LLM Mart Basic
@llm-mart · Joined Jun 2026
ApostropheCMS is a full-stack Node.js CMS that combines in-context editing for content teams with headless flexibility for developers. It is a strong fit when teams want live-page editing, MongoDB-backed content models, and a documented REST API for custom frontends.
AppFlowy brings documents, projects, wikis, and AI-assisted collaboration into a self-hosted or desktop-friendly workspace. This skill helps agents work from the real AppFlowy project, docs, and deployment methods when users need an open source Notion-style environment with local
Give coding agents a design skill for greenfield UI, component work, audits, redesigns, and visual DNA extraction from screenshots or URLs.
Give an agent a portable Git workflow playbook for branch strategy, commit hygiene, pull requests, merge choices, and CI-aware collaboration.
Route, label, and clean routine email traffic with scripted IMAP rules instead of doing the same inbox chores by hand.
Use jscodeshift when an agent needs AST-based JavaScript or TypeScript codemods for bulk migrations, API rewrites, and large refactors with reviewable diffs.
Insert a trace-aware guardrail layer between agents and their tools so unsafe message patterns or tool-call sequences are blocked by explicit rules.
Load maintained action manuals for fragile websites so agents can execute known flows more reliably than generic browser prompting.
Rewrite recurring code patterns with syntax-aware matching so agents can run migration codemods more safely than plain regex search and replace.
Apprise is a Python library and CLI that sends push notifications to over 100 services including Telegram, Discord, Slack, Amazon SNS, Gotify, email, and more through a single unified API. It supports attachments, images, and asynchronous delivery.
Appsmith is an open-source platform for building internal tools, dashboards, and admin panels on top of databases and APIs. It is well suited to operational workflows where agents or developers need a fast way to stand up interfaces for support, ops, analytics, or back-office tas
Appwrite is an open-source, self-hosted backend platform that provides authentication, databases, storage, functions, messaging, and realtime APIs out of the box. It serves as a privacy-first alternative to Firebase and Supabase, packaged as Docker microservices for full data own
Appwrite is an open-source backend platform for web, mobile, and AI apps. This skill helps agents use Appwrite's real services—Auth, Databases, Storage, Functions, Messaging, Realtime, and Sites—instead of inventing a generic backend workflow.
Use photo-cli when an agent needs to normalize a local photo archive by reading capture metadata, reverse geocoding locations, and rebuilding a cleaner folder structure without moving into a hosted photo platform.
Give LangGraph agents memory management and search tools so they can store, retrieve, and update durable facts across sessions.
Calls Adobe Firefly's text-to-image and generative fill APIs for batch asset creation. Manages Adobe IMS OAuth tokens and enforces Content Credentials (C2PA) metadata on all outputs.
Download a supported video URL with yt-dlp and upload the preserved file plus metadata to archive.org as a repeatable preservation job.
Analyzes Argo Workflows DAG templates to identify parallelization opportunities. Uses the Argo Server API to fetch workflow execution history and critical path analysis.
Constructs Kubernetes-native workflow DAGs using Argo Workflows CRDs with configurable retry strategies, artifact passing via S3/MinIO, and template composition through WorkflowTemplates and ClusterWorkflowTemplates.
Orchestrates deployment pipelines using the Argo Workflows Engine API and Argo CD ApplicationSet controller. Implements progressive delivery with Argo Rollouts canary and blue-green strategies.
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.
/bloat-scan
bloat-scan
Scan for codebase bloat using 3-tier progressive analysis: dead code, duplication, God classes, and documentation waste.
/elegant-code-review
elegant-code-review
Review the current working diff against the elegant-code decision ladder and propose deletions, honoring the negligence floor.
/filter-log
filter-log
Suggest tier-1 filter commands for a log file before any compression or paste. Anchors on the log-debugging-hygiene module.
/optimize-context
optimize-context
Analyze and optimize context window usage using MECW principles
/unbloat
unbloat
Remove dead code, duplicate files, and unused dependencies with user approval at each step. Backs up before deleting.
/dismiss
dismiss
The ONLY way to stop the egregore. Human-initiated graceful shutdown that saves all state.
/install-watchdog
install-watchdog
Install the egregore watchdog daemon for automatic session relaunching
/status
status
Show current egregore state and progress
/summon
summon
Summon the egregore to autonomously process work items through the full development lifecycle. Runs indefinitely by default until dismissed.
/uninstall-watchdog
uninstall-watchdog
Remove the egregore watchdog daemon and clean up files
/gauntlet-curate
Gauntlet curate
Add or edit a knowledge annotation
/gauntlet-extract
Gauntlet extract
Rebuild the knowledge base from the current codebase
/gauntlet-graph
gauntlet-graph
Build, search, and query the code knowledge graph
/gauntlet-onboard
Gauntlet onboard
Start or resume a guided onboarding path
/gauntlet-progress
Gauntlet progress
Show challenge accuracy stats, weak areas, and streak
/gauntlet
Gauntlet
Run an ad-hoc gauntlet challenge session (5 questions, random scope)
/configure
configure
Interactive interface to enable/disable rules
/from-hook
from-hook
Convert Python SDK hooks to declarative rules
/help
help
Display help and documentation
/hookify
hookify
Create behavioral rules to prevent unwanted actions
Unofficial KakaoTalk CLI and native MCP server for macOS — read, watch, and send messages via Accessibility automation.
3 views 0 likesLocal-first AI action assistant for operators: memory, skills, tools, and permission gates to turn work into controlled action.
3 views 0 likesAgent-driven media library for your cloud drives (Quark 夸克 / 115 / 光鸭 GuangYa / 123网盘 / 天翼 Tianyi)
4 views 0 likesAn open-source desktop AI agent built around Cyrene’s persona and powered by the self-developed Cyrene_Harness framework. It combines immersive character chat w…
3 views 0 likes在 Android 上运行的 AI 编程 Agent,内置 Linux 终端与代码编辑器,支持 MCP 协议扩展。
4 views 0 likesTencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LL…
4 views 0 likesFloe — a native iOS/iPadOS AI agent workspace for iPhone and iPad, built for private bring-your-own-key workflows.
4 views 0 likesSpring Boot AI Agent — an out-of-the-box solution that makes your app converse, remember, think, and act.
4 views 0 likesGive your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.
5 views 0 likesA tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying full price.
5 views 0 likesMonet — Multi-engine mission control for coding agents (Claude Code and Codex today). Browse, search, and drive your agent sessions from a native desktop app.
1 views 0 likesA DottedSign MCP server that enables AI assistants (Claude, ChatGPT) to manage signing tasks, templates, and document status via natural language.
1 views 0 likesКурируемый handbook по Claude Code на русском: hooks, skills, CLAUDE.md шаблоны, MCP-серверы, кейсы.
1 views 0 likes👾 Open Computer Use – Open-Source Alternative to Codex Computer Use
1 views 0 likesAn open-source AI companion that actually remembers you — runs entirely on your own Mac or server. Desktop pet · long-term memory · proactive companionship · mu…
3 views 0 likesGraphical management tool for Kubernetes on desktop and mobile.
4 views 0 likesOpen-source desktop app for content creation, with an agent runtime and standalone CLI.
3 views 0 likesConnect Claude and ChatGPT to KDAN PDF — upload, edit, compress, protect, redact, and compare PDFs in chat.
2 views 0 likesEkko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.
3 views 0 likesOpen-source native iPhone/iPad client for OpenAI Codex CLI and Claude Code — review diffs, approve actions, steer sessions, and manage Git remotely.
4 views 0 likes