LLM Mart Basic

Phase-1 Layer-0 of the comic-author suite — turn ANY raw idea / a locked video skeleton / an audience note into ONE schema-valid intent_spec node that fixes the logline (an editorial climax), the tagline, and the named DUAL-IDENTITY design constraint the whole comic optimizes aga

Phase-1 (S9, the FINAL comic-author step) — assemble the LOCKED storyboard + locked per-panel blueprints into ONE schema-valid `comic.json` (the comic-ir/1.0 contract boundary handed to comic-director / run_comic.py). Project the page_order + each panel's condition{} + render fie

Phase-1 Layer-2 of a comic — turn a LOCKED skeleton (intent_spec + the pre-locked beat/shot list) into an approved outline_spec: a 6-column beat table that binds every ARIS capability to a STORY COST, plus the continuity-motif contract the storyboard layer will be held to. NOT fr

Phase-1 step of comic-author — the DETERMINISTIC compiler (搬运工原則) that turns ONE gate-approved panel_spec + its status:locked blueprint into the EXACT fixed-section bake string for the spiral engine via the shipped scripts/build_prompt.py (+ the canonical scripts/_validate.py vet

Phase-1 comic-author step — turn a LOCKED, user-approved outline into the page-first storyboard that IS the authoring source of truth: a fixed page order BEFORE any prose, the MOTIF STATE TABLE (the master per-panel continuity ledger), a fixed 9-field per-panel spec, and one dedu

Phase-1 (S2) of the comic-author suite — compile the project's ART_BIBLE.md into an EXECUTABLE convergence target, not aesthetic prose. The bible is the ONE visual dialect read verbatim into every bake prompt AND into every visual reviewer's rubric (`style_consistency`/`identity_

Generate a publication-grade method / architecture / pipeline / workflow figure (a paper or README 'Figure 1') as an AUDITABLE object, not a one-shot prompt. A deterministic JSON blueprint LOCKS the content; an image model (gpt-image-2, baked by the agent via mcp__codex__codex —

End-to-end Pipeline A in ONE slash-command — turn a fuzzy story idea into a cross-model-audited, image-based movie + a clickable viewer. Chains comic-author (Phase 1 — intent→style→outline draft→provisional storyboard→assets→final locks→blueprints→prompts→comic.json) → the zero-c

Analyze architecture for consistency between ADRs and AD, completeness, and quality issues. Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or periodically to detect drift.

Generate a full Architecture Description (AD.md) from accepted ADRs using multi-agent DAG orchestration. Use when accepted ADRs exist and you need to produce or update unified architecture documentation.

Review, accept, reject, or defer Change Decision Records (ChDRs) discovered by change-init. Interactive one-ChDR-at-a-time workflow that validates inferred decisions against their git/issue evidence before promotion to project memory.

Mine git history for Change Decision Records (ChDRs) by detecting commit messages that link to issue trackers, clustering the commits into change stories, and inferring the decisions behind them. Use when bootstrapping project memory from an existing repo's history (brownfield),

Promote accepted Change Decision Records (ChDRs) from drafts to project memory at .adlc/memory/chdr/, write OKF-style frontmatter, and regenerate the boot-facing .adlc/memory/chdr.md index that team-boot injects at session start. Use after /change-clarify has accepted ChDRs.

Analyze evaluation results and close the loop. Specification failures create local CDRs to fix agent rules; generalization failures go to evaluator backlog.

Refine, cluster, and accept draft criteria into the published goldset. Isolates 20% holdout split and publishes goldset.md + goldset.json.

Generate executable graders and configs from goldset. Generates Python graders / metrics and auto-runs unit tests to verify grader correctness.

Initialize evals/{system}/ directory structure for evaluation system following EDD principles (Standalone). Choose PromptFoo or DeepEval based on tech stack, generate security baseline.

Extract eval criteria from product specs and production failure traces (bottom-up error analysis). Writes proposed criteria to .adlc/drafts/evals/.

Run evaluations and validate evaluator quality (SLA compliance, TPR/TNR, statistical accuracy). Executes PromptFoo or pytest DeepEval.

Read-only analysis of PDR↔PRD consistency, PDR quality, cross-PDR conflicts, and staleness. Outputs a structured markdown report with severity-assigned findings. Use after /product-implement or periodically to detect drift.

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 shard` forks a [checkpoint](checkpoint.md) into `--count` leases

`crabbox share` grants other people access to an existing lease through the

`crabbox ssh` resolves a lease and prints a ready-to-run `ssh` command for it.

`crabbox status` prints the current state of a lease: its slug, provider,

`crabbox stop` ends a single lease. For coordinator-backed and direct cloud

`crabbox sync-plan` prints the local sync manifest and its size hotspots

`crabbox tunnel` opens one foreground SSH local port-forward to a resolved

`crabbox unshare` removes sharing rules from a coordinator-backed lease. It is

`crabbox usage` reports lease cost and usage estimates from the broker, broken down by user, organization, or the whole fleet.

`crabbox verify` checks a signed run receipt produced by `crabbox run --attest`.

`crabbox vnc` prints (or opens) the connection details for a desktop-capable

`crabbox warmup` leases a box and waits until it is ready: it provisions (or

`crabbox watch` runs a command on a warm lease, then watches the local

Linux portal viewers default to **Match window**: only the connected controller

`crabbox whoami` calls the broker's `/v1/whoami` endpoint and prints the

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

{{SKILL_ENTRY:decision-lifecycle}}

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

Conduit — native SwiftUI iOS client for Hermes Agent

一个现代化的可视化规则引擎平台，用于编排复杂的 AI 工作流。在无限画布上设计、测试和部署 AI 流程——无需编写代码。结合 flowgram.ai 的能力与 Java 服务端，提供生产级工作流管理。在此之上提供AI Agent / Copilot的助手编排能力。

Job application tracker and AI-powered job search assistant. Helps job seekers manage their search journey with AI resume review, job matching, task logging, an…

📝 Markdown and HTML renderer for Svelte 5 — built for streaming AI agent output from Claude Code, ChatGPT, and agentic workflows. XSS-safe defaults, token cach…

ServiceNow MCP server: 500+ tools and 26 AI capabilities for any AI (Claude, ChatGPT, Gemini, Cursor, Copilot). Multi-transport (stdio, SSE, HTTP), A2A, dynamic…

Free crypto news API - real-time aggregator for Bitcoin, Ethereum, DeFi, Solana & altcoins. No API key required. RSS/Atom feeds, JSON REST API, historical archi…

Build production-ready AI agents in both Python and Typescript.

From agent user to agent builder: build a Claude Code-style coding agent from scratch in Python: 8 articles, 4 videos, one codebase

🪁 A lightweight, modern Kubernetes dashboard that unifies multi-cluster and resource management, enterprise-grade user governance (OAuth, RBAC, and audit logs)…

Stateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns.

AgentCall lets AI Agents join meetings with voice, video & screen-share to build together. Supports Google Meet, Teams, Zoom (Beta)

Kition brings Markdown, DataTable, WhiteBoard, a tool-using AI agent, browser research, and visual workflows into one desktop workspace.

IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.

A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.

Turn your Claude Pro/Max subscription into an OpenAI-compatible API for your IDEs and devices — LAN auth, per-key quotas, response cache, disciplined cli.js ali…

Paw Work - selection-first web agent for Chrome: select on the live page, describe the outcome, take away an editable office file. BYOK, sandboxed, no server.

基于 AI Agent + MCP 工具链 + 渗透 Skill 编排， 配合大语言模型， 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。

Lexora — Personal AI workspace built around Desktop / 以 Desktop 为核心的个人 AI 工作台

First AI Journey for DevOps - with comprehensive learning paths, practical tips, and enterprise guidelines

AI coding agent with one Python core and three front-ends — headless CLI, Textual TUI, and an Electron desktop. Works with any OpenAI-compatible API, with risk-…