LLM Mart Basic

This agent should be used to "run verification task", "check quality gate", "verify acceptance criteria", "run [VERIFY] task", "execute quality checkpoint". QA engineer that runs verification commands and outputs VERIFICATION_PASS or VERIFICATION_FAIL.

This agent should be used to "update spec files", "refactor requirements", "revise design", "modify tasks after execution", "incrementally update specifications". Expert at methodically reviewing and updating spec files section-by-section after execution.

This agent should be used to "execute a task", "implement task from tasks.md", "run spec task", "complete verification task". Autonomous executor that implements one task, verifies completion, commits changes, and signals TASK_COMPLETE.

This agent should be used to "review artifact", "validate spec output", "check quality", "review research output", "review requirements", "review design", "review tasks", "review execution", "review prototype evidence". Read-only reviewer that validates artifacts against type-spe

This agent should be used to "create tasks", "break down design into tasks", "generate tasks.md", "plan implementation steps", "define quality checkpoints". Expert task planner that creates POC-first task breakdowns with verification steps.

This agent should be used to "decompose a large feature", "triage a big task", "break down into multiple specs", "create epic decomposition", or needs guidance on splitting large features into dependency-aware spec graphs.

Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serv

Extract semantic structure and transferable style grammar from academic figures, PDFs, and paper or figure URLs for analysis, redraws, or reference-conditioned generation. Do not use it for paper-text-only figure planning.

Unified academic figure designer, semantic color & surface decision engine, and FigureSpec v1 compiler. Handles style selection, reference palette derivation, colorblind-safe token binding, SVMC visual metaphors, and normalized compact prose prompt compilation across classic-tech

Plan evidence-backed figures for a paper draft, markdown notes, outline, manuscript, PDF, or paper webpage. Supports Draft-to-Figure fast-track for Markdown notes as well as comprehensive multi-figure planning for full manuscripts.

Plan, generate, inspect, and refine academic figures from repositories, papers, draft notes, paper URLs, PDFs, or reference images. Supports fast-track draft-to-figure generation and user passthrough mode.

Analyze ML, AI4Science, Systems, and research repositories into an evidence-backed semantic architecture graph for paper figure planning. Code serves as supporting evidence; paper narrative and user intent remain the primary source of truth.

Coordinate agents via the AMQ CLI for file-based inter-agent messaging. Use this skill whenever you need to send messages to another agent (codex, claude, or any named handle), check your inbox, drain queued messages, set up co-op mode between agents, join a swarm team, route mes

Parallel-research-then-converge design workflow between two agents. Use this skill when the user wants two agents to independently think through a design problem before aligning on a solution — "spec X with codex", "design X together", "both agents think through X", "brainstorm a

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit

Research a codebase and create architectural documentation describing how features or systems work. Use when the user asks to: (1) Document how a feature works, (2) Create an architecture overview, (3) Explain code structure for onboarding or knowledge transfer, (4) Research and

Create and manage todo tracking documents for features, bugs, and multi-step tasks. Use when starting new work that benefits from a persistent record of decisions, progress, and context.

Review test code for quality, design, and completeness after implementing a feature or fixing a bug. Use when the user asks to "review my tests", "check my test quality", "are these tests good enough", "review testing", or after completing a feature implementation that includes t

Set a tracking document as the source of truth for the current feature or task. Use when starting work on a feature, bug fix, or multi-step task that benefits from a persistent record of decisions, discoveries, and progress. Keeps the document updated as work proceeds.

Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.

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.

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

{{SKILL_ENTRY:post-merge-cleanup}}

Show the codeArbiter command catalog — the public command list and what each routes to.

{{SKILL_ENTRY:commit-gate}}

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

{{SKILL_ENTRY:context-check}}

{{SKILL_ENTRY:context-creation}}

{{SKILL_ENTRY:debug}}

{{SKILL_ENTRY:decompose}}

Verify the active host install, package, command ownership, enforcement{{IF:pi}}, wrapper self-test, and active-dispatch coverage gap{{ELSE}}, and harmless live-fire probe{{END}}. Read-only.

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

{{SKILL_ENTRY:finishing-a-development-branch}}

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.

{{SKILL_ENTRY:decision-variance}}

AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemini and Windsurf.

Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist

出行路书工作流 skill：联网实查 + 多源交叉验证，产出可核验、能执行的旅行攻略。覆盖吃住行游拍避全维度，附美食情报卡、基准骨架与校验工具，支持一键部署在线版。

Self-hosted AI code reviewer with indexed PR reviews, walkthroughs, vulnerability scanning, dependency graphs, custom rules, and a learning loop.

🧬 Extend EvoScientist with Installable Skill & Knowledge Packs

Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops t…

Automatic memory consolidation for OpenClaw agents — like sleep for your AI. Powered by MyClaw.ai

🗂 The essential checklist for modern web development, for humans and AI agents

Distribb CLI, Claude, Codex, Hermes, OpenClaw skill for AI-powered SEO. Write content with your own AI, publish through Distribb's backlink network.

Open-source AI browser agent — type plain-language commands and Bah operates the web for you. Works with cloud AI (DeepSeek, Mistral, NVIDIA) or local Ollama mo…

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…

Use your ChatGPT / Codex subscription with DeepSeek Harness via OAuth, with model access, usage quotas, search, and image generation — no API key or Codex CLI r…

Local-first A-share research workbench for DeepSeek Harness: market dashboards, watchlists, valuation, four investor agents, versioned reports, and continuous p…

Open-source video pipeline (clipper, AI video & more) — scout trends, clip long videos, generate captioned shorts, design motion graphics. Local-first, BYOK. AG…

Desktop app for the pi coding agent: streaming timeline, Git review with hunk staging, session tree, native UI for pi extensions. Windows · macOS · Linux. pi 编程…

Zero-dependency browser video editor that AI agents can drive — JSON timeline, MCP + REST, live-reloading UI

Personal Context Manager for Claude Code. Your life in walnuts.

Fast way to switch between Claude Code configuration profiles

AutoClip｜一个链接，一键出片。开源 AI 视频剪辑桌面工具，将播客、访谈、课程等长视频自动剪成短视频，生成字幕、封面和发布文案，适配抖音、小红书、TikTok、Reels 与 YouTube Shorts。Open-source AI video clipping & content repurposing.