Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' or 'monetization.' This skill covers pricing research, tier structure, and packaging strategy.
Elementary school math problem imitation expert: analyzes the knowledge domain, core concepts, mathematical thinking methods, difficulty level, and cognitive requirements of elementary school math problems, and generates equivalent replacement problems and multiple variations.
Produce cyber threat intelligence by pivoting on indicators to find related infrastructure, tracking actors and campaigns, enriching and contextualizing IOCs, applying attribution discipline and analytic confidence, and packaging finished intel products tied to a consumer's decision. Covers the intelligence lifecycle, the Diamond Model and Pyramid of Pain, STIX/MISP/OpenCTI storage, TLP sharing, and passive enrichment via passive DNS, crt.sh, Shodan, Censys, GreyNoise, and VirusTotal. Use when pivoting from a domain, IP, hash, or certificate to related infrastructure, tracking a threat actor or campaign, enriching raw indicators, writing a finished intel report, assessing an external report's relevance to your org, or building a threat model of adversaries that matter to you
Product Owner (/po, alias: Max, /max) - Senior PO with 10+ years agile experience. Use when defining product vision, creating/prioritizing backlog, writing user stories with acceptance criteria, making scope decisions, validating features against business goals, or planning releases and sprints.
Reverse-engineer the current state of analytics tracking from a codebase. Scans for SDK calls, identity management, and instrumentation patterns to produce a factual inventory — not recommendations. Outputs .telemetry/current-state.yaml and a timestamped audit report. Use when the user wants to know what's currently tracked, audit existing analytics, capture tracking reality before designing a new plan, 'what analytics do we have,' 'what events are tracked,' 'scan for tracking,' or 'tracking inventory.'
Design an opinionated target tracking plan and produce an explicit delta from current state to target. Combines the product model, current-state audit, and telemetry best practices to decide what events, properties, entities, and group hierarchies should exist. Outputs .telemetry/tracking-plan.yaml and .telemetry/delta.md. Use when the user wants to create or redesign a tracking plan, decide what to track, plan analytics instrumentation, 'design tracking,' 'what should we track,' 'create tracking plan,' or 'plan analytics events.'
Software project effort estimation assistant. Outputs three-point estimates (optimistic/most-likely/pessimistic values with confidence intervals), T-shirt sizes, or Function Point Analysis (FPA) counts. Triggered when users ask 'how long will this feature take,' need to assess project workload, perform PERT estimation, T-shirt sizing, FPA, sprint planning, or quote-based effort breakdowns.
Use when the user needs to understand a TOTVS Protheus ERP business process, module workflow, or cross-module integration -- covering Compras (COM), Estoque (EST), Faturamento (FAT), Financeiro (FIN), Contabilidade (CTB), Fiscal (FIS), PCP, and Manutencao de Ativos (MNT), including their main routines (e.g. MATA110, MATA460), tables/fields, and business rules. Also triggers on Portuguese phrasing like "processo de negocio", "modulo de compras/estoque/faturamento/financeiro/fiscal/contabilidade/pcp/manutencao", "como funciona o ciclo de compras", or questions about integration between modules.
Pydantic AI Python agent framework. Covers typed tools, model providers, evals, MCP, UI adapters, and observability. Use when building Python AI agents with Pydantic AI, configuring model providers, implementing typed tools/dependencies, running evals, or integrating MCP servers. Keywords: pydantic-ai, agents, evals, MCP, Logfire.
Fast local PDF parsing with PyMuPDF (fitz) for Markdown/JSON outputs and optional images/tables. Use when speed matters more than robustness, or as a fallback while heavier parsers are unavailable. Default to single-PDF parsing with per-document output folders.
Opinionated Python coding standards for clean, type-safe code. Use when writing or reviewing Python functions, classes, type hints, data structures, enums, or module organization. Applies to any Python 3.12+ project. Also use when deciding on app architecture, where to place business logic, how to organize modules, or choosing between dicts vs Pydantic models. Do NOT use for: Django-specific patterns (use django skill), test files (use pytest skill), frontend code, or shell scripts.
Python patterns for system reliability — background jobs and task queues (Celery, async), resilience and recovery (retries, backoff, timeouts, circuit breakers via tenacity), and observability (structured logging via structlog, metrics, distributed tracing, golden signals). USE WHEN building async workers, queueing tasks, handling transient network/IO failures, instrumenting Python services for production, designing retry policies, configuring logging or tracing, or any combination of these system-reliability concerns. NOT FOR language idioms or type hygiene (use `writing-python`) or project setup and dependency management (use `uv`).
Write, complete, or extend Qlik Sense load scripts (.qvs) for data preparation. Primary use case is preparing flat datasets for ML experiments with Qlik Predict — engineering features, handling train/test splits, and outputting QVD files. Also covers general Qlik load script authoring: completing scripts from starting code, comments, or prompts. Use this skill whenever the user mentions Qlik load script, .qvs files, Qlik data load, QVD output, data preparation for Qlik Predict, or asks for help writing or fixing Qlik script syntax. Also trigger when the user provides a Qlik load script and asks for modifications, extensions, feature engineering, or data transformations. Even if the user just pastes Qlik script code and asks a question about it, use this skill.
