LLM Mart Basic

Adapt a draft to a user's writing samples or explicit tone brief. Use for consistent personal or project voice across docs and posts; distinguish style evidence from factual content.

Prepare release notes and migration guidance from a verified revision range and project release policy. Use for release preparation; never present open PRs or planned changes as shipped features.

Reduce a reported software bug to a runnable, minimal reproduction with the exact command, environment, and observed failure. Use when verifying a bug report; do not infer success from a failing setup command.

Review a pull request for concrete correctness regressions using its diff, surrounding code, and relevant tests. Use for a requested PR review; distinguish actionable defects from optional preferences.

Review an upstream documentation change against the skills, agent instructions, or runbooks that cite it. Identify supported updates, unaffected instructions, and unresolved version or evidence gaps. Use with a supplied source diff or Skill Watch result.

Turn a repository issue into an evidence-backed triage note: observed behavior, missing reproduction details, possible duplicates, and the next useful action. Use for issue triage, not implementation or bulk issue closure.

Verify a proposed bug fix against an unchanged regression test and the relevant existing tests, reporting baseline and candidate outcomes separately. Use for fix verification, not a general claim that software is bug-free.

Draft factual project announcements, GitHub launch posts, and development updates for a specified audience or platform. Use to explain shipped work clearly, with evidence and a useful invitation for feedback.

Draft clear, respectful replies to issues, PR discussions, and technical support reports from available evidence. Use to explain status, request a minimal reproduction, or communicate a project decision without inventing commitments.

Create or improve a repository README from actual project evidence, with a clear purpose, usable quickstart, and honest limitations. Use for project landing documentation and onboarding, rather than long tutorials or release notes.

Write a focused regression test from an established bug reproduction and public behavior. Use when a fix needs a test that fails on the affected version; avoid mirroring the implementation or weakening assertions.

Build a step-by-step technical tutorial around a reproducible outcome, with prerequisites, checkpoints, and recovery steps. Use for hands-on guides when a README quickstart is too short.

Write or revise interface labels, errors, empty states, and confirmation text from actual product behavior. Use for UI microcopy with clear next actions, preserved localization tokens, and explicit length constraints.

Investigate training failures, NaNs, missing gradients, misleading losses, and non-reproducible runs in PyTorch, Lightning, or TensorFlow/Keras. Use for a concrete training bug or regression, not an open-ended architecture or hyperparameter search.

Edit stiff or AI-sounding prose into natural writing while preserving meaning, facts, citations, and the author's point of view. Use when asked to humanize, de-AI, or make an existing draft sound more human, in its original language.

Translate and localize Polish and English technical documentation, UI text, and project updates. Use for natural PL/EN phrasing while preserving commands, placeholders, factual precision, and a project glossary.

Adapt a draft to a user's writing samples or explicit tone brief. Use for consistent personal or project voice across docs and posts; distinguish style evidence from factual content.

Prepare release notes and migration guidance from a verified revision range and project release policy. Use for release preparation; never present open PRs or planned changes as shipped features.

Reduce a reported software bug to a runnable, minimal reproduction with the exact command, environment, and observed failure. Use when verifying a bug report; do not infer success from a failing setup command.

Review a pull request for concrete correctness regressions using its diff, surrounding code, and relevant tests. Use for a requested PR review; distinguish actionable defects from optional preferences.

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.

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.

Inspect architectural variances with SMARTS; record only explicit user choices. Report-only requests make no changes.

Restructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.

Prepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.

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 /ca: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.

Threat-model a sensitive design with STRIDE on request. Read-only analysis of threats, controls, and implementation constraints.

Run an opt-in deep codebase audit with persisted findings. Confirm cost before dispatch; filing and telemetry need separate approval.

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

Reviews a new or changed third-party dependency before adoption. The read-only

A read-only health scan of every recorded ADR under `.codearbiter/decisions/`. For each one it

Records an architectural decision as a numbered, dated ADR under `.codearbiter/decisions/`.

Assembles everything codeArbiter logs — `overrides.log`, `triage.log`, `decisions/`,

The one exception to codeArbiter's slash-command pipeline: a lightweight question-and-answer

A periodic whole-repository review. The caller supplies the reviewer unit list to

Claude Code skills for Chinese-narration recaps from supported video files, with optional editable JianYing/CapCut draft export. | 用 Claude Code skills 为支持的视频文件…

Drive the Unity Editor from an AI agent or the terminal. The Editor serves MCP itself over HTTP, so there is no second process to run, and the isuzu-unity-cli c…

面向企业的数字员工构建与运行平台：把专业员工的经验、流程与判断标准，固化为可随时上岗、可配置、可审批、可观测的 AI 数字员工。

A local-first, Pi-powered AI agent workspace for Desktop, WebUI, and CLI

660+ muapi-hosted generative-media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) — one YAML file per entry, browsabl…

A compounding agent OS for recursive agents. Also an open source alternative to Grok Bot and Meta's Muse.

Independent desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes on Linux and macOS.

Production agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-chain explorer.

See and manage what your coding assistants load — skills, commands, subagents, plugins and MCP servers, with real usage.

An Enterprise-Grade Full-Stack RBAC Permission Management System Built with Go + React

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

基于 DeepSeek Harness（DSH）的稳定桌面端，集成Git、内置浏览器与记忆功能 | DeepSeek Harness desktop GUI with local workspaces, Git, browser and memory.

⚡ Control Apache Airflow with natural language via MCP. Chat with your workflows using Claude, GPT, or any LLM — no REST API calls needed. Supports Airflow 2.x…

Open-source CLI, schemas, resolver, and DSH agent tools for DSH Plugin Hub

Pi Coding Agent 中文学习蓝皮书：从安装与第一个可验收任务开始，逐步掌握 Session、Context、Skill、Extension、Subagent 与长期 Agent 工作流。

Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic coding pipeline, model-agnostic and local-friendl…

Self-hosted, vendor-neutral control plane for your local coding agents (Claude Code & Codex). Run your agents, on any plane.

A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and…

Vibe Coding 从入门到精通教程｜AI 结对编程工作流｜Prompt、Skill、Workflow、上下文管理、codex实战指南

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangC…