Generates a product spec doc in Markdown from a Jira ticket. Use when the user provides a Jira ticket ID (e.g. CCC-284) or URL and asks for a spec, design doc, or tech spec ("write a spec for this ticket", "make a spec from this Jira").

Manage version control with Jujutsu (jj) — no staging area, immediate changes, smart rebasing. Use when navigating history, squashing, or pushing to Git remotes.

Use this skill when the user is new and doesn't know where to start, asks 'what should I do first,' 'what order do I do things in,' 'where do I begin,' 'I have an idea but don't know what's next,' or seems lost among the available skills. Also use when the user asks for a roadmap or overview of the full process from idea to launched product. This is the starting point — it routes users to the right skill for their current stage.

Process, filter, and transform JSON data using jq - the lightweight and flexible command-line JSON processor.

Working effectively with JSON data structures.

JWT and OAuth token attack playbook. Use when validating token trust, signing algorithms, key handling, claim abuse, bearer flows, and OAuth account-binding weaknesses.

Use when securing Kubernetes clusters, implementing network policies, configuring RBAC, pod security standards, or asking about "Kubernetes security", "NetworkPolicy", "PodSecurityPolicy", "RBAC", "pod security standards", "OPA Gatekeeper"

Run Kiro CLI as an independent reviewer over the current branch, a specific commit, or uncommitted changes. Builds a focused prompt from the real diff and returns a compact review summary.

Project-specific prompt optimization knowledge management. Use when storing or retrieving learned patterns from comparisons. Provides schema, extraction criteria, capacity management, and retention scoring.

Audits a local Claude-managed knowledge base in Simon's '/Users/simon/Claude CoWork/Knowledge Base/' system. Surfaces contradictions between articles, broken backlinks, unsourced claims, stale articles, writing-rules violations, and three suggested new articles. Files a full report into the KB's 'Outputs/' folder, appends a one-line CHANGELOG entry, and (in interactive sessions) walks through which findings to action. Use this skill whenever the user says "run a health check", "audit the [name] KB", "audit my knowledge base", "check the wiki", "let's go through the health check report", or "action the latest health check". Also use when the monthly scheduled task 'knowledge-base-monthly-health-check' fires. Use this skill for any audit-style request against a folder under 'Knowledge Base/' even if the user doesn't say the word "health check" - the protocol is the same.

Test fixture skill that satisfies all 15 auditor checks (Pass 1 + Pass 2). **Use when:** - The auditor integration tests assert PASS verdict on a canonical input **Triggers:** "known-good fixture", "auditor PASS smoke", "skill-auditor regression" **Not ideal for:** - Real-world use (this is a test fixture)

Use when writing or reviewing Kotlin Flow state and event APIs with StateFlow, MutableStateFlow.update, SharedFlow, Channel, stateIn, SharingStarted, .value, receiveAsFlow, one-shot events, or sentinel initial values.

Diagnose and fix common Kubernetes issues with systematic debugging approaches. Use this skill when troubleshooting K8s clusters, pods not starting, deployments failing, or networking issues. Activate when: kubernetes, k8s, pod, deployment, kubectl, container, crashloopbackoff, imagepullbackoff, pending pods, kubernetes networking, service not working, ingress issues.

Reviews AWS Lambda functions for performance, memory configuration, and cost optimization. Activates when users write Lambda handlers or discuss Lambda performance.

INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the langsmith CLI tool.

Audit multilingual content consistency. Use when: checking language parity, regional compliance, or translation quality.

Process large datasets efficiently using chunk(), chunkById(), lazy(), and cursor() to reduce memory consumption and improve performance

Best practices for Laravel middleware including before/after patterns, terminable middleware, groups, parameters, and common middleware implementations.

Best practices for Laravel task scheduling including defining schedules, frequency constraints, overlap prevention, and monitoring hooks.

When the user needs a 3-5 word opening hook for a product launch video — the first second of on-screen text or voice that stops the scroll. Also use when the user mentions "hook for my video", "first second", "opening line", "tagline", "one-liner for launch", or "catchphrase". Produces 10+ hook candidates, not one answer.

Owns CI/CD pipelines, infrastructure provisioning, environment portability, observability, disaster recovery, and operational resilience for the project.

Extract a learned skill from the current conversation

Proactively learn about the user through onboarding and ongoing observation. Use at session start and when you notice potential preferences.

Use when a phase or milestone is complete and you need to extract reusable knowledge, before shipping, or when reflecting on completed work. Also use when the user says "what did we learn", "capture lessons", "retrospective", "wrap up", "ship this phase", or "done with this phase". If a phase is about to ship without lesson capture, this skill must activate.

Generate high-quality LinkedIn posts for GEO thought leadership. Use when asked to write LinkedIn content, create social media posts, or generate content about SEO/GEO topics.

List all architecture decisions and specs with their status. Use when the user asks "what decisions have we made", "list ADRs", "show specs", or wants an overview.

When the user wants to design, optimize, or audit list layouts for content display. Also use when the user mentions "list layout," "list design," "vertical list," "stacked list," "blog list," "article list," "documentation list," "search results layout," or "infinite scroll list." For blog index page, use blog-page-generator.

Troubleshoot and debug LiveAvatar integration issues. Use when the user's LiveAvatar integration isn't working, the avatar is silent, audio is garbled, sessions fail to start, events aren't received, or they're getting API errors.

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

Use an LLM as an evaluator for open-ended outputs — rubrics, pairwise comparison, calibration with human labels, bias mitigation. Covers when LLM-judge works, when it fails, and how to trust its scores. Use this skill when evaluating generative outputs at scale, building eval pipelines, or replacing expensive human review for non-critical judgments. Activate when: LLM as judge, LLM evaluator, automated evaluation, pairwise comparison, rubric evaluation, eval model.

Use when "LLM inference", "serving LLM", "vLLM", "llama.cpp", "GGUF", "text generation", "model serving", "inference optimization", "KV cache", "continuous batching", "speculative decoding", "local LLM", "CPU inference"

Design prompts, schemas, validation, and recovery logic for reliable machine-readable model outputs. Use when generating JSON, typed objects, extraction results, tool arguments, or any output another system must parse safely.

Book real-world services through Lokuli MCP. Use when user needs to find, check availability, or book local services like plumbers, electricians, cleaners, mechanics, barbers, personal trainers, etc. Triggers on requests like "book me a haircut", "find a plumber near me", "I need a smog check", "schedule a massage", or any local service request. 75+ service categories available.

When the user wants to optimize for local search, set up Google Business Profile, or build local citations. Also use when the user mentions "local SEO," "Google Business Profile," "Google Maps," "NAP," "citations," "local search," "local business," or "service area." For location pages, use programmatic-seo.

Best practices for working with .NET local tools, including manifest management, tool installation, and versioning. Use when setting up dotnet-tools.json for a project, installing or updating local tools, or managing tool versions across team members.

Look up a service, team, or catalog entity in Rootly. Returns owner, on-call, recent reliability, dependencies, and any active incidents. Use when something breaks and the first question is who owns this.

Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.

Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.

Search and ingest knowledge from Lore, a research repository with citations

Guide new users through macrodata setup. Creates identity, human profile, and workspace files. Use when get_context returns isFirstRun true, or user asks to set up their profile.

Generates WPF IValueConverter or IMultiValueConverter classes with MarkupExtension pattern. Use when creating a new value converter, scaffolding a MultiValueConverter, or adding a converter with direct XAML usage. Usage: /wpf-dev-pack:make-wpf-converter <ConverterName> [multi]

Generates WAFFLES Declarations for social media posts — preemptive lists of what a post does NOT say. Use when users mention WAFFLES, ask for clarifications on their post, want to prevent misinterpretation, or request disclaimers for controversial/nuanced takes.

Run an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the local wasm-agent runtime

Use Anthropic's Managed Agents API (/v1/agents, /v1/sessions) — server-side agent runtime that handles the tool loop, compaction, memory, and scaling for you. Covers when to pick Managed over SDK, request shape, and cost model. Use this skill when building production agents at scale, deciding between SDK vs Managed, or migrating from self-hosted agent loops. Activate when: Managed Agents API, /v1/agents, /v1/sessions, server-side agent, Anthropic agent runtime.

Linear.app issue management using Linearis CLI with JSON output and smart ID resolution. Use when creating, viewing, updating, or searching Linear issues, managing sprints/cycles, or listing teams/projects.

Guide users through targeted manual verification after code changes. Use when asked to "test this", "verify it works", "QA this", "walk me through testing", "smoke test", "sanity check", "regression test", "acceptance test", or after implementing a feature or bug fix that still needs human validation. Favor this skill for focused verification of the current change; use a broader exploratory-testing skill for open-ended bug hunting across an entire app.

Generate a visual architecture overview of the codebase with Mermaid diagrams. Produces ARCHITECTURE.md at repo root. Use when the user says "map", "architecture", "overview", or wants to understand the codebase structure.

# Market & Industry Research Protocol

CLI for converting files to Markdown using Microsoft's markitdown. Use when converting PDF, DOCX, PPTX, XLSX, HTML, images, audio, or other file formats to Markdown for text analysis or LLM processing. Triggered by requests involving file-to-markdown conversion, document text extraction, or preparing files for LLM input.

Professional sub-skill for Matplotlib focused on high-performance animations, complex multi-figure layouts (GridSpec), interactive widgets, and publication-ready typography (LaTeX/PGF).

Query public GitHub repos via DeepWiki MCP — AI-powered answers about architecture, internals, and design decisions without cloning. Use for: 'how does this repo work', 'explain the architecture of X', 'compare two frameworks'. No auth required.

Conversational interface for managing MCP (Model Context Protocol) server configurations in Claude Code

Configures MCP servers for projects. Use when setting up Linear, GitHub, Chrome DevTools, Render, or other MCP servers for a project. Handles token selection and configuration.

Build production-quality MCP (Model Context Protocol) servers that expose tools, resources, and prompts to AI clients like Claude Desktop, Claude Code, Cursor, and the Claude Agent SDK. Use this skill when the user wants to build an MCP server, expose internal tooling to an AI agent, wrap an API for agents, or publish a reusable MCP server to a registry. Activate when: MCP server, Model Context Protocol, expose tools to Claude, @modelcontextprotocol/sdk, mcp.json, stdio server, HTTP MCP server.

Design MCP tool schemas, names, and descriptions that AI agents actually pick correctly and use without hand-holding. Covers the anti-patterns that make agents loop, pick wrong tools, or hallucinate arguments. Use this skill when designing or reviewing MCP tools, debugging "the agent isn't using my tool", or pruning a bloated tool surface. Activate when: MCP tool design, tool description, agent picks wrong tool, too many tools, tool schema, tool naming.

Choose between MCP transports — stdio for local processes, Streamable HTTP for remote servers, SSE for legacy — and implement each correctly with reconnection, backpressure, and session handling. Use this skill when deciding transport for a new MCP server, migrating SSE to Streamable HTTP, or debugging transport-level issues (connection drops, buffering, session loss). Activate when: MCP transport, stdio vs HTTP, Streamable HTTP, MCP SSE, MCP reconnection, MCP session.

# Media Converter Skill

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

Teaches the mediator pattern for centralized component communication. Use when multiple components need to communicate and direct coupling between them creates complexity or tight dependencies.

Prepare structured briefings for meetings with legal relevance and track resulting action items. Use when preparing for contract negotiations, board meetings, compliance reviews, or any meeting where legal context, background research, or action tracking is needed.

Prepare for an upcoming meeting with context from past meetings, related docs, and attendee information

Execute AI tasks (codex/claude/gemini) with memory and resume support via memex-cli stdin protocol.

Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation.

Manages the ai-context/ memory layer: initialize from scratch, update with session work, or maintain/cleanup. Trigger: /memory-init, /memory-update, /memory-maintain, initialize memory, update memory, maintain memory.

Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.

Searches the Obsidian vault for prior knowledge, past decisions, and accumulated learnings — and finds unexpected connections between domains. Make sure to use this skill whenever the user asks "do I have notes on", "what did I write about", "find in my vault", "check my notes about", "have I learned about", "what did I decide about", "connect [A] and [B]", "find bridges between", or any phrasing that implies consulting personal vault knowledge rather than answering from general knowledge. Also fires when user references prior sessions or wants to know what they already know about a topic.

Use when implementing agent memory, persisting state across sessions, building knowledge graphs, tracking entities, or asking about "agent memory", "knowledge graph", "entity memory", "vector stores", "temporal knowledge", "cross-session persistence"

Guide for creating syntactically correct Mermaid diagrams that render properly on GitHub

Security pattern for implementing Message Authentication Codes (MACs) to ensure data integrity and origin authentication. Use when implementing HMAC, CMAC, or other MAC algorithms, verifying message integrity, authenticating message origin with shared secrets, or when non-repudiation is NOT required. Specialization of Cryptographic action pattern.

Weighted pandas DataFrames for survey microdata analysis - inequality, poverty, and distributional calculations. Triggers: "weighted mean", "Gini", "poverty rate", "inequality", "MicroDataFrame", "MicroSeries", "weighted statistics", "decile", "quintile", "income distribution", "microdf"

Migrate existing notes into the organized lab notebook structure

Plan and execute Convex schema migrations safely, including adding fields, creating tables, and data transformations. Use when schema changes affect existing data.

Patterns for safe database migrations in production environments

Build and maintain a personal profile from therapy sessions and journal entries. Creates a living document that accumulates self-knowledge about patterns, strengths, coping strategies, and growth over time. Unlike other skills, insights updates an existing profile rather than creating new files.

Generate summaries of therapy sessions and journal entries at various lengths and for different audiences. Supports action item extraction, highlights reels, and session prep. Use for quick recaps, sharing with others, or preparing for your next session.

Host modded Minecraft servers (CurseForge, Modrinth).

Deep methodology knowledge for ML-NMR including IPD/AgD integration, population adjustment, numerical integration, and prediction to target populations. Use when conducting or reviewing ML-NMR analyses.

Master dispatcher for all MLflow workflows. Use this skill when the user wants to do anything with MLflow — tracing, evaluating, debugging, or improving an agent. Routes to the right MLflow sub-skill automatically. Triggers on: "use mlflow", "help with mlflow", "mlflow agent", "add mlflow to my project", "trace my agent", "evaluate my agent", or any MLflow task without a specific skill in mind.

Multi-model code review — dispatch, poll, and collect results from multiple AI model CLIs

Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

Use Mori CLI to enable agent-to-agent communication and coordination across Mori-managed panes. Use this whenever you need to launch a helper agent, send a message to another agent (Claude, Pi, Codex), read another agent's output, or coordinate multi-agent workflows. Prefer this over ad-hoc tmux whenever the task involves mori pane operations or agent-to-agent messaging.

Generate a complete Amazon product listing image set — hero image, lifestyle shot, infographic with features, and comparison/detail closeups optimized for Amazon standards.

Generate a cinematic "freeze effect" video where time stops mid-scene, the subject walks through the frozen world, then time resumes with a snap.

Setup and utility scripts for muapi.ai — configure API keys, test connectivity, and poll for async generation results

Generate a full multi-channel product campaign — hero visuals, social media assets, short ad video, and platform-specific crops for an end-to-end launch campaign.

Material-UI styling approaches

Use when designing multi-agent systems, implementing supervisor patterns, coordinating multiple agents, or asking about "multi-agent", "supervisor pattern", "swarm", "agent handoffs", "orchestration", "parallel agents"

Adopt multiple expert personas sequentially for complex problem analysis from diverse perspectives. Single-agent only — do NOT spawn sub-agents.

Create optimized multi-stage Dockerfiles for any language or framework. TRIGGER WHEN: creating Dockerfiles, optimizing container images, multi-stage builds, Docker best practices. DO NOT TRIGGER WHEN: the task is outside the specific scope of this component.

Multiple testing procedures reference for clinical trials. Use when selecting or implementing multiplicity adjustments, gatekeeping procedures, or graphical approaches.

Generates AI images using the nano-banana CLI (Gemini 3.1 Flash default, Pro available). Handles multi-resolution (512-4K), aspect ratios, reference images for style transfer, green screen workflow for transparent assets, cost tracking, and exact dimension control. Use when asked to "generate an image", "create a sprite", "make an asset", "generate artwork", or any image generation task for UI mockups, game assets, videos, or marketing materials.

Generate AI images using Nano Banana for fast image creation. Use when you need to: (1) quickly generate images from prompts, (2) create prototypes and iterations, or (3) produce simple image content efficiently.

Pay-per-call access to the Nansen API via MPP (Tempo). Use when a user wants anonymous Nansen access without an API key and without managing their own Base/Solana wallet — they install the tempo CLI separately and call the API through `tempo request`.

Manage smart alerts — list, create, update, toggle, delete. Use when setting up or managing token flow alerts, smart money alerts, or notification rules.

Electric neon glow effects with high-contrast color pairings for bold, attention-grabbing interfaces.

Provides Nette Schema for data validation and normalization. Use when validating configuration, API inputs, or any data structures with Expect class. Covers Expect::structure(), Expect::from(), anyOf, arrayOf, listOf, assert, transform, castTo, otherItems, and Processor. This is about nette/schema – not Nette Forms validation (addRule), not Nette\Utils\Validators, and not JSON Schema.