Comprehensive codebase quality audit with parallel agent orchestration, GitHub issue creation, automated PR generation per issue, and PM-prioritized recommendations. Use for code review, refactoring audits, technical debt analysis, module quality assessment, or codebase health checks.
Rough cycle time and cost estimation for CNC machined parts. Uses MNMUK plant capabilities and standard estimating factors. USE WHEN user says 'quote', 'estimate', 'cycle time', 'how long', 'cost estimate', 'pricing', 'how much to make', or describes a part needing a rough quote.
Generate and edit images with Alibaba Qwen-Image-2.0 models via inference.sh CLI. Models: Qwen-Image-2.0 (fast), Qwen-Image-2.0-Pro (professional text rendering). Capabilities: text-to-image, multi-image editing, complex text rendering. Triggers: qwen image, qwen-image, alibaba image, dashscope image, qwen image 2, qwen image pro
Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Professional text rendering, fine-grained realism, enhanced semantic adherence. Ideal for posters, banners, and text-heavy designs. Triggers: qwen image pro, qwen-image-pro, qwen 2 pro, alibaba image pro, dashscope pro, professional text rendering
Read and visualize any file—images, video, documents, code, data, 3D models, and more—with MCP tools. Use when the agent needs to inspect file contents or media metadata, crop an image, draw bounding boxes, or save document pages and video frames
Generate a ralphify-approved ralph directory (RALPH.md + optional scripts) from a plain-English description of repetitive or iterative work. Use this skill whenever the user says "ralphify", "create a ralph", "ralph wiggum", "autonomous loop", "/ralphify", references Geoffrey Huntley's Ralph Wiggum method, or asks to wrap iterative work in ralphify (test-until-green, refactor-until-done, lint-until-clean, coverage-until-90, burn-down-todos, resolve-review-comments). Trigger even when the user does not explicitly name ralphify but describes an open-ended loop ("keep fixing tests until they pass", "port files one by one until the directory is done"). Do not trigger for one-shot tasks — ralphs exist for work that benefits from running N times against a stop condition.
Design and restyle React Native and Expo UI with a real visual direction: themes and color tokens, palettes from brand colors, screen layouts, and design audits of existing screens. Measures WCAG contrast with a bundled script and applies the platform rules that web habits get wrong (shadows, gradients, edge-to-edge, safe areas, blur). Use when the task is about how a screen or component looks or is laid out: a new theme, a new screen, a UI that feels off, a web or Figma design to translate. Not for data fetching, state management, navigation wiring, or non-visual bugs.
Find, rank, and safely remove accidental codebase complexity by proving real consumers, dynamic entrypoints, compatibility obligations, duplicate representations, speculative surfaces, and lifecycle ownership. Use when asked to simplify or clean up a repository, reclaim code entropy, reduce over-engineering or redundancy, find deletion candidates, collapse duplicate state/APIs, remove dead or added-then-abandoned code beyond static-tool output, or implement an evidence-backed simplification pass in any language or stack. Also trigger for 代码化简、熵回收、删代码、清理冗余、收敛抽象、去除过度设计. Do not use as a performance audit unless simplification is the stated goal.
Inject compressed SKILL-MAP and AGENT-MAP directive blocks into CLAUDE.md so skill names and agent IDs survive a long session. Use when modifying a CLAUDE.md, when adding a skill or agent to a plugin, or for "update the skill map", "register this agent", "skills keep getting forgotten", "sync skills to CLAUDE.md".
Publish the user's own gbrain over MCP so other devices, desktop apps and cloud agents can reach it. `gbrain mcp expose` installs and signs in Tailscale, publishes the running `gbrain serve --http` on the tailnet (HTTPS, tailnet-only by default; Funnel only when a client lives in a vendor cloud), keeps the server alive as a user service, and hands back the MCP URL. Then register one least-privilege client per consumer, choose native OAuth/PKCE or a private machine handoff for that client, and verify the connection inside the intended harness.
Generate structured research questions, testable hypotheses, and candidate empirical strategies from a topic, phenomenon, or dataset description. Use when user says "give me research ideas on X", "brainstorm questions about Y", "what could I study with this data?", "I'm looking for a paper idea on...", "generate hypotheses for...". One-shot generation, not multi-turn. For idea-refinement use `/interview-me`.
Bootstrap a structured research project on any topic — generate an initial items list and research-field schema from model knowledge, supplement with up-to-date web search, then emit `outline.yaml` + `fields.yaml` that drive the rest of the research pipeline. Use when starting academic research, benchmark comparisons, technology selection, competitive analysis, market scans, literature reviews, or any structured investigation that needs a typed schema before deep dives — even when the user just says "let's research X" without explicitly asking for an outline.
