Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Create, publish, delete, and submit plugins for coding agents (Claude Code, OpenCode, Devin CLI/Desktop). Use when user wants to (1) create a new plugin with proper structure, (2) create or configure a plugin marketplace, (3) publish plugins to GitHub/GitLab/npm, (4) delete/uninstall plugins, (5) validate plugin structure, or (6) prepare and submit plugins to the official Anthropic directory or the OpenCode ecosystem.
Articulate your organization's Distinctive Competencies the Pragmatic Institute way — the unique abilities to deliver value that are valued, different, and provable. Use when a PM says “what makes us different”, “our moat”, “unique strengths”, “why us”, “competitive advantage”, or “distinctive competence”. Strategy = intersect market problems with what only you can do. Produces a Distinctive Competencies worksheet as a Markdown or Word .docx artifact.
Run a Pragmatic Institute Gap Analysis — a market-driven self-assessment of how well the team performs the 37 activities of the Pragmatic Framework, who owns each, and where the biggest gaps are. Use when the PM asks “where do we stand”, “how are we doing on the framework”, a product-org self-assessment, a maturity check, or where to focus. Produces a Gap Analysis table plus a top-3-gaps action plan as a Markdown or Word .docx artifact.
Create a Pragmatic Institute Positioning Document — describe a product by the market problems it solves (not features), for one persona in one segment. Use when the PM asks for positioning, messaging, “how do we describe/pitch this”, an internal positioning doc, or a positioning statement. Produces a Positioning Document plus a Problem-Oriented Capabilities (POC) worksheet as a Markdown or Word .docx artifact.
Build a Pragmatic Institute Strategy Matrix — a forced-choice 4×4 that decides who to win and what to build over a set time frame, and surfaces alignment between the product team and leadership. Use when the PM asks about product strategy, “where should we invest”, “what should we build for whom”, focus, prioritizing markets, or avoiding a spread-too-thin roadmap. Produces a Strategy Matrix as a Markdown or Word .docx artifact.
Write market-driven, prioritized product requirements (a Market Requirements Document / MRD) the Pragmatic Institute way. Use when the PM asks for “requirements”, “an MRD”, “what should we build”, “prioritize features”, “market requirements”, or wants development to stop saying “requirements aren't specific enough”. Articulates each requirement as a persona's problem, prioritizes with Market Evidence × Impact, and groups them for delivery. Produces a Market Requirements Document as a Markdown or Word .docx artifact.
Run a Pragmatic Institute Win/Loss analysis — understand why recent evaluators did or did not buy and the steps they took in their buying process. Use when a PM says “why did we win/lose”, “win-loss”, “why do deals slip”, “churn reasons”, “why did they pick the competitor”, or “interview a lost prospect”. Enforces the rule that win/loss is run by an objective party not involved in the sale, and evaluates the buying PROCESS, not the salespeople. Produces a Win/Loss Interview Guide and a Win/Loss Findings Report as a Markdown or Word .docx artifact.
Draft labour rules and regulations / employee handbooks — including province-level supplementary clauses, generating local versions where the law differs by jurisdiction. Use when the user says "draft a [topic] policy", "we need rules on [topic]", "update our [topic] policy", or points out a policy gap.
Set up, inspect, link, and deploy Polpo projects using the current .polpo directory layout and CLI. Use for project bootstrap, project files, cloud linking, deployment, or deciding whether behavior belongs to Polpo OSS or Polpo Cloud. For agent design, runtime calls, Channels, integrations, or React UI, use the corresponding specialized Polpo skill.
Build React interfaces for Polpo agents with @polpo-ai/react and @polpo-ai/chat. Use for chat components, Sessions, durable reconnect, attachments, ask-user interactions, suggestions, client tool rendering and continuation, agent selection, or Polpo UI theming.
Debug failing Power Automate cloud flows using the FlowStudio MCP server. The Graph API only shows top-level status codes. This skill gives your agent action-level inputs and outputs to find the actual root cause. Load this skill when asked to: debug a flow, investigate a failed run, why is this flow failing, inspect action outputs, find the root cause of a flow error, fix a broken Power Automate flow, diagnose a timeout, trace a DynamicOperationRequestFailure, check connector auth errors, read error details from a run, or troubleshoot expression failures. Requires a FlowStudio MCP subscription — see https://mcp.flowstudio.app
Foundation skill for Power Automate via FlowStudio MCP — auth setup, the reusable MCP helper (Python + Node.js), tool discovery via `list_skills` / `tool_search`, and oversized-response handling. Load this skill first when connecting an agent to Power Automate. For specialized workflows, load `power-automate-build`, `power-automate-debug`, `power-automate-monitoring` (Pro+), or `power-automate-governance` (Pro+) — each contains the workflow narrative, this skill provides the plumbing they all rely on. Requires a FlowStudio MCP subscription or compatible server — see https://mcp.flowstudio.app
Enhance copy with emotional trigger words from 21 psychological categories. Use when headlines feel flat, CTAs lack urgency, copy needs more punch, or conversion rates are low. Transforms bland text into compelling, conversion-focused content.
