lukacf

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

workgraph-workflow

How to use WorkGraph for durable commitments, dependencies, claims, and evidence

multi-agent-comms

Setting up keep-alive, peer trust, send vs request/response patterns

API & Backend Listed

hook-authoring

Writing hooks for the 8 hook points, execution modes, and decision semantics

memory-retrieval

How semantic memory works with compaction and the MemoryStore trait

mob-communication

How to communicate with peers in a collaborative mob

schedule-workflow

How to author and inspect durable schedules from agent tools

builtin-utilities-workflow

How to use Meerkat built-in utility tools safely and productively

shell-patterns

Background job patterns with shell and job management tools

skill-discovery-workflow

How to browse, load, and use Meerkat skills during a session

task-workflow

How to use builtin task tools for private lightweight work tracking

meerkat-architecture

Internal architecture guide for the Meerkat agent platform. This skill should be used when understanding crate ownership, trait contracts, the agent construction pipeline, session service lifecycle, runtime control plane, mob orchestration internals, machine authority, comms wiring, or making cross-cutting architectural changes. Oriented toward AI agents and developers working on meerkat internals, not end users.

meerkat-cli-reference

Exact rkat CLI command contract for Meerkat help answers. Use this as the authority for command names, flags, aliases, and negative CLI facts.

Web & Frontend Listed

meerkat-dogma-inquisition

Ruthless Meerkat dogma inquisition for architecture, code, PRs, plans, tickets, ledgers, and designs. Use when Codex must find semantic-authority violations, shadow truth, provider leakage, surface-owned meaning, projection/mirror abuse, typed-truth failures, terminality lies, generation theater, or meta-level repeated dogma failure patterns; use for brutally honest reviews that cite concrete evidence and group symptoms by root dogma failure.

API & Backend Listed

meerkat-platform

Build on the Meerkat agent platform. Covers every shipping surface (CLI, REST, JSON-RPC stdio/TCP, MCP, Python/TypeScript/Web/Rust SDKs), realm-scoped sessions, streaming, skills, hooks, memory, multimodal content, mob orchestration (spawn/fork/helpers/flows/profiles), durable scheduling, and provider auth via `auth_binding` + AuthMachine (env keys, OAuth, cloud IAM). Use when integrating with Meerkat, picking a surface, wiring auth, building agents, scheduling automated runs, deploying mobpacks, or asking how a feature exposes through a particular SDK.

meerkat-wasm

Developer guide for the Meerkat WASM embedded runtime (meerkat-web-runtime) and the `@rkat/web` browser SDK. Covers wasm32 compilation, building/deploying WASM bundles, writing/auditing wasm_bindgen exports (sessions, mobs, comms, JS tool callbacks, external auth resolver, subscription handles), the auth_binding + registerExternalAuthResolver auth model, tokio_with_wasm aliasing, cfg-gating patterns, mobpack bootstrap, and common wasm32 gotchas. Use when touching meerkat-web-runtime, sdks/web, browser auth flows, or making a meerkat crate wasm32-compatible.

rct-methodology

RCT (Representation Contract Tests) methodology for AI-assisted development. This skill should be used when creating implementation checklists from specifications, planning phased implementations, or when the user mentions "RCT", "representation contracts", "Gate 0", or asks for an "agent-ready checklist". It transforms specifications into executable, phased checklists with reviewer gates that an AI agent can autonomously execute.

DevOps & Infrastructure Listed

rust-cicd-pipeline

Set up a professional Rust CI/CD pipeline with pre-commit hooks, automated linting, testing, changelog management, and version control. This skill should be used when creating a new Rust project that needs CI/CD, when adding CI/CD to an existing project, or when troubleshooting pipeline issues. The pipeline follows the "Makefile as single source of truth" pattern and works without GitHub Actions for enterprise environments.