LLM Mart Basic
@llm-mart · Joined Jun 2026
Restate the last message in plain human language, with no jargon. Use for /bro or when asked to say it plainly.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", "make a driver skill for this repo", or when a project has no scripted way to pro
Remove AI-generated code slop and clean up code style
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it o
Find failing PR checks, inspect logs or external check links, and apply focused fixes
Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution
Fetch and summarize review comments from the active pull request
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
Apply when repeated fixes sharing an assumption fail. State the assumption and choose an observation that can challenge it before trying another fix that depends on it.
Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
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 MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.
/requirements
Requirements
Generate requirements from goal and research
/research
Research
Run or re-run research phase for current spec
/start
Start
Smart entry point that detects if you need a new spec or should resume existing
/status
Status
Show all specs and their current status
/switch
Switch
Switch active spec
/tasks
Tasks
Generate implementation tasks from design
/triage
Triage
Decompose a large feature into multiple dependency-aware specs (epic triage)
/tree-ring-update
Tree ring update
Check for or install a verified Tree Ring Memory CLI update without changing installation scope
/README
README
This directory contains the command implementations for the fast-agent CLI.
/close
Close
They operate it without you.
/outcome
Outcome
Promised, measured, accepted. A number nobody signed is claimed, not delivered.
/prep
Prep
Prepare the meeting. One page from the record.
/receipts
Receipts
Find the receipt. A dated line, or it did not happen.
/trust
Trust
Diagnose trust. Process gap, or they stopped trusting you.
/awesome-docs
awesome-docs
Generate, convert, and maintain animated GitHub-safe Markdown documents with animated SVG diagrams. Covers four SVG patterns (architecture flow, lifecycle loop, field carousel, timeline phases), guided interview for any doc type (README, architecture guide, runbook, API reference, tutorial, RFC, post-mortem, how-it-works, or custom), converting existing plain Markdown, diffing for stale diagrams, quality auditing, local preview, and multi-platform export. Use when asked to "create a README for X", "write an architecture doc", "animate this guide", "convert my doc to animated", "check if my diagrams are stale", or "export my doc for Confluence".
/aws-profile
aws-profile
AWS profile management for MCP servers — discover profiles across SSO, Granted, and assumed-role chains, check credential TTL, switch profiles across VS Code and Claude Code MCP configs, and scan AWS Organization accounts.
/aws
aws
Structured guidance for AWS CloudFront distributions, WAF web ACLs, Lambda@Edge, CloudFront Functions, Firewall Manager multi-account enforcement, and IAM/IRSA patterns. Covers OAC, cache policies, security headers, managed rule groups, rate limiting, FMS FIRST/MIDDLE/LAST ownership model, and production-ready Terraform generation.
/azure
azure
Azure identity (Workload Identity, OIDC, Entra ID), resource tagging, AKS platform patterns, RBAC scoping, and production-readiness review — with Terraform generation.
/chaos
chaos
Design, run, and debug Chaos Engineering experiments on Kubernetes using Litmus Chaos v3 and Chaos Mesh v2. Covers fault injection (pod-delete, network-loss, CPU stress, node-drain), steady-state hypothesis probes, GameDay runbooks, scheduled experiments, DORA feedback loop, and RBAC setup. Use when asked to "inject a pod fault", "run a GameDay", "schedule chaos experiments", or "debug why my ChaosEngine is stuck".
/checkov
checkov
Bootstrap Checkov on a developer laptop, run static or plan-level Terraform security scanning for AWS/Azure/GCP/EKS, resolve private GitHub modules via gh CLI, generate pre-commit hooks, produce multi-format output (cli/json/sarif/junit), and fix violations with AI-generated patches. Use when asked to "scan my Terraform", "run checkov", "check my IaC for security issues", "set up checkov pre-commit", or "fix checkov findings".
Make any song you can imagine
39 views 0 likesLeading AI-powered video generation platform that specializes in creating hyper-realistic talking avatars
37 views 0 likesHermes Agent is an open-source, self-improving autonomous AI agent developed by Nous Research
36 views 0 likesKilo Code is a popular, open-source AI coding agent and "agentic engineering" platform designed to help developers build, refactor, and debug software faster
34 views 0 likesGeneral-purpose agent in one static Go binary. ReAct loop, ACP server for IDEs, OpenAI-compatible REST API with embedded web UI, Telegram gateway, cron schedule…
20 views 0 likesAutonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.
20 views 0 likesTSP自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | 基于 TickFlow 数据源 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源 ,非TickFlow官方项目
15 views 0 likesCurated, verified Agent Skills powered by ModelStudio.
18 views 0 likesRun Claude Code, Codex, Antigravity, Cursor Agent and OpenCode as one runtime — persistent sessions, multi-agent councils, an OpenAI-compatible endpoint, an MCP…
17 views 0 likespi had nothing (nothing), so I made something (something) — sorry mariozechner-senpai, I went ahead and lovingly soiled your pure pi for you. opinionated fork o…
14 views 0 likesA persistent workspace for development work that self-improves and continues beyond one session.
33 views 0 likesOpen-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
20 views 0 likes📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | http…
28 views 0 likesDeterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.
31 views 0 likesDeterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, with bundled web/docs/fe…
20 views 0 likesNative Safari browser automation for AI agents. 97 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chro…
32 views 0 likesAgent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
15 views 0 likesGit for agent memory. Branches, diffs, PRs, and rollback for what your agents know.
32 views 0 likesMulti-Provider AI Gateway - No personal logs by design. Model autodiscovery, Failover groups, High availability, Android companion app, and more - "Because we h…
16 views 0 likesProduction-grade MCP server for MikroTik RouterOS with secure AI-native network automation.
28 views 0 likes