Comprehensive guide to React Query (TanStack Query) covering data fetching, caching, mutations, error handling, TypeScript, testing, and advanced patterns. Use when working with React Query, TanStack Query, or async state management in React applications.
Conduct a thorough pre-implementation discussion before making significant changes. Use when the user wants to discuss, plan, or evaluate a change before implementing it — especially when they say words like 'discuss', 'evaluate', 'plan', or 'let's talk about'.
Run a premortem on any plan, launch, product, hire, pricing change, strategy, or high-stakes decision. Uses Gary Klein's prospective-hindsight method — assume it already failed at a future date and work backward to surface every plan-specific cause, then produce a revised plan, mitigations, early-warning signals, and a pre-launch checklist. USE WHEN premortem this, run a premortem, what could kill this, future-proof this, stress test this plan, what am I missing here, find the blind spots, what could go wrong, am I missing anything, poke holes in this, where will this break, before I commit to this. NOT FOR adversarial attack on an arbitrary idea or argument (use RedTeam), current-state multi-perspective debate (use Council), network/system vulnerability testing (use Security), or simple feedback/factual questions. DO trigger when someone has a concrete plan or commitment where the cost of being wrong is high and the decision is still changeable.
Review of the three attributes of evidence — a first-round review of an evidence list, making clear legality/relevance judgements and flagging difficult items that need lawyer review. Use when the user says "review the evidence list", "three-attribute evidence review", "check the admissibility of this evidence", or has an evidence list to screen before cross-examination.
Designs complete onboarding, activation, retention, and expansion lifecycles for SaaS products. Use when the user mentions 'onboarding lifecycle,' 'activation strategy,' 'user onboarding,' 'time to value,' 'aha moment,' 'onboarding audit,' 'retention lifecycle,' or 'lifecycle design.'
Use this skill when project delivery constraints or action tracking are needed for test strategy, test strategy review, or test report review; triggers include project delivery perspective, delivery planning, schedule and capacity.
Researches any project idea against live data from GitHub and Dev.to to surface what already exists, how mature the space is, and where the real opportunity lives. Use when a developer describes something they want to build and wants to know if it's been done before. Triggers on phrases like "validate my idea", "has this been built", "is this already a thing", "what exists for X", "should I build this", "is this idea original", "check if my project exists", "what are the alternatives to what I want to build", "is the market saturated for X", or any request to research the competitive landscape before starting a project.
Engineers prompts into clear, structured, model-optimized instructions using the 4-D methodology (Deconstruct, Diagnose, Develop, Deliver) with architecture-specific tuning. Use when a draft prompt, instruction set, or agent skill description needs refinement for clarity or improved performance.
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches - a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "try a few designs".
Bulk RNA-seq DE with PyDESeq2: load counts, normalize, fit negative binomial models, Wald test (BH-FDR), LFC shrinkage, volcano/MA plots. Use for two-group comparisons, multi-factor designs with batch correction, multiple contrasts.
You are an expert Python software engineer with deep knowledge of modern Python 3.12+ best practices. Use when creating new Python projects, reviewing Python code, refactoring existing code, or when the user asks about Python project structure, dependencies, type hints, testing, or modern Python features. Ensures code follows current best practices with proper tooling (uv, ruff, ty/mypy, pytest), type hints, dataclasses, async patterns, and project structure. Includes version-specific features for 3.12, 3.13, and 3.14
Hardens a Python repository's supply chain — Dependabot update automation, pip-audit vulnerability scanning, secret scanning and push protection, CodeQL, OpenSSF Scorecard, SBOMs, CODEOWNERS. Use for 'set up dependabot', 'audit dependencies', 'someone committed a key — stop that happening again', 'protect paths with CODEOWNERS', 'harden this repo'. Not for CI quality gates, workflow hardening, or PyPI publishing.
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.