LLM Mart Basic

用户直接运行 cm-test、要求分析当前分支相对主分支的业务影响，或说“测试已有功能”“根据代码生成用例”“用浏览器走查”时使用。无参数分析已提交差异、单测覆盖率与回归重点；明确说“补齐单测”时连续补测并重跑、审查。显式目标保留原模式，不擅自修产品代码。

UI 还原工程师 Skill，把已确认的设计基准像素级还原为生产代码（token 先行、原子顺序、按交付形态量化验收：Web 用 BackstopJS、App 用 Maestro+模拟器截图）；有基准才出场，不做业务逻辑

项目代码库上下文管理。通读项目生成参考文档(scan)，或加载文档辅助开发(dev)。

Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (s

将产品讨论、问题研究、学术研究、根因假设、测试设计或对抗审查交给外部高能力模型，并由本地主执行者核验、裁决和留存证据；不修改代码或代替正式测试。

Extract a production-ready brand-lock.md from a brand's existing assets. Point it at a website URL, a brand book PDF, screenshots, or a written description and it produces the nine-section brand-lock the rest of shotkit consumes, with a confidence and source noted for every value

Turn a creative brief into a production-grade storyboard with shot specs, timing, on-screen text, and per-shot rationale. Use when the user describes a video brief, plans a video, references shots or beats, scripts a social video, or hands over a creative concept to break into sc

Render a structured storyboard (storyboard.md, shots.json, text-overlays.json, brand-lock.snapshot.md) into a single-file HTML preview that is shareable, printable, and offline. Use when the user wants to share a storyboard, export for review, hand off to an editor, or print a ha

Critique a generated image against its source storyboard shot and prompt, producing revision notes. Use when the user has generated an image and wants feedback before committing. Triggers on "does this match the brief", "review this render", "is this on-brand", "what should I cha

Generate model-specific prompts from shots.json. Outputs copy-paste-ready prompts for stills (Midjourney, Flux, Ideogram, GPT Image, Nano Banana, Seedream) and motion video (Kling, Veo, Seedance, Hailuo). Also runs a revision mode that reads a critique.json and re-emits prompts f

Use aai-cli to inspect and manage Confluence spaces, pages, comments, attachments, and page moves.

Use aai-cli to create local spreadsheet files, manage their sheet tabs, and read, update, or clear cell values — Excel (.xlsx/.xlsm) and delimited text (.csv/.tsv).

Use aai-cli to inspect and manage GitHub repositories, issues, pull requests, reviews, branches, source files, and Actions logs.

Use aai-cli to find Google Drive files and folders, read their metadata, download their content (including Google-native Docs, Sheets, and Slides), check who a file is shared with, and upload a local file back to Drive.

Use aai-cli to inspect HubSpot CRM records, files, events, conversations, visitor identification, and custom channels.

Use aai-cli to search and manage Jira issues, Jira Product Discovery ideas, projects, boards, sprints, comments, and attachments.

Work with Microsoft 365 through aai-cli by choosing the right Microsoft service and resource model, then using durable Graph credentials for Outlook, OneDrive, SharePoint, Teams, Excel, To Do, and Planner workflows.

Use aai-cli to read OpenPanel projects, raw event exports, aggregated insights (metrics, pages, referrers, devices, geo), and user profiles.

Use aai-cli to manage Pipedrive leads, persons, organizations, deals, labels, activities, notes, deal flow/stage history, and synced mailbox data.

Use aai-cli to query PostHog product analytics, read projects, execute HogQL event queries, list saved insights, inspect persons and cohorts, read team dashboards, and view release annotations.

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.

Plural alias for task status, pause, prompts, recovery, and ignore

Verify that the autorun plugin command surface is loaded

Tmux session management - create, list, cleanup isolated sessions, short for /ar:tmux

Tmux session management - create, list, cleanup isolated sessions

CLI testing in isolated tmux sessions, short for /ar:ttest

CLI testing in isolated tmux sessions

Graceful stop - finish current task then stop (short for /ar:stop)

Set AutoFile policy to ALLOW — permit creation of new files without justification

Refresh git commit guidelines before staging changes

Set AutoFile policy to FIND — restrict edits to existing files only

Start an autorun task with three-stage verification (initial → critical review → final verification)

Refresh the universal system design philosophy before designing or reviewing code

Show the current AutoFile policy and any active autorun state

Extract text from PDF files or directories to markdown

Trigger: `/ship` or "ship it" or "deploy to production"

Suppress 5-question enforcement for rapid sessions

Check a Dutch address for KPN outages and report what connectivity is available there

Find the KPN business-mobile contract for a lost or stolen phone and block its SIM after confirmation

Run the SkillOpt-Sleep cycle with the handoff backend — no API subprocess; this session answers the engine's model calls via prompt/answer files, in isolated fresh-context subagents

Run or manage the SkillOpt-Sleep self-evolution cycle (review past sessions, replay tasks through a selected backend, consolidate validated memory + skills, or schedule nightly runs)

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding