LLM Mart Basic

Give Claude Code a video perception layer that extracts frames, transcribes audio, and lets Claude answer questions about local videos or YouTube URLs.

Angular is a TypeScript-based web application platform by Google providing dependency injection, declarative templates, a powerful CLI, and comprehensive libraries for routing, forms, and HTTP communication.

Diagnoses Ansible playbook failures using ansible-playbook --check --diff mode, ansible-lint, and the Ansible callback plugin API. Parses task execution results and suggests fixes for common module errors in ansible.builtin and community collections.

Runs Ansible diagnostic playbooks using ansible-runner and the Ansible Collections ecosystem (ansible.builtin, community.general). Captures system health, service status, and log analysis across inventory hosts.

Executes ansible-playbook --check --diff mode and parses the JSON callback output using the ansible.posix.json callback plugin. Identifies tasks that would change, predicts idempotency issues, and generates change impact reports.

Validates Ansible playbooks using ansible-lint and the Ansible Galaxy API. Performs check-mode dry runs, validates role dependencies, and detects deprecated module usage across collections.

Validates Ansible playbooks in check mode using ansible-playbook --check --diff and the Ansible Python API. Detects idempotency issues, undefined variables, and unreachable hosts before production runs.

Validates Ansible playbooks and roles using ansible-lint and yamllint APIs. Enforces best practices for idempotency, variable naming, and handler usage with custom rule profiles.

Validates Ansible playbooks using ansible-lint with custom rule plugins and the Ansible Collections API. Checks for deprecated modules, missing handlers, insecure variable practices, and role dependency conflicts.

Imported from agentskillexchange/skills/skills/ansible-playbook-runner.

Generates Ansible playbook YAML with proper module usage, handler chains, and role structures using ansible-core built-in modules. Supports Jinja2 template rendering and vault-encrypted variable files.

Generates and validates Ansible playbooks from infrastructure requirements. Uses ansible-lint for validation and queries Ansible Galaxy API for discovering certified roles and collections.

Executes Ansible playbooks against dynamic inventories from AWS EC2 or Azure, decrypting Ansible Vault secrets via HashiCorp Vault KV v2 API. Streams task output in real time and posts a per-host pass/fail summary to Slack. Supports --check mode for dry-run validation before live

Executes Ansible playbooks for server diagnostics and remediation using ansible-runner Python SDK. Supports inventory parsing, vault-encrypted credentials, and real-time task output streaming.

Instruments Anthropic API calls to log token usage, latency, and cost per request using the Anthropic TypeScript SDK. Wraps the anthropic.messages.create method to capture usage.input_tokens, usage.output_tokens, and timing from the API response. Writes structured logs to CloudWa

Anyquery is a SQL query engine that lets you run SQL against 40+ apps, files, and databases including GitHub, Notion, Chrome, and Apple Notes. Built on SQLite with MCP server support for connecting AI agents to structured data across services.

Imported from agentskillexchange/skills/skills/apache-airflow-mcp.

Manages Apache Avro schema evolution with compatibility checking via Confluent Schema Registry API. Validates forward, backward, and full compatibility across schema versions automatically.

Maps and transforms data between systems using Apache Camel route definitions and the Camel Component API. Supports XSLT, JSONPath, and DataFormat transformations via camel-core SDK.

Diagnoses Kafka consumer group lag using the Kafka AdminClient API and JMX metrics exposed via the Confluent Metrics API. Identifies slow consumers, topic partition hotspots, and broker rebalance storms that contribute to lag growth. Provides a step-by-step runbook to tune fetch.

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.

Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.

Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.

An MCP server exposes tools, resources, or prompts through a standard protocol so an AI application can discover and use external capabilities.

The weekly review

Implement an approved plan or issue in its own worktree, run the gate, open the pull request.

Close a finished session: sweep for unfinished work, land and hand off, file the follow-ups, tell the sessions that depend on this one, then archive.

Write the repository handoff file for the next session, and record any durable learning.

Merge an approved pull request, clean up its worktree and branch, then check whether a release is due.

Turn a topic or issue into a plan the reviewer approves in the native plan pane.

Answer a research question with parallel read-only gatherers and one synthesized digest.

Review the branch's diff in two fresh contexts — scope against the spec, then quality — and report findings only.

Transform a vague prompt into precise, structured AI instructions

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding