LLM Mart Basic

Use this skill when you need evidence-bounded repeat inputs, version/model/prompt factors, invariants, variance evidence, and comparison boundaries; triggers include LLM 一致性 and LLM consistency.

Use this skill when you need to design LLM evaluation datasets, judges, metrics, and human-review boundaries; triggers include llm evaluation design.

Use this skill when you need evidence-bounded claim-to-source relations, unsupported assertions, abstention, uncertainty, and evidence review; triggers include LLM 幻觉 and LLM hallucination.

Use this skill when you need to test LLM behavior, failure modes, and evidence-based quality boundaries; triggers include llm testing.

Use this skill when you need to analyze logs into evidence, timelines, anomalies, and follow-up hypotheses; triggers include log analysis.

Use this skill when you need to plan manual or exploratory testing with charters, heuristics, and session records; triggers include manual testing and exploratory testing.

Use this skill when you need to derive test candidates from input transformations and expected relations when a direct oracle is limited; triggers include 变形测试 and metamorphic test design.

Use this skill when you need to identify, contextualize, and investigate metric anomalies from observability evidence; triggers include metrics anomaly analysis.

Use this skill when you need to design mobile test plans for iOS or Android covering functionality, compatibility, performance, network, and security; triggers include mobile testing and app testing.

Use this skill when you need to review mock fidelity, contract alignment, over-mocking, and drift evidence; triggers include Mock 质量评审 and mock quality review.

Use this skill when you need to derive test-path candidates from sourced behavior, state, or process models; triggers include 基于模型的测试 and model-based test design.

Use this skill when you need evidence-bounded delegation, coordination, shared state, conflicts, ownership, termination, and traceability; triggers include 多 Agent 协作 and multi-agent coordination.

Use this skill when you need to interpret mutation operators, killed and survived mutants, and evidence limits; triggers include 变异测试分析 and mutation testing analysis.

Use this skill when you need to discover invalid, denied, failed, degraded, or unsafe-recovery scenarios from product evidence; triggers include negative scenario discovery.

Use this skill when logging, metrics, tracing, alerting, or SLO design needs an evidence-bounded review before implementation; triggers include observability design review, telemetry readiness review, and alert actionability audit.

Use this skill when you need to identify interactions that need at least pairwise coverage after factors, values, and constraints are explicit; triggers include 成对测试 and pairwise test design.

Use this skill when you need to form evidence-based performance bottleneck hypotheses and validation steps; triggers include performance bottleneck analysis.

Use this skill when you need to compare performance evidence across versions and assess regression risk; triggers include performance regression analysis.

Use this skill when you need to interpret performance results, evidence quality, and risk without inventing conclusions; triggers include performance result analysis.

Use this skill when you need Gatling performance scope, simulations, or runnable entry points; triggers include Gatling, Gatling simulations, and Gatling performance testing.

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

`/ca:debug` investigates an unexplained symptom and returns a cited diagnosis or a bounded

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 an authorized repair of a confirmed code defect. Give the observed

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,

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with NVIDIA Nemotron, pays…

DSH 插件 · 注入式优化器 0.8（主线）：你照常说话，它在你发送后,AI接收前把"这一轮到底要什么"理清楚，再把这份理解交给工作 AI(上下文注入) —— 原话不改写，条条带逐字依据。含控制界面（档位/权限/模型/上下文/只读工具）、拦截浮层（思维层+产出层）与真实 token 用量。可明显提升大多数模型的发挥稳…

Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹

MCP server and CLI tools for web search and crawling, built on SearXNG and Crawl4AI

Delta MCP is a free app that sits between your AI apps and their MCP servers: one program per task instead of one tool call per step, up to 24.1× fewer tokens i…

Ava turns any Android 5+ device into a voice-first Home Assistant kiosk. Native C++ under the hood, so a 10-year-old tablet still listens, talks, and runs the h…

Roblox Studio macOS Window Capture Fix 2026: Real Screenshot Tool Instead of Magenta Playtest Glitch

LabTether