LLM Mart Basic

Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosing between preference-optimization methods, or when a DPO run needs hyperparameters or debugging.

Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes promotion, when choosing a quantization format for a target device, or when an exported model fails its smoke test.

Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO pairs from passing and failing runs.

Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring frozen-vision-tower LoRA, or debugging a VLM fine-tune that trains without learning.

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.

Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced X For You algorithm. Use when building any system that picks "the top K items for a (user, context)" — c

Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.

Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.

Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.

Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.

Create structured incident response runbooks with step-by-step procedures, escalation paths, and recovery actions. Use this skill when building a service outage runbook for a payment processing system; creating database incident procedures covering connection pool exhaustion, rep

Master on-call shift handoffs with context transfer, escalation procedures, and documentation. Use this skill when transitioning on-call responsibilities between engineers and ensuring the incoming responder has full situational awareness, when writing a shift summary that captur

Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks. Use when debugging microservices, analyzing request flows, or implementing observability for distributed systems.

Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.

Set up Prometheus for comprehensive metric collection, storage, and monitoring of infrastructure and applications. Use when implementing metrics collection, setting up monitoring infrastructure, or configuring alerting systems.

Define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting. Use when establishing reliability targets, implementing SRE practices, or measuring service performance.

Implement GitOps workflows with ArgoCD and Flux for automated, declarative Kubernetes deployments with continuous reconciliation. Use when implementing GitOps practices, automating Kubernetes deployments, or setting up declarative infrastructure management.

Design, organize, and manage Helm charts for templating and packaging Kubernetes applications with reusable configurations. Use when creating Helm charts, packaging Kubernetes applications, or implementing templated deployments.

Create production-ready Kubernetes manifests for Deployments, Services, ConfigMaps, and Secrets following best practices and security standards. Use when generating Kubernetes YAML manifests, creating K8s resources, or implementing production-grade Kubernetes configurations.

Implement Kubernetes security policies including NetworkPolicy, PodSecurityPolicy, and RBAC for production-grade security. Use when securing Kubernetes clusters, implementing network isolation, or enforcing pod security standards.

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.

`crabbox shard` forks a [checkpoint](checkpoint.md) into `--count` leases

`crabbox share` grants other people access to an existing lease through the

`crabbox ssh` resolves a lease and prints a ready-to-run `ssh` command for it.

`crabbox status` prints the current state of a lease: its slug, provider,

`crabbox stop` ends a single lease. For coordinator-backed and direct cloud

`crabbox sync-plan` prints the local sync manifest and its size hotspots

`crabbox tunnel` opens one foreground SSH local port-forward to a resolved

`crabbox unshare` removes sharing rules from a coordinator-backed lease. It is

`crabbox usage` reports lease cost and usage estimates from the broker, broken down by user, organization, or the whole fleet.

`crabbox verify` checks a signed run receipt produced by `crabbox run --attest`.

`crabbox vnc` prints (or opens) the connection details for a desktop-capable

`crabbox warmup` leases a box and waits until it is ready: it provisions (or

`crabbox watch` runs a command on a warm lease, then watches the local

Linux portal viewers default to **Match window**: only the connected controller

`crabbox whoami` calls the broker's `/v1/whoami` endpoint and prints the

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.

{{SKILL_ENTRY:decision-lifecycle}}

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

A governance harness for AI coding.

DeepSeek Harness 手机版：可直接安装的 Android APK，AI 免 Root 操作手机（Shizuku/root 可选），文件编辑只需所有文件访问权限，前台保活 + AI 通知

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Orbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

The SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web

Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.

The extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…

Bridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…

针对 AI 自动化渗透 Agent 的新一代反制蜜罐，通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent，实现多款主流通用Agent的反制上线控制。

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…

Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…