Triage PR review comments by confidence score and act — fix the high-scoring ones, push back on the low-scoring ones, and ask about the borderline. Handles both inline review threads (anchored to diff lines) and PR-level review body comments (summaries submitted with reviews, like Age tables or Copilot overviews). First checks the PR's build and merge state and fixes those before processing comments. Use when the user says "respond to PR comments", "handle review feedback", "address PR reviews", "fix the build", "fix CI", "fix merge conflicts", or invokes /respond with a PR number. Also trigger when the user mentions a specific PR and wants to deal with reviewer suggestions — Copilot, human, or bot. Every reply this skill posts ends with an "agent on behalf of;" attribution line so reviewers can tell the comment came from an agent on behalf of the human, not the human directly. Do NOT use to generate a new review — that is /copilot-review's job.
Run digital forensics and incident response: triage, evidence acquisition with chain of custody, host and cloud artifact analysis, timeline reconstruction, scoping, containment, eradication, and postmortem. Use during a suspected compromise, when analyzing a disk or memory image, reconstructing an attacker timeline, or answering how far an intrusion spread
Review a GitCode pull request from a PR number or URL when `oh-gc` must fetch PR metadata, diff, and comments, local repository code must be inspected for context, and the output should be concrete findings or a GitCode submission draft. Use for GitCode PR review or comment-submission requests that depend on `oh-gc`. Do not use for generic local review, GitHub/GitLab flows, or automatic submission without explicit user confirmation.
Generate, convert, preview, and integrate retro game sound effects with raysan5/rfxgen. Use when a user needs coin, laser, explosion, power-up, hit, jump, or blip SFX; wants `.rfx` parameters converted to WAV/raw/C headers; needs batch CLI generation; or must build and troubleshoot rFXGen. Triggers on: rFXGen, rfxgen, sfxr, chiptune SFX, .rfx, procedural game sound, or sound preset.
Build and revise Rive Luau scripts across Node, Layout, Converter, Path Effect, Transition Condition, Listener Action, Util, and Test protocols. Use when the user asks to write or modify Rive scripts, choose protocols, wire script inputs or data binding, debug runtime behavior, or plan unit tests for script logic.
Build and query fully local RAG knowledge bases from documents (PDF, MD, code, etc.) using RLAMA and Ollama — no cloud, no data leaving the machine. Triggers on 'local knowledge base', 'search documents', 'document Q&A', 'RAG query', 'ingest files', 'semantic search'.
Create or load an operational runbook for a given topic. Searches `runbooks/` for an existing match; if none, scaffolds a new one from the standard template (Purpose / Prerequisites / Steps / Verification / Troubleshooting / Last Tested). Use when asked to "create a runbook", "load runbook for X", document a procedure, or look up an SOP.
Design Rust tests that catch real regressions — unit, integration, doc, property, snapshot, and golden tests, and differential tests that prove a port matches its source. Use when writing or reviewing Rust tests, when a change lands without tests, when deciding what form a test should take, when a port needs parity evidence, or when the user asks about proptest, insta, rstest, or test coverage.
Designs and manage customer loyalty programs — points, tiers, rewards, referrals, VIP programs, brand communities, retention mechanics. Covers strategy, structure, and implementation across Brevo Loyalty, Smile.io, LoyaltyLion, Yotpo, Stamp.me, Skeepers Brand Communities, and custom-built programs. Use when repeat purchase rate is low, loyalty members not redeeming rewards, unsure which loyalty platform fits, tier structure not motivating upgrades, brand community inactive, or can't prove program ROI. Do NOT use for affiliate/referral programs with commission payouts (use /sales-affiliate-program), email marketing to loyalty members (use /sales-email-marketing), checkout optimization (use /sales-checkout), or Skeepers-specific config (use /sales-skeepers). For Brevo-specific help, use /sales-brevo.
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Convert scanned PDF books (all pages are images, no text layer) into readable EPUB with a full navigation table of contents and clickable links. Recognition is done page by page by a Claude vision sub-agent (Sonnet model), while the CLI script handles page splitting and rendering, marker checks, batch merging, splitting and packaging by chapter, and EPUB validation. Whenever the user mentions "scanned PDF to ebook / PDF to EPUB / scanned book to epub / turn this book into an epub / scanned document to readable format / generate a table of contents for an image PDF", use this skill, even if they do not explicitly say "skill" or "epub".
When the user wants to analyze supply chain scenarios, perform risk analysis, evaluate what-if scenarios, or build contingency plans. Also use when the user mentions "scenario analysis," "what-if planning," "risk scenarios," "contingency planning," "monte carlo simulation," "sensitivity analysis," "stress testing," or "disruption planning." For demand uncertainty, see demand-forecasting. For S&OP scenario integration, see sales-operations-planning.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.