LLM Mart Basic

Build a whole course on a subject, from scratch, on disk. A light survey of the domain, then the placement-quiz decision, then a deep multi-agent research pass that becomes an ordered taxonomy, a table of contents grouped into books and chapters, and a course folder that teaches

Placement quiz that finds someone's real level in a subject and writes it to PROFILE.md. Scenario questions in small batches, never definitions, with neutral options that cannot be eliminated by tone, plus self-report checks that separate knowing a word from being able to act on

Make a fig. A single looping animated SVG, one self-contained HTML file you can drop in an email or a slide. Use it when an idea moves (flows, loops, retries, queues, fan-outs). Faster than a paragraph, livelier than a static diagram. No player, no deck.

Search and fetch free, licensed stock images from the internet (Pexels, Pixabay, Unsplash, Openverse, Wikimedia Commons). Two jobs: add optimized WebP images to sites, blogs, and docs, or show a fitting photo right in the chat while answering about a topic. Use when the user want

Run a conservative, end-to-end art-direction photo pass over a whole website: audit where photos genuinely earn their place, define one visual language, source free images, melt them into the design, verify in both themes, and record credits. Use when the user asks for a "photo p

Use the Open Design content library: 151 design systems with real tokens (Apple, Vercel, Linear, Stripe, Notion, GitHub, Raycast, plus styles like brutalism and claymorphism), 71 design and frontend skills, and 114 rendering templates for decks, documents, video frames, and socia

Apply first-principles thinking and design-thinking to product, architecture, and communication decisions. Use this skill whenever the user is framing a problem, choosing between alternatives, debating a tradeoff, questioning a design, adding scope, or saying "should we…" / "that

Delegates one self-contained coding or research task to the Cursor CLI (cursor-agent), running it on the Cursor subscription's quota instead of Claude's. Use when the user asks to "delegate to Cursor", "offload this to cursor-agent", "have cursor do it", or wants to spend idle Cu

Writes one ready-to-teach chapter file for a learnable course from its brief: every lesson's opening question with plausible options, the correction, the plain-language explanation, the terms with their origins, and the end-of-chapter quiz. Use one per chapter when writing a book

Designs one track of a learnable curriculum: its chapters, its lessons, each lesson's hard opening question, the misconception it kills, its key terms and its teaching angle. Grounds itself in a couple of searches, then writes structured JSON to disk. Use one per track when build

Power search via Exa MCP. Modes: quick, deep research, code, docs, debug, news, compare. Use when searching the web, finding docs, debugging errors, or researching any topic.

Author a product brief by interviewing the user, then emit user stories, scope, success metrics, and a derived task list. Triggers on "write a brief", "create a brief", "spec this feature", "brief". A brief is a product spec (what/why), NOT a technical design (use propose) and NO

Design workflow in the RFC tradition. Forces reasoning before action: problem → alternatives → tradeoffs → design → risks → recommendation → impl plan. Two sizes with hard ceilings: one page for a bounded choice, a few pages for a real design question. Use when user says "propose

Execute a predetermined spec. Ingests a finalized brief (docs/brief/<slug>/ with brief.md status ready + tasks.md) or an Accepted propose (PROPOSAL.md), locks a definition-of-done contract, implements it on the strongest available engine (agent-teams / subagents / solo, with ultr

Report unfinished brief/propose/ship work in this repo and the exact command to resume each, ranked by what to do now. Use when the user asks "what's next", "what's left", "where do I resume", "/next", "la suite", or to re-orient after a context reset. Reads artifact frontmatter

Use GitHub issues as persistent cross-session resolution memory. Create, update, and re-read issues that are self-contained and re-readable cold, recording the hypothesis and the resolution. Triggers on "track this in an issue", "create an issue I can resume", "resume issue", "is

Read or hand-write the project progress ledger (.claude/trace.md). Use when the user says "/trace", "what did I do", "log this", "trace done", or wants to record or review what moved this session. The automatic Stop hook already logs file changes; this skill is the reader and the

Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources. Use when the user needs thorough investigation, market research, technical deep-dives, due diligence, or comprehensive analysis on any subject.

Guides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.

Guides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.

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.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

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.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.