LLM Mart Basic

Audit ML experiment tracking infrastructure for reproducibility gaps, parameter logging completeness, metric capture, artifact management, and pipeline orchestration. Covers MLflow, Weights and Biases, DVC, Sacred, Neptune, Hydra configs, model registries, and produces a reproduc

Optimize mining extraction operations by analyzing ore grade control, processing plant throughput, metallurgical recovery rates, energy consumption, and water balance.

Audit commercial building energy performance including HVAC optimization, ENERGY STAR scoring, utility cost analysis, demand response readiness, and sustainability compliance.

Analyze fleet maintenance programs for preventive maintenance scheduling effectiveness, parts inventory forecasting, vehicle downtime minimization, total cost of ownership modeling, and telematics integration.

Analyze fleet safety programs including driver behavior scoring, accident trend analysis, CSA BASIC score monitoring, DOT audit readiness, Hours of Service compliance, and drug and alcohol testing programs.

Manage the full Freedom of Information Act (FOIA) and state public records request lifecycle — intake form generation, agency-specific portal routing (FOIA.gov, FBI eFOIA, USCIS, FOIAonline successor portals).

Analyze food supply chain systems for waste reduction opportunities including shelf life prediction models, FIFO and FEFO inventory rotation enforcement, demand forecasting accuracy and bias, donation logistics workflows, cold chain temperature monitoring, and sustainability repo

Benchmark franchise locations by comparing top and bottom quartile performance across revenue, profitability, and operational scores.

Analyze franchise inventory management for par level optimization, waste tracking and root cause analysis, and theoretical vs. actual usage variance.

Analyze fraud detection systems including rule engines, ML scoring models, real-time transaction monitoring, alert triage workflows, false positive management, SAR/CTR regulatory reporting, adversarial robustness testing, and adaptive retraining pipelines for payment fraud, accou

Analyze fleet fuel optimization systems including MPG consumption analytics, eco-driving behavior scoring, route fuel cost modeling, idling detection and anti-idle programs, IFTA tax compliance reporting, alternative fuel transition planning, EV charging infrastructure readiness,

Analyze university and research institution funding allocation systems including RCM revenue attribution, performance-based budgeting, faculty startup package management, F&A indirect cost recovery distribution, equipment sharing and core facility recharge rates.

Analyze game AI systems including behavior trees, finite state machines, GOAP planning, utility AI scoring, A-star and NavMesh pathfinding, steering and flocking behaviors, perception and awareness models, dynamic difficulty adjustment, NPC dialogue trees and scheduling, boss AI

Analyze game design documents and implementations for core gameplay loop clarity and depth, XP leveling curves and unlock pacing, difficulty curve spikes and plateaus, skill tree viability, player motivation via Self-Determination Theory.

Analyze in-game economy systems including soft and hard currency source-sink balance, inflation projection modeling, loot table drop rate fairness and pity system evaluation, gacha probability disclosure, player marketplace health and price manipulation risks.

Analyze game monetization implementations including IAP purchase flow and server-side receipt validation, ad mediation waterfall and rewarded video placement, subscription lifecycle and grace period handling, battle pass XP progression.

Analyze game code for performance bottlenecks including draw call batching and overdraw, shader complexity and LOD strategy, per-frame GC allocation pressure, object pooling gaps, physics timestep and collision matrix tuning, spatial partitioning for entity queries.

Whole-codebase analysis powered by Gemini 2.5 Pro's 2M token context window. Triggers: bounded per-module analysis misses inter-module patterns or when you need a full-graph view before a major refactor.

Generative Engine Optimization (GEO) / Answer Engine Optimization (AEO) — make a site citable by ChatGPT, Perplexity, Claude, Gemini, and Google AI Overviews. Triggers: "GEO", "generative engine optimization", "AEO", "answer engine optimization", "AI search optimization".

Analyze grant management and sponsored research operations including proposal lifecycle tracking, pre-award routing and budget development, post-award expenditure monitoring and burn rate analysis, 2 CFR 200 Uniform Guidance cost allowability enforcement.

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.

Daily standup: all 8 departments report on the current project in parallel

Identify skills injected where not needed, propose regex and description tightening

Draft X/Twitter announcement post (or thread) for the latest plugin release

Deep quality audit of all skills, agents, and commands for inconsistencies, gaps, duplication, and token waste

Analyze negative-signal sessions for a skill, identify failure patterns, propose and apply fixes

Eval all skills with sufficient data, rank by procedure-following score, identify candidates for optimization

Propose a skill revision and compare fresh executions under a frozen rubric

Prune stale entries from the whetstone sync decision log

Bump version, commit, push, mirror to ai-skills, and update local plugin

Run the SkillOpt process-skill optimizer (offline, local). Default prints the exact bare-terminal command (safe); --run executes it in-session (hardened + checkpointed).

Analyze reference repos and recommend skill/agent/command improvements based on cross-repo patterns

Triage all open PRs with parallel agents, label, group, and review one-by-one

Author a new skill from scratch with paired trigger fixtures and full validation. Use when adding a skill that has no upstream skills.sh source (discipline, meta, or internal-pattern skills).

Create Architecture Decision Records with format selection and lifecycle management

Score each of the 5 agent-native principles (parity, granularity, composability, emergent capability, improvement-over-time) against a codebase and report gaps

Explore requirements and approaches through collaborative dialogue before planning implementation

Create engaging changelogs for recent merges to main branch

Expand each section of a plan via parallel research agents that add framework specifics, library conventions, and concrete implementation steps

Post-ship documentation sync. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, and optionally bumps the version.

Record a video walkthrough of a feature and add it to the PR description

AI coding platform for teams

AI Multi-Agent Framework in .NET

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight & extensible, works with any harnesses, any models,…

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to…

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harnesss. Suppprtd automation, scripting, coding, build anything and more. Power…

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex