LLM Mart Basic

Technical debt detection and remediation. Run at session end to find duplicated code, dead imports, security issues, and complexity hotspots. Triggers: 'find tech debt', 'scan for issues', 'check code quality', 'wrap up session', 'ready to commit', 'before merge', 'code review pr

Terraform and OpenTofu infrastructure-as-code operations - project layout, state management, module design, plan/apply safety, CI/CD pipelines, and secrets. Use for: terraform, opentofu, infrastructure as code, IaC, tfstate, terraform state, terraform module, remote backend, terr

Generate tests with skill-preloaded routing, framework detection, and auto-TaskCreate. Triggers on: generate tests, write tests, testgen, create test file, add test coverage.

Cross-language testing strategies and patterns. Triggers on: test pyramid, unit test, integration test, e2e test, TDD, BDD, test coverage, mocking strategy, test doubles, test isolation.

Application/game-scale three.js: ES modules, GLTF pipeline (DRACO/KTX2/meshopt), AnimationMixer, physics (rapier/cannon-es), react-three-fiber, and performance at scale (InstancedMesh, LOD, draw calls). Triggers on: three.js, GLTFLoader, r3f, game loop, WebGL memory leak, boids.

Recommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool). Triggers on: which agent, which skill, what tool should I use, help me choose, recommend agent, find the right tool.

TypeScript type system, generics, utility types, strict mode, and ecosystem patterns. Use for: typescript, ts, type, generic, utility type, Partial, Pick, Omit, Record, Exclude, Extract, ReturnType, Parameters, keyof, typeof, infer, mapped type, conditional type, template literal

Django Unfold admin theme - build, configure, and enhance modern Django admin interfaces with Unfold. Use when working with: (1) Django admin UI customisation or theming, (2) Unfold ModelAdmin, inlines, actions, filters, widgets, or decorators, (3) Admin dashboard components and

Vue 3 development patterns, Composition API, Pinia state management, Vue Router, and Nuxt 4. Use for: vue, vuejs, composition api, pinia, vue router, nuxt, nuxt4, nuxt3, script setup, composable, reactive, defineProps, defineEmits, defineModel, v-model, provide inject, vue3.

yt-dlp media acquisition layer feeding ffmpeg-ops: format selection avoiding post-download transcodes, clip-at-download, cookies/auth, channel archive sync, SponsorBlock, subtitles, failure triage (403s, nsig). Triggers on: yt-dlp, download video/playlist/channel, youtube to mp3.

Expert in Firecrawl API for web scraping, crawling, and structured data extraction. Handles dynamic content, anti-bot systems, and AI-powered data extraction.

Background git operations agent - commits, PRs, branch management, release workflows. Runs on Sonnet to free main session.

Analyzes and reorganizes project directory structures following industry best practices. Cleans up old files, logs, and redundant code. Handles Python, JavaScript, and general software projects with git integration.

Break a design brief into executable time-boxed tasks, each with a done-when line. Use immediately before a build session.

Turn an interrogated brief into the single source of truth for a design project. Use after /grill-me, before any IA or UI work.

Critique a design on layout, accessibility, responsiveness, dark mode and edge cases, with Pass, Needs work or Fail verdicts. Use on a built screen.

Establish color, typography, spacing, radius and motion as named role-based tokens. Use before building any interface.

Build an interface from the brief and the tokens rather than from a guess. Use only after grill-me, design-brief, information-architecture and design-tokens have run.

One move you can run on anything: point grill-me at a target and it makes you defend your thinking from first principles until the true matter is clear. Point it at your working contract and it rewrites the weak lines in place. Point it at a brief and it produces a Requirements H

Audit a design against Nielsen's ten usability heuristics, tying every finding to a specific element with a specific fix. Use on a built screen or a detailed mockup.

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.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

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