LLM Mart Basic

Use when a PR has review feedback and the user wants it addressed — pull the review comments, triage each one, apply the changes it warrants, then commit, push, and post a humanized reply per comment. Closes the loop between a review and the follow-up commit; it does not re-revie

Use when the user wants to record an architectural decision — drafting an Architecture Decision Record (ADR) or RFC, documenting a design choice and its trade-offs, or capturing why an approach was taken. Detects the repo's existing ADR location and template style (MADR or Nygard

Use when the user reports an error, bug, or unexpected behavior in this repo and wants help diagnosing it. Five phases — reproduce, diagnose root cause (read-only), write a failing test, fix, verify against the full suite. Also known as `klaussy-debug`.

Use when the user wants to upgrade the project's dependencies safely — bump versions, read changelogs for breaking changes, and verify the suite still passes. Upgrades incrementally and stops on the first break; it does not add new dependencies (that's a design decision to raise

Use when the user wants documentation written or updated — docstrings, API docs, a README section, or a doc comment on a tricky piece of code. Documents selectively: what a reader genuinely can't infer from the code, and nothing they can. Writes prose, not code changes. Also know

Use when the user wants lint, format, and type errors fixed in the current changes. Reads CLAUDE.md for the repo's lint/format/type-check commands, runs each, and fixes only style/format/type issues — no behavior changes. Also known as `klaussy-fix`.

Use when the user is tired of approving the same routine dev work ("stop asking me yes", "allow the normal dev tools", "grant permissions"). Detects the repo's stack and writes a curated allow-list into the agent's own local permission file so the basics stop prompting — reading,

Use whenever prose, a comment, a doc, a PR or commit body, or a file's text should read like a human engineer wrote it instead of an AI — "humanize this", "make it sound less like a bot", "does this read AI-written?", or before shipping prose a human will read. Rewrites in four p

Use when the user pastes a ticket, design doc, or task description and wants it implemented. Multi-phase flow — understand, investigate (in plan mode), plan, implement, verify. Enforces strict scope rules and writes failing tests first for bug fixes. Also known as `klaussy-implem

Use when the user wants a new git worktree created for a task. Picks a kebab-case branch name with a fix/feat/chore/docs/refactor prefix, runs `git worktree add` from the configured base branch, and reports the new path. Also known as `klaussy-new-worktree`.

Use when reviewing a staged diff or an about-to-commit/push change for last-mile issues — silent failures, leaked secrets, debug leftovers, blatant correctness landmines, and excessive/narrating comments. Reports findings on the changed lines only; it does not refactor or rewrite

Use when the user wants the current change QA'd and PR-ready evidence captured. Classifies the diff and runs the verification that actually fits it — screen recordings and screenshots for UI/frontend changes, endpoint or e2e runs for backend, command output for a CLI, tests for a

Use when the user wants to restructure code while preserving behavior exactly. Establishes a passing test baseline first, then makes incremental moves that each leave the suite green. Refuses to change behavior and structure in the same step. Also known as `klaussy-refactor`.

Use when the user wants to cut a release — bump the version, update the changelog from conventional commits, and tag. Detects where the version lives, derives the next version from the commits since the last tag, and stages the release locally; it does not push or publish unless

Use when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that won't go significant. NOT recurring metric tracking (that is `analytics`), NOT north-star/KPI trees (that is `kp

Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA roles/names/live regions, contrast, tap-target size. NOT palette or visual intent (that is `design`), NOT test-runner setup (that is `testi

Use when running or fixing paid acquisition on Google or Meta — campaign structure (Performance Max, Demand Gen, Search, Advantage+), platform-fit creative, budget/scaling rules, break-even ROAS math, and Consent Mode v2 / CAPI tracking gaps. NOT the page the ad clicks into (that

Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT build

Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already

Use when a creative goal must become a finished media file: pick and order generative-media models per modality — AI voiceover, image-to-video clips, score — then glue them with ffmpeg (mux, duck, loudnorm, concat). NOT still-image generation/editing (that is `replicate-images`);

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.

Use the bundled `skillopt-sleep` skill to run or manage SkillOpt-Sleep for the

Git + worktree orchestrator entry point. /git-ops --landall surveys every branch/worktree and batch-lands the ones that are done; bare /git-ops runs a status survey. Thin router over the git-ops skill.

Save session state - persist tasks (via TaskList), plan content, and git context. Complementary to /sync.

Session bootstrap - read project context, restore saved state, show status. Quick orientation with optional deep dive.

Query AI Gateway models (list, filter by provider/tag, get details)

Search for icons by name, or identify a PUA character

Install a pinned skill extension on demand (/add-skill <id>), or list core packs and extensions

Implement an approved plan or issue in its own worktree, run the gate, open the pull request.

Close a finished session: sweep for unfinished work, ask once, land, file the follow-ups, hand off, tell the sessions that depend on this one, then archive.

Write the repository handoff file for the next session, and record any durable learning.

Merge an approved pull request, clean up its worktree and branch, then check whether a release is due.

Turn a topic or issue into a plan the reviewer approves in the native plan pane.

Answer a research question with parallel read-only gatherers and one synthesized digest.

Review the branch's diff in two fresh contexts — scope against the spec, then quality — and report findings only.

Open-source MCP servers for Latin American commerce — Pix, NF-e, banking, fiscal, logistics, and messaging across Brazil, Mexico, Argentina, Colombia, Chile, an…

pi coding agent in a technicolor web trenchcoat

Open-source AI Search Intelligence Platform — track, analyze, and improve AI visibility, citations, prompts, competitors, and content opportunities across ChatG…

Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs for agents to discover, inspect, call, and…

⚡ The Complete X/Twitter Automation Toolkit — Scrapers, MCP server for AI agents (Claude/GPT), CLI, browser scripts. No API fees. Open source. Unfollow people w…

The AI agent that interacts with you in the real world.

Offline Codex Desktop migration for Windows and macOS.

LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashbo…

Your smart, reliable, and friendly personal AI assistant.

The LLM Anti-Framework

A general-purpose AIGC video engine: script to finished film in one pipeline — dramas, ads, product videos, otome games, and more. | 通用 AIGC 视频引擎 —— 从剧本到成片一条流水线…

GTM agent for technical founders. Pay-per-result. Signed receipts. Two surfaces: terminal CLI + local web dashboard.

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio)

DeepSeek Harness (dsh) Windows desktop client - bundled Node.js + dsh CLI, one-click launch

Open-source, real-time collaborative AI canvas - notes, mini-apps, and agents on one infinite board.

MCPSafari: Native Safari MCP Server for AI Agents

197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Po…

The AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.

The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, with…

Ouroboros — self-creating AI agent. Born Feb 16, 2026.