LLM Mart Basic

Use when asked to predict Culture Index traits from an interview transcript before a survey exists, including sparse or contradictory evidence. Not for interpreting completed survey results.

Use when a manager needs profile-specific communication, one-on-one, motivation, and energy guidance for a direct report. Not for general pair or team compatibility analysis.

Use when a signed new hire's Culture Index profile and team profiles need a first-90-days plan. Not for manager coaching: use culture-manager-coaching.

Use when implementing pool/slab/arena allocators, tuning jemalloc/mimalloc/tcmalloc, writing a Rust GlobalAlloc, or benchmarking allocator performance and fragmentation.

Use when customer feedback, NPS, churn, email feedback, call transcripts, or voice-of-the-customer analysis needs a report over a time window.

Use when the user asks to cut, trigger, or start a release candidate for a release branch. Not for full releases, hotfixes, or non-release-candidate workflow dispatches.

Use when the caller supplies a falsifiable out-of-happy-path invariant and a finite budget. Restores via bounded patches or reverts. Not for normal feature delivery or universal retries.

Use when a build, QA pass, demo, user complaint, or abandoned attempt leaves the next pass needing lessons rather than code. Not for changelog extraction. Not for session handoff: use handoff.

Use when a human-curated dbt model index must guide BigQuery SQL for a warehouse question. Not for discovering undocumented models or executing warehouse changes.

Use when a user asks to tighten verbose-but-correct prose without a full rewrite. Cuts in place to load-bearing density, preserving every load-bearing claim.

Use when debugging RelWithDebInfo or -O2 release builds, using -Og for debuggable optimization, split-DWARF, GDB scheduler-locking, reading inlined frames, or understanding "value optimized out".

Use when the user has a fork and wants it resolved and applied, not explored: "decide this", "choose the path", or "decide and fix it".

Use when a user wants to record why one world won over the others, as a decision-diary entry. Not for remote, credential, publish, deploy, or irreversible changes.

Use when a current decision needs pressure-testing until the rationale is clear to a skeptic. Not for tasks requiring source or remote-system changes.

Use when an imperative program needs pre-conditions, post-conditions, and loop invariants proved automatically by SMT in Dafny or Why3, short of a tactic prover.

Use when asked to deduplicate a skill tree, fold overlapping skills, or cut the skill count: analyze, gate per family, then fold. Not for prompt-doctrine cascades: use cascade-dedup.

Use when the user asks to research a topic and produce a thorough sourced report. Not for remote, credential, publish, deploy, or irreversible changes.

Use when the user wants the finished-system contract for a piece of work: behavior, protocols, allowed, forbidden, and impossible states with a state-space proof. Not for runtime verification.

Turns a song (audio file + lyrics) into a hand-painted watercolour music video (MP4) in the style of PDoomVideo, following its pipeline end to end: measure the beat grid and time the lyrics, scaffold the p5.brush engine, design the story, characters and sets from the lyrics, pain

Paints one chapter (src/ch/cNN_name.js) of a paint-mv music video in the PDoomVideo style: watercolour-and-ink frames drawn with p5.brush, the song's own characters (designed from its lyrics) acting on the beat, camera moves and motivated transitions, each frame a pure function o

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 inspect` prints the full record for a single lease: state, provider,

Run named, repo-local jobs defined in your Crabbox config.

`crabbox list` shows the current Crabbox machines (leases) for a provider. It is

`crabbox login` authenticates the CLI against a coordinator, stores the

`crabbox logout` clears the stored broker token from your user config so the CLI

`crabbox logs` prints the retained command output for a recorded run.

`crabbox marketplace` previews the Crabbox credits gateway: one Crabbox billing

`crabbox media` turns a recorded desktop video into lightweight review

`crabbox open` prepares an existing SSH-capable lease for an external editor.

`crabbox pause` pauses a single lease, freeing the remote compute while

`crabbox pond` is the cross-provider peer-discovery and lifecycle surface for a

`crabbox pool` contains machine-pool helpers. `pool list` keeps the older

`crabbox ports` bridges provider-native port publishing for an existing Crabbox

`crabbox prewarm` leases a reusable box and prepares it for test runs. For

`crabbox providers` prints the provider capability matrix that the CLI compiles

`crabbox receipt <run-id>` retrieves a brokered run's committed terminal

`crabbox results` prints the structured test summary attached to a recorded

`crabbox resume` resumes a lease previously paused with [`pause`](pause.md),

`crabbox run` syncs the current dirty checkout to a box, runs a command there,

`crabbox screenshot` captures a single PNG from a desktop lease without opening a

Your car as a chat-room agent: Raspberry Pi 5 + dashcam + local AI. CodeWatch's sibling for the garage.

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts.…

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for ma…

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

同花顺官方 A股金融数据服务，提供股票实时行情、历史行情、财务报表、指数、板块、涨停等数据，适用于 AI Agent、量化研究和应用开发，支持 API、MCP、CLI 和 Python。Official Tonghuashun (HiThink) A-share financial data service provi…

Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 15+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server…

🤖 Local-assist BOSS Zhipin CLI for AI agents — search, welfare filtering, shortlist, JSON-envelope output; low-risk & compliant by default.

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives your live graph: edits,…

Persistent memory for Claude Code — identity, context, and continuity across sessions

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI…

A curated list of plugins, skills, MCP servers, patch/profile layers, orchestrators & UIs for DeepSeek Harness (DSH). Visualization · PPT · Coding · Agents · Lo…

World Memory Protocol.

Run your own organization of agents.

The most RAM efficient harness

AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday. Built for Scrum teams where humans and AI agents collaborate as equals — on the same…

Free open-source desktop app that scrapes JAV metadata and generates NFO + cover art for Jellyfin, Emby & Kodi. No Docker, no CLI — one-click install on Windows…

A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ global skills directories — “Install once, sync ever…

天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy…