MCP server development including tool design, resource endpoints, prompt templates, and transport configuration

Load MCP development patterns and best practices for building tools with the @umbraco-cms/mcp-server-sdk. Use when starting tool development or needing pattern reference.

Pattern for building MCP servers in Next.js with mcp-handler, shared Zod schemas, and reusable server actions.

Debug MCP server communication. Use for troubleshooting MCP integrations, viewing traffic, and analyzing latency.

Load MCP eval testing patterns using @umbraco-cms/mcp-server-sdk/evals. Use when writing LLM-based acceptance tests for MCP tools.

Use when user shares a Medium article URL behind a paywall and wants to read the full content. Also use for articles on Medium-hosted publications like towardsdatascience.com, betterprogramming.pub, levelup.gitconnected.com, etc.

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

# Member Profile Management

Auto-executes when the [CRABSHELL_SAVE] trigger is detected in hook output. Saves session memory following a numbered step sequence. Not user-invocable — triggered automatically by the plugin system.

Merge all open pull requests, close linked issues, delete feature branches, and clean up local and remote refs. Use when completing features, merging PRs after review, or finalizing a release cycle.

Bayesian meta-analysis models including fixed effects, random effects, and network meta-analysis with Stan and JAGS implementations.

Define product metrics with a North Star, input/output tree, and counter-metrics. Use when asked to define metrics, set up measurement, choose KPIs, pick a north star metric, or build a metrics framework. Prevents vanity metrics and gaming.

Use when designing small UI feedback moments like button states, toggles, form validation, loading indicators, or notification badges.

Microservices design patterns including service mesh, event-driven architecture, saga pattern, and API gateway

Plan and execute migrations (database, API, framework)

Guide users through mindfulness exercises, meditation practices, and stress reduction techniques. Use when users ask for help with relaxation, stress management, breathing exercises, or cultivating inner peace.

Use when finishing a Pi, Codex, or other coding-agent session and wanting to save a lean Markdown session note into an Obsidian vault with decisions, code changes, validation, caveats, and follow-ups.

External-lookup skill with NO brain-first compliance

Complete guide to implementing modals in the finstreet context. Covers the store, modal component, and optional open button. Use when building or modifying any modal.

# Model Routing System

Generates structured, career-focused modular curriculums for software engineering students. Use when designing new educational modules or tailoring learning journeys to specific career roles.

Define a motion system with duration tokens, easing vocabulary, and reduced-motion handling for consistent animation across a product.

# Microsoft 365 Operations (MCP-by-Code)

Run parallel Claude instances for writer+reviewer patterns, git worktrees, and specialist agents. Use for independent verification and parallel progress.

Skill that uses multiple external tools without compliance

Guide building a minimum viable product the minimalist entrepreneur way — manual first, then processized, then productized. Use when someone is ready to build their first product or struggling with scope.

Use when animation should feel organic and lifelike—creature animation, realistic characters, nature elements, or any motion that needs to breathe with authentic living quality.

Create an admin user in Medusa

Next.js 14+ App Router patterns including RSC, ISR, middleware, parallel routes, and data fetching

Skill that operates purely on local state

A skill that lacks negative triggers in its description.

Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.

Generate production-ready Express + TypeScript + PostgreSQL + Redis projects. Use when the user wants to create a new backend service, API, or microservice from scratch. Automatically invoked when discussing project scaffolding or generation.

GitHub notifications command center -- read, filter, triage, and manage notifications entirely from the editor. Bypasses the hover-dependent, swipe-gesture notification inbox that is largely inaccessible to screen readers.

Use when publishing or releasing a new version of an npm/pnpm/yarn/bun package to the registry. Covers package-manager detection, semver bump selection, tagging, pushing, scoped-package access, authentication, and one-time passwords (OTP).

Design first-run experiences that get users to value quickly without overwhelming them.

Skills for querying ontologies using the Ontology Access Kit (OAK). This should only be used for complex ontology operations, for basic external ontology searching use the OLS MCP

Run this skill to harden openclaw's security by adding an override so that the admin can always get into the bot even if the allowlist is corrupted. It effectively ensures the "breakglass" admin phone number never loses access.

Knowledge and patterns for identifying and resolving performance issues.

Use when building multi-part animation sequences - staggered reveals, choreographed UI, coordinated motion where multiple elements work together

Use to assess + improve project structure — folder layout, file placement, naming, separation of concerns. Read-mostly with structured proposal output. User approves before any moves.

Summarise an academic paper from URL, DOI, or file path

Only to be triggered by explicit /parallel-task commands.

Expert system for reviewing utility patent applications against USPTO MPEP guidelines.

Use to freeze current session state with rich resumption context. "Pause this", "save my place", "I need to step away". Different from native task tracking — captures full thinking state, not just todos.

PDF accessibility remediator. Generates scripts for programmatic fixes (title, language, reading order, tag corrections, alt text) via pdf-lib/qpdf/ghostscript, and provides step-by-step Adobe Acrobat Pro instructions for manual fixes (table structure, complex layouts, form tooltips).

Evaluates student code submissions based on conceptual mastery rather than just correctness. Use to provide high-quality educational feedback on architectural patterns and programming logic.

Performance analysis, profiling, and optimization

Use for dedicated performance profiling — wall time, CPU, memory, allocation, query count, network. Different from /optimize (which assumes a target). Perf measures + reports; optimize fixes.

Use this skill when the user asks to "analyze performance", "check bundle size", "optimize component", "analyze imports", "reduce bundle", "check for performance issues", or wants to identify and fix performance bottlenecks in their Storybook components with AI-powered suggestions.

Analyzes code for performance issues including inefficient algorithms, unnecessary computations, memory leaks, large file sizes, slow queries, and missing caching. Returns structured performance issue reports with optimization suggestions.

Web performance optimization including bundle analysis, lazy loading, caching strategies, and Core Web Vitals

Profile and optimize application performance including load times, memory usage, and rendering. Use when debugging slow performance, memory leaks, or optimizing app speed.

Shared branch creation and verification logic for sequential and parallel task execution - handles git operations, HEAD verification, and MODE-specific behavior

Multi-agent ensemble planning with pl4n CLI. Use when discussing implementation plans, task planning, or when user mentions pl4n sessions. Knows pl4n CLI syntax and workflow.

Use when a plan exists and needs validation gates added to each step before implementation begins. Produces task files that implement can consume. Triggers include "break down this plan", "add validation to the plan steps", "plan-breakdown", and "gate this plan".

Use after creating a plan and before exiting plan mode. Contains a checklist of things to remember with the plan.

Analyze code and recommend refactoring opportunities

Software architect and planning specialist - conduct thorough read-only planning before any action. Use when exploring a codebase to design implementation plans, defining objectives, gathering relevant files, and summarizing available tools before coding begins.

Execute end-to-end testing of React micro frontends using Playwright MCP to validate functionality, responsiveness, and user workflows

Automated visual QA testing using Playwright — navigate web apps like a real user, capture screenshots, find bugs, and fix them.

Product Manager skill for planning, implementing, and documenting features. Use when creating GitHub issues from specs, implementing planned work, or maintaining project documentation.

Use when the codebase spans multiple languages/runtimes — frontend (TS) + backend (Python) + infra (HCL) + scripts (Bash). Finds cross-language consistency issues — naming, types, API shape, error contracts.

Use when implementing Disney's 12 animation principles with Popmotion's functional animation library

Brainstorm product positioning ideas differentiated from competitors. Identifies top competitors and generates positioning statements with rationale. Use when developing product positioning, differentiating from competitors, or crafting brand positioning strategy.

PostgreSQL optimization including indexes, query plans, partitioning, JSONB operations, and connection pooling

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.

Use this skill when posting inline comments to GitHub pull requests. Apply when formatting comments following Bitwarden engineering standards with severity emojis, clear explanations, and actionable suggestions. Use after findings are classified and ready to post. DO NOT USE when posting summary comments.

Run as a background subagent after a PR is created or pushed. Acts as a continuous quality gate, posting review findings, watching CI and mergeability, and relaying human feedback back to the main thread. Invoke via the Agent tool with run_in_background true.

Merge one or more PRs into the base branch with queue-like sequencing and conflict resolution. Use when merging PRs that may conflict with each other or the base, requiring ordered application and intelligent conflict handling.

Review code changes on a given GitHub PR using gh CLI. Use when the user asks to review a pull request, analyze PR diffs, or provide feedback on open PRs with structured quality, security, and testing assessments.

Capture and document UI changes with before/after screenshots for pull requests. Use when creating PRs that include visual changes to ensure reviewers can assess design modifications.

Use when creating PRs, linking issues, managing PR comments, or creating GitHub issues

Use when organizing PRDs, tracking requirements, managing product specs, updating PRD status, archiving completed docs, or setting up PRD structure. Auto-applies naming conventions and lifecycle management.

Use when ready to build a reviewable implementation plan as a lore artifact. Input can be a spec, design, brainstorm, research, or a well-defined prompt. Triggers include "prep plan", "prepare a plan", "plan this", "make a plan", "plan the implementation", and "break this into steps".

Use when creating Keynote, PowerPoint, Google Slides animations, or any presentation motion design work.

Help figure out pricing for a product or service using minimalist entrepreneur principles. Use when someone is setting prices, considering price changes, or struggling with what to charge.

Key facts and breaking changes for upgrading to Prisma ORM 7. Consider version 7 changes before generation or troubleshooting

Use when animation "feels wrong" but you can't pinpoint why—debugging floaty movement, stiff characters, unclear action, or any motion that isn't working and needs systematic troubleshooting.

Design a product-led sales motion from usage signals to sales handoff and conversion.

Brainstorm an inspiring, achievable, and emotional product vision that motivates teams and aligns stakeholders. Use when defining or refining a product vision, creating a vision statement, or aligning the team around a shared direction.

# Progressive Memory

Analyzes any project to understand its structure, tech stack, patterns, and conventions. Use when starting work on a new codebase, onboarding, or when asked "how does this project work?" or "what's the architecture?"

One-time project setup for creative writing. Interviews you about your project, collects writing samples, proposes kb structure, and creates CLAUDE.md with project conventions.

Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design

A test skill with prompt injection patterns

Minify verbose prompts into semantically equivalent minimal prompts while preserving behavior. Supports configurable output modes (prompt-only or prompt + compression report).

Propose structured interpretations of underspecified requests. Use when a user's request is vague or incomplete but reasonable assumptions can be made. Rapidly prototypes intent by restating, structuring, and committing to a next action.

This skill should be used when the user submits code for review, shares a pull request, pastes a code snippet, asks "what's wrong with this", "review this PR", "is this code good", "find bugs", "code smell", or any request involving code quality analysis. Performs forensic code autopsy with zero mercy.

Publish a skill folder as a .skill package to GitHub. Use when distributing skills.

Download the persistent memory database from your self-hosted dashboard into the current repo. Use after cloning a repo on a new machine to restore accumulated sessions, knowledge, facts, and embeddings for RAG/context.

Use pup to query Datadog metrics and logs -- search, query, aggregate, list, and analyze observability data from the command line.

Use when running git push or diagnosing why a push failed. Especially when output mixes SSH transport with hook output (lefthook, husky, pre-commit), errors include "Permission denied (publickey)" or "rejected/non-fast-forward", a pre-push hook fails, or about to debug SSH with `-v`.

Use for Python development requiring async programming, type system expertise, testing patterns, or performance optimization.

Use when building or structuring Python CLI commands with Typer, including commands, options, and multi-command apps.

Android device logcat reader for real-time log monitoring. Use when working with pywayne.adb.logcat_reader module to read Android device logs via adb logcat command, supporting both C++ backend (faster) and Python backend (subprocess) with generator-style output for streaming logs.