Also use when the user says commit, push, create pr, git workflow, ship it, or asks to branch/commit/PR their changes. Orchestrates specialist agents for: new-project setup, phase planning, phase execution, verification, debugging, codebase mapping, and git workflow.

ralph-wren Bundle

Omni-Recall: Neural Knowledge & Long-Term Context Engine with Vector Semantic Search. Manages cross-session agent memory via Supabase (pgvector + HNSW) and LLMHub. Supports intelligent natural language queries with similarity scoring.

quran Skill

Use when choosing Quran Foundation API families, authentication flows, endpoints, SDK runtime boundaries, Developer Console onboarding, font rendering, or official integration references.

quynj Bundle

Use when the user wants to turn a long YouTube interview, talk, or podcast into 5 to 8 short clips for a target audience language. This skill downloads the source video and any available subtitles, can transcribe videos that have no subtitles with an open-source Whisper model, lets the calling AI translate subtitles into a user-specified target language, analyzes the transcript, selects strong standalone moments, cuts clips under 3 minutes, prepares target-language packaging copy, and burns stacked bilingual subtitles into the exported videos.

qwwiwi Bundle

Audit and redesign workflows that depend too much on LLM reasoning. Use when: (1) repeated operational logic still lives in prompts or model memory, (2) you are designing triage, routing, escalation, summaries, alerts, coordination, reporting, or content/ops pipelines, (3) you need to decide what should move out of the model and into system state, triggers, scripts, tools, runbooks, or policy, (4) a user asks to make an agent workflow more systematic, deterministic, less noisy, less fragile, or less dependent on “keeping things in the model’s head”, (5) you are auditing repeated workflows for drift, stale thresholds, duplication, inconsistent routing, or unstable alert quality.

ralphcrisostomo Bundle

Use when the user invokes /herdr-goal with a large multi-part objective inside a Herdr session (HERDR_ENV=1) and wants it split across parallel lead agents. Not for single tasks one agent can do directly, and not outside Herdr.

rammc Bundle

Implement, review, or improve Salesforce Agentforce agents written in Agent Script — the declarative DSL for hybrid reasoning in the Agentforce Builder. Use when working with Agent Script syntax (blocks, expressions, variables, hooks, transitions, action chaining); when designing topics or subagents and the start_agent block; when exposing actions as tools to the LLM via reasoning actions; when balancing deterministic logic instructions against LLM prompt instructions; when migrating between Topics and Subagents terminology (April 2026 rename); when building agents in Agentforce Builder Canvas or Script view; when using Agentforce DX CLI or the Agentforce DX VS Code extension; or when writing agents with Agentforce Vibes. Trigger this skill whenever the user mentions Agentforce, Agent Script, agent topics, subagents, Atlas Reasoning Engine in a scripting context, agent transitions, reasoning actions, @utils, @variables, or @actions — even if they don't explicitly name the skill.

raphaelsalaja Bundle

Generate a SoundDefinition for @web-kits/audio from any input - a natural-language prompt, an audio file the user shares, or both. Use when the user says "create a sound", "/create-sound", "design a sound for X", shares a WAV/MP3/sprite, or asks to reverse-engineer a sample. Optionally renders a WAV preview and round-trip-validates the result.

realskyrin Bundle

Annotate existing image files with the clipcap command-line agent. Use only when the user supplies an image file and wants deterministic arrows, boxes, labels, mosaic blocks, or callouts rendered into a PNG. This skill must not capture the screen or request macOS privacy permissions.

r14521128 Bundle

Use whenever the user works on FLAC3D 6.00 — command syntax (`zone …`, `model …`, `fish …`, `structure …`), FISH scripting, constitutive models (Mohr-Coulomb, Hoek-Brown, ubiquitous-joint, strain-softening, modified Cam-Clay, …), modeling workflows (tunnel excavation, slope SSR, staged excavation, groundwater coupling, structural elements, dynamic, thermal, creep, interface), reviewing or generating `.f3dat`/`.f3prj`/`.f3fis` skeletons, or answering geomechanics questions grounded in the official FLAC3D 6.00 install at `C:\Program Files\Itasca\Flac3d600\`. Activates on `.f3dat`/`.f3prj`/`.f3fis`/`.fis`/`.dat`/`.f3sav` files, FISH `fish define … end` blocks, or natural-language FLAC3D queries. Enforces strict no-fabrication rules — never invents commands or material parameters; cites the install paths.

