LLM Mart Basic

Use when the user is explicitly working with Quarto, .qmd files, _quarto.yml, Quarto projects, or Quarto features such as callouts, cross-references, citations, Mermaid diagrams, extensions, websites, books, presentations, and reports. Also use for explicit migration from or comp

Deploy or publish Python and R content to a Posit Connect server using rsconnect-python or the R rsconnect package. Handles interactive apps and dashboards, web APIs, rendered documents, and prepared bundles/manifests. Use whenever the user asks to deploy, publish, or redeploy co

Guide for drafting issue closure and decline responses as an open-source package maintainer. Use when helping compose a reply that says "no" to a feature request, closes an issue as won't-fix, redirects a user to a different package, explains why a design choice is intentional, o

Use when the user wants to find, evaluate, audit, or install an open-source AI agent skill or MCP server — e.g. "find an MCP server for Postgres", "is this skill safe to install", "what should I use to scrape a website". Searches a quality-scored, security-graded catalog of ~20K

Generator-evaluator separation and review methodology — loaded by review agents to enforce fresh-context review discipline and gate verdicts; findings from the code, security, and docs reviewers are formatted per the conventional-comments skill. Trigger on "review this diff", "re

Adversarially review a technical design document with fresh context. Dispatches the built-in read-only `Explore` subagent (clean context, no shared history with the design-author) against `docs/plans/<id>/design.md` and presents its verdict — APPROVE, REQUEST CHANGES, or COMMENT.

Tear down local and remote branch state after a pull request is finished, in one of two modes. Mode A (merged): verify the PR actually merged, remove the branch's worktree, resync the default branch, and delete the local branch. Mode B (closed / abandoned): close the PR(s), then

Bring a feature branch up to date with its base without changing what the branch does: capture a pre-rebase check baseline, fetch, rebase onto the latest base, resolve each conflict from both sides' intent with the rationale recorded to disk, re-run the same checks, and treat any

Watch your own pull request for review feedback: undraft it when the cue clearly says it is ready (an ambiguous cue watches the draft), take a baseline snapshot, then poll GitHub in ~31-minute cycles for up to 24 hours and triage new feedback as it arrives — inline review threads

Watch a pull request you are reviewing until your feedback is settled, re-review each settlement, then approve once: poll GitHub in ~31-minute cycles for up to 24 hours until every review thread you opened is resolved and every plain PR comment you posted has a later push behind

Land a reviewed pull request: discover the open PR for the current branch, push any unpushed commits, wait for CI to go green, then squash-merge it so the PR title (which may carry a version) lands as the commit subject. Handles a PR that has fallen behind its base (rebase + forc

Decide the approach before any code is written. The design-author drafts the ~200-line design document, resolving its own open questions autonomously as recorded assumptions, then an adversarial design review gates advancement. Trigger on "design this", "let's align on the approa

Compressed bug-fix pipeline — reproduce, write failing test, minimal fix, verify, and open a draft PR. Skips Question/Research/Design/Structure/Plan phases. Invoke ONLY on explicit pipeline intent — the user says "run the bug-fix pipeline", "team-fix this bug", or runs "/team-fix

Execute the implementation phase. Includes test-first sub-step (writing failing tests, mechanical confirmation gate) and adversarial verification (5 parallel reviewers with hard-gate retry loop). Trigger on "implement this", "execute the plan", or "/team-implement".

Produce the tactical implementation plan from the structure. The plan is an autonomous artifact for the implementer — no approval gate at this phase (the design was already gated by the adversarial design review). Trigger on "plan the implementation", "spell out the steps", or "/

Open the pull request after verification passes. Updates the changelog, optionally surfaces the tracking ticket, and closes out the topic. Trigger on "open the PR", "open a draft PR", or "/team-pr". To land/merge a reviewed PR (wait for CI, then squash-merge) use the separate /sh

Decompose a feature description, ticket, or issue link into the QRSPI Question artifacts (task.md, questions.md). Trigger on "shape this idea", "decompose this task", or "/team-question".

Research a codebase area before making changes. Dispatches parallel read-only agents (file-finder + researcher) that read questions.md only — never task.md. Trigger on "research this", "explore the codebase for", or "/team-research".

Break the reviewed design into vertical slices with verification checkpoints. Runs autonomously and advances to PLAN — no approval gate. Trigger on "slice this up", "break the design into steps", or "/team-structure".

Prepare one or more isolated git worktrees — one per repository the topic touches. Router action — no agent. Trigger on "set up the worktree", "isolate this work", or "/team-worktree".

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 attach` follows the recorded events of an active coordinator run and

`crabbox azure` groups Azure provider setup commands. It currently has a single

`crabbox bench` records and reports local benchmark timing observations. It is a

`crabbox cache` inspects, purges, or warms package and build caches on a

`crabbox capsule` captures, replays, and tracks lightweight failure capsules.

Save the state of a lease, then restore it onto another box or fork it into a

`crabbox claims list` prints the lease claims stored on the current machine. It

`crabbox cleanup` sweeps direct-provider machines and local provider state that

`crabbox code` bridges a Linux lease's `code-server` workspace into the

`crabbox config` inspects and updates user configuration. It has three

`crabbox connect` resolves a lease and opens an interactive SSH session to it.

`crabbox cp` copies files or directories between the host and a Crabbox-owned

`crabbox desktop` drives a visible desktop session on a lease that was warmed

`crabbox doctor` runs a preflight before you commit to a long workflow. It is

`crabbox egress` gives a lease mediated outbound network: a lease-local browser

`crabbox events` prints the broker's event log for a recorded run.

`crabbox heartbeat` refreshes the idle deadline for one owned lease and prints

`crabbox history` lists recorded remote command runs from the broker. Each run is

`crabbox image` holds the trusted-operator controls for provider base images:

`crabbox init` onboards the current repository: it writes the minimal config

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…