LLM Mart Basic

Use when setting up or modifying CI/CD pipelines, quality gates, test runners, or deployment pipeline configuration through workflow files. Not for triggering a deployment.

Use when "CI is red", "fix the checks", or "make CI green", one check needs classifying, or a bounded sweep runs. Not for deploys, credentials, or rerun-as-fix. Non-CI bugs: use strike-the-root.

Use when a C or C++ build uses clang and needs diagnostics, optimization remarks, clang-tidy, ThinLTO with lld, LLVM PGO, or a GCC-to-Clang migration. Not for LLVM IR work: use llvm.

Use when setting up a project, auditing agent command permissions, or asking which read-only bash commands and domains to allow. Not for remote, credential, publish, deploy, or irreversible changes.

Use when the user just edited a durable artifact, or says "clean and true", "run the hygiene pass", or "taste the output". Routes the artifact through the hygiene passes it earned.

Use when asked to run /clean-clean-cut to cut accumulated records and residue. Not for untracked or non-VCS changes, or branch/worktree cleanup: use git-cleanup.

Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or profiling a CLI: use control-cli.

Use when the user wants to batch-close resolved or outdated tracker items. The agent never closes tracker items itself. Not for individual closure or items still under active work.

Use when a human explicitly runs /cloud-task-orchestrator for a large task across cloud agents to drain a verified task graph. Not for local subagent coordination: use orchestration-patterns.

Use when writing CMakeLists.txt, out-of-source builds, target_link_libraries, target properties, find_package/FetchContent, toolchain files, CPack, CMake presets, or cmake configure errors.

Use when reading llc output, tracing IR through legalization and instruction selection, or scoping a new LLVM target. Not for IR-level passes: use llvm-ir-and-passes.

Use when the user asks to simplify, clean, or refine code. Not for new abstractions or whole-codebase refactors.

Use when building or reusing a CodeQL database, running CodeQL security analysis, or modeling project-specific sources and sinks. Not for manual vulnerability review: use security-review (mode: confirmed).

Use when asked to commit changes, create a typed branch, format history for a changelog, or rewrite messages of HEAD or an unpushed range. Not for pushing or a PR: use commit-push-pr.

Use when a human asks to commit and push, not publish, the checked-out branch, including directly to the default branch, with no branch creation and no pull request. Not for a feature branch off the default: use commit-push-pr in its no-PR mode.

Use when asked to commit and push a feature branch, with or without a pull request. Its no-PR mode publishes without a PR. Not for a PR body alone: use create-pull-request.

Use when asked to research a feature across competitor products or to analyze competitor release changelogs (mode: changelog), and publish a cited report.

Use when the user asks for direction and a compilable 3D workflow from an interview. Not for remote, credential, publish, deploy, or irreversible changes.

Use when building a lexer, Pratt or recursive-descent parser, AST, symbol table, type checker, or LLVM IR emitter for a language or DSL. Not for optimizing IR: use llvm-passes.

Use when -O3 leaves a hot loop scalar, spills appear in assembly, or a PGO or BOLT deployment is planned or stalls. Not for machine lowering: use code-generation-and-backends.

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.

Generate ranked improvement ideas by scanning the codebase, divergent ideation, adversarial critique, and impact ranking

Full autonomous engineering workflow (plan, build, review, ship)

Transform feature descriptions into well-structured project plans following conventions

Report a bug in the whetstone plugin

Reproduce a GitHub issue bug with visual evidence (browser screenshots, log analysis). Takes a GitHub issue number. For non-issue bug validation, use the bug-reproduction-validator agent.

Resolve PR review comments with cluster analysis and parallel agents. Use when bulk-fixing PR comments after triage.

Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees

Diagnose the whetstone environment and configure review agents. Checks CLI dependencies and plugin version, then runs the review-agent wizard that writes whetstone.local.md. Use when onboarding a project, troubleshooting missing tools, or configuring review agents.

Run browser tests on pages affected by current PR or branch

Run pre-PR verification chain: build, types, lint, tests, security scan, diff review

Execute work plans efficiently while maintaining quality and finishing features

Run a dry run first:

Run:

Run:

Create or update an OpenCode skill using the bundled skill-creator workflow

Rebuild the OpenCode skill registry for the current project and installed skills

Session-2 fix loop for Agentation — read structured annotations from the dev overlay and apply targeted UI fixes.

Consume the project's design contract — a .design file or DESIGN.md — and thread its tokens through UI code (CSS, Tailwind, or design-system components).

Fork pov.md for installer taste, or append a one-liner to gotchas.md after a real agent failure.

Audit animation timing, easing, springs, and transitions — decide first whether motion should exist, then apply the motion cluster.

Implementation of Podlite markup language

Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard, references, generat…

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.

本地优先的类飞书 Markdown 编辑器,内置可审改的 AI 助手 | Local-first WYSIWYG Markdown editor with a reviewable AI agent

A lightweight all-in-one terminal with 20+ protocols — SSH, RDP, SFTP, databases, Kubernetes and more. With a built-in autonomous AI Agent that plans and runs m…

一款专注于桌宠方向的AIAgent。特点是一键安装、功能齐全、极低开销、完全暴露上下文、全功能插件化、AI自主插件开发、永久唯一会话、类游戏引擎交互策略。具有极高的扩展性和拟人程度上限，非常适合想长期培养和自定义需求高的用户。

Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace MCP Server & CLI Tool

一个先接住情绪、再分析关系并给出可执行策略的 Codex 恋爱军师，内置心理、法律、社会、人文、哲学、婚姻家庭与性学知识库，支持多元关系。

AI-powered SRE platform — read-only infrastructure diagnostics with deep investigation, security governance, and team collaboration

An open-source AI desktop companion inspired by Cyrene, combining immersive Chat, personalized long-term memory, and an agentic Work mode.

A local-first AI agent with persistent memory, emotional intelligence, and a peer-to-peer skills economy.

The open-source, multi-agent alternative to Claude Tag. @ any agent, wherever work happens, your agents work alongside your team and each other, learning as the…

Simple LLM service identification - translate IP:Port to Ollama, vLLM, LiteLLM, or 60+ other AI services in seconds

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

Claude in Chrome, reverse-engineered and open-source. No domain blocklist. Any Chromium browser. Same 18 MCP tools, same performance.

Agent-native flight & hotel search and booking — MCP server, CLI, and Python/JS SDKs. Hundreds of airlines plus the major booking sites, with per-flight reliabi…

Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs l…

Privacy-first Codex skill for discovering, validating, completing, and tracking job applications