resolved-sh Bundle

The fastest way for any agent to launch a business on the open internet — page, data storefront, custom domain. Trigger when an agent needs: a public URL or `/.well-known/agent-card.json` endpoint, a way to monetize (paid API gateway, paid data queries/downloads, paid blog posts, paid courses, paid Q&A inbox, tip jar, sponsored slots, paywalled page sections), a free permanent subdomain at `{slug}.resolved.sh`, a custom .com or .sh domain purchase, live activity feeds (Pulse events, follower digests, waitlists), or social proof (testimonials, contact form, changelog). Covers the full operator lifecycle: bootstrap identity (ES256 keypair, no human in loop), publish or register, configure revenue streams, upgrade for vanity/BYOD/domain, operate & maintain, distribute. Three payment rails: x402 USDC on Base, MPP Tempo USDC on Tempo, or Stripe credit card — all marketplace earnings go 100% directly to the operator's EVM wallet at time of purchase. Full machine-readable spec: https://resolved.sh/llms.txt

rarce Bundle

Maintain a personal, LLM-curated knowledge wiki in a git repo using the Karpathy LLM-wiki pattern. Use this skill when the user wants to ingest a source (article, paper, notes, URL) into their wiki, query accumulated knowledge ("what do I know about X?", "what did I learn from Y?"), or lint the wiki for drift. Activate even when the user does not explicitly say "wiki" — e.g., "save this paper to my notes", "add this to what I know about X", or "check my notes for contradictions". Uses `qmd` for on-device hybrid BM25+vector search and `gh` only for GitHub-backed wiki repos. Do not invoke for installing this skill, unrelated markdown editing, or general GitHub work.

raroque Bundle

Use when reviewing, debugging, or building AI agents with the Claude Agent SDK (TypeScript or Python). Covers the Agent class, query(), agent.stream(), tool_use, tool schemas, maxIterations, subagents, hooks (PreToolCall, PostToolCall, StopHook), MCP integration, multi-agent coordination, structured output, context window management, stop_reason handling, and agentic loop architecture. Do NOT activate for general Claude API usage without agents, simple messages.create() calls, or non-agent Anthropic SDK usage — use the claude-api skill for those.

rebelytics Bundle

Companion skill for the Peec AI MCP server (https://api.peec.ai/mcp). Load when the user does Peec reporting, analysis, or multi-step work — visibility reports, per-engine comparisons, competitive gap analysis, source-authority audits, project tune-ups (brands, prompts, topics, tags), or Peec slash commands (`peec_weekly_pulse`, `peec_competitor_radar`, `peec_engine_scorecard`, `peec_topic_heatmap`, `peec_prompt_grader`, `peec_source_authority`, `peec_campaign_tracker`). Also load for Peec data interpretation (sentiment, position, visibility, share of voice, retrieval vs citation, `get_actions` two-step workflow, `list_prompts.volume` ordinals, `get_url_content` 5-day refresh cadence) or when combining two or more Peec tools. Skip for trivial single-tool lookups like `list_projects`, `list_brands`, `list_topics` where Peec's own tool descriptions suffice. Teaches agents the real behaviour of the Peec MCP, including gotchas the official docs omit or get wrong.

rabithua Bundle

Manage Rote notes, articles, attachments, reactions, settings, and note share links. Use when an agent should operate Rote through an already-connected OAuth HTTP MCP server or through rote-toolkit CLI, SDK, or stdio MCP with a local OpenKey workflow.

restatedev Bundle

Design, build, run, and test Restate durable services, virtual objects, workflows, and AI agents across TypeScript, Python, Java, and Go. This skill should be used when the user mentions "restate", "durable execution", "virtual object", "restate service", "restate workflow", or "durable agent" or wants to build resilient backend services, AI agents, or workflows with automatic failure recovery. Also use when converting existing applications or migrating from workflow orchestrators to Restate. Use proactively when a project contains restate dependencies in package.json, requirements.txt, pyproject.toml, pom.xml, build.gradle, or go.mod.

raichominev Bundle

Adversarial cross-model review for hard, load-bearing tasks — combining frontier models: the Claude session (Opus 5 or Fable 5 as the intended orchestrator) hands a claim, diff, or result to an OpenAI model (gpt-5.6-sol / gpt-5.6-terra / gpt-5.5, via the codex CLI on ChatGPT-subscription auth, no API key), which probes it with falsification attempts and PROPOSES a verdict; the orchestrator checks the probe and RATIFIES. Two EXPERIMENTAL, opt-in extra-family seats can be added when asked for — Kimi (Moonshot, via the Kimi Code CLI or the local Kimi Desktop runner) and Grok (xAI, via the Cursor Agent CLI on Cursor-subscription auth); neither is part of a default round. Use whenever the user wants a second opinion from a different model, a cross-model or concilium review, adversarial verification of a research claim, benchmark number, or diff, says "have GPT/codex check this", explicitly asks to add the kimi or grok seat, wants codex set up as a reviewer, needs to switch codex models mid-session (park-and-resume

reflectt Bundle

Agent Memory Kit

reflectt Bundle

Agent Team Kit

rauls-kjarners Bundle

Offloads heavy, token-intensive reasoning and search tasks to Antigravity CLI (agy) via MCP. MANDATORY delegation for grep, git diff, git log, large files, multi-file analysis.