LLM Mart Basic

Review a PR against the Pascal architectural rules — package boundaries (core/viewer/editor/nodes), the registry-driven composition model (def.geometry / def.renderer / def.system), legacy-dispatch regressions, the slots + world-scale-UV convention for new nodes/geometry, hook hy

Operate, troubleshoot, secure, upgrade, and automate Kubernetes clusters and workloads safely across upstream Kubernetes, k3s, RKE2, MicroK8s, k0s, Talos, OpenShift/OKD, kind, Minikube, Rancher-managed clusters, EKS, AKS, and GKE. Use when a task involves kubectl, Kubernetes APIs

Build LLM applications with LangChain. Use when working with LangChain or comparing LLM application frameworks. Do not use this skill for unrelated requests; route to the nearest named specialist.

Discover product requirements from human stakeholders — map who to talk to, ask questions that surface hidden assumptions, detect gaps in real time, resolve conflicts, and translate conversations into structured SDD specs. Phase 0 upstream of Spec-Driven Development. Do not use t

Route a product through its full lifecycle — discovery, strategy, portfolio choice, roadmap, UX and requirements, experimentation, delivery handoff, adoption, success, and lifecycle review — by composing existing specialist product skills with phase-entry evidence, handoff artifa

Compare intended product outcomes against observed results to close the launch-to-learning loop: collect post-launch evidence, distinguish expected from observed from uncertain from inferred claims, update assumptions, assess feature health, and choose among continue/improve/harv

Define and run product governance — recurring decision rights, intake, portfolio cadences, evidence standards, and cross-functional operating contracts. Covers six review cadences (intake, portfolio, roadmap, experiment, launch, lifecycle) with named accountable owners, minimum e

Build and maintain outcome-based product roadmaps and portfolio views that sequence strategic bets by evidence, not dates. Covers Now/Next/Later views, strategic-bet management, capacity allocation, dependency and confidence mapping, scenario planning, continue/pause/kill/revisit

Use this skill to shape product or engineering work before committing time to it: set appetites instead of estimates, narrow raw ideas into bounded problems, sketch solutions at the right level of abstraction, de-risk rabbit holes, write pitches, bet with capped downside (circuit

Set product vision, positioning, market strategy, and portfolio direction with a CPO methodology. Route tactical prioritization, specifications, and backlog decisions to `product-methodology`; do not use this skill for delivery-level product decisions or unrelated requests.

Build cross-domain production evidence from readiness, migration, recovery, capacity/cost, and incident learning into launch or operational decisions. Do not use this skill for a single specialist's risk packet and launch gate; use `production-readiness` for that readiness review

Apply distilled coding principles from 14 classic software books to code review, refactoring, design, and implementation decisions. Do not use for language- or framework-specific tutorials, tool manuals, or tasks already governed by a project's established conventions.

Teach promise vocabulary, fundamentals, and coordination diagnosis for promise-based systems. Do not use this skill for Semantic Spacetime models or SST CLI tooling; use `semantic-spacetime` for those model and tool workflows.

Query, search, and download public datasets and civic information for the City of Raleigh. Use for live ArcGIS Hub catalog discovery, ArcGIS FeatureServer and MapServer queries, ImageServer imagery exports, official Raleigh geocoding, GoRaleigh transit feeds, guest-public develop

Operate React applications as a named tool: inspect and diagnose React/Vite projects, design component boundaries and state flow, implement accessible responsive UI, and verify behavior with the project's tests. Use when a task explicitly involves React, JSX/TSX, React hooks, Rea

Design, automate, and operate end-to-end software releases: release process models and pipelines (trunk-based development, CD stages, release trains), progressive delivery and feature flags, versioning and artifact management (SemVer, conventional commits, changelogs, SBOM/proven

Administer and troubleshoot remote Linux, FreeBSD, NetBSD, OpenBSD, and macOS systems safely, one host or a fleet at a time. Use when a task requires SSH, Ansible, Paramiko, POSIX diagnostics, service management, software updates, system configuration, firewall changes, or eviden

Chain web research, atomic extraction, and durable note capture when the same research-to-notes sequence must repeat. Do not use this skill to design or evaluate an investigation; use `research-methodology` for research questions, methods, and evidence assessment.

Plan, conduct, evaluate, and synthesize rigorous research investigations with credible evidence and a traceable method, including source-to-claim closure for media evidence. Do not use this skill for repeated source extraction and durable note orchestration; use `research-and-vau

Design, exercise, and evidence graceful degradation, disaster recovery, and restoration behavior across systems and dependencies. Covers failure-mode analysis, RTO/RPO decision records, restore testing, game days, failover drills, data integrity verification, and recovery communi

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

This is the lane for changes with no behavior to test-drive — prose edits, a version bump on an

Use this after a pull request has merged but your local checkout is still on the topic branch.

Prints the public command catalog straight from `COMMANDS.md` — the plugin's own single source

This is the single entry point for turning staged work into a commit — nothing in codeArbiter

The protocol for a rule conflict — not a skill route, an orchestrator-level halt. When two sources

An optional, on-demand drift audit for the bypass case: a merge, a direct push, or a manual edit

This is the populator for a project that already has code to read. Instead of interviewing you about

This is where an unexplained defect goes before anyone touches code. The investigation is

This is the populator for a project that has no code yet to read. Rather than guessing at

Proves the install is actually enforcing, rather than just present. codeArbiter's worst failure

This is the standard entry point for new work with a human in the loop at every step. A short

This is the entry point for a defect that already has a known cause, or one you can describe

This is how a repository opts into codeArbiter for the first time. It writes the root-level state

A bare-numbers governance glance — three metrics, each with a trend arrow against the prior

The sanctioned, logged escape hatch. A routine gate — a lint rule, a style check, a non-security

Explicit PR entry and a direct request to open a PR use the same branch-finishing owner.

A zero-onboarding, read-only dry-run of the reviewer fleet against whatever is currently

This is a Feature Forge preview command — the after-each-turn service ships **off** by default and

Compares architectural records with the scaffold and prior decisions using SMARTS.

This is the lane for moving or reshaping code without changing what it does — a rename, an extract,

AI coding platform for teams

AI Multi-Agent Framework in .NET

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight & extensible, works with any harnesses, any models,…

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to…

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harnesss. Suppprtd automation, scripting, coding, build anything and more. Power…

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex