LLM Mart Basic

Patterns for building production-quality CLI tools with predictable behavior, parseable output, and agentic workflows. Triggers: cli tool, command line tool, build cli, cli patterns, agentic cli, cli design, typer cli, click cli.

Cloudflare Workers + Wrangler edge ops: runtime, bindings, local dev, secrets, deploy/CI, Pages-vs-Workers. Triggers on: cloudflare workers, wrangler, wrangler deploy, wrangler.toml, KV, D1, R2, durable objects, queues, vectorize, compatibility_date, edge functions, illegal invoc

Analyze codebase with tokei (fast line counts by language) and difft (semantic AST-aware diffs). Get quick project overview without manual counting. Triggers on: how big is codebase, count lines of code, what languages, show semantic diff, compare files, code statistics.

Color for developers: color spaces, accessibility contrast, palette generation, CSS color functions, design tokens, dark mode. Triggers on: color, palette, contrast, WCAG, APCA, OKLCH, color-mix, dark mode colors, design tokens, CVD, color blind, P3, sRGB.

Docker, Kubernetes, and AWS ECS/Fargate patterns. Triggers on: Dockerfile, docker-compose, kubernetes, k8s, helm, pod, deployment, service, ingress, container, image, ecs, fargate, task definition, ecs service, awsvpc, FARGATE_SPOT, ALB, ecs vs kubernetes.

Craft CMS 5 development - content modeling, Twig templating, element queries, GraphQL, plugins, and the Craft 4-to-5 Matrix-as-entries change. Use for: craft cms, craftcms, craft 5, twig, pixel & tonic, matrix field, entry types, sections, element query, eager loading, blitz, pro

Cypress end-to-end and component testing operations - selector/retry-ability strategy, cy.intercept network stubbing, cy.session auth, component vs e2e, flake diagnosis, CI, Test Replay. Use for: cypress, e2e test, component test, cy.get, cy.intercept, cy.session, data-cy, data-t

Process JSON with jq and YAML/TOML with yq. Filter, transform, query structured data efficiently. Triggers on: parse JSON, extract from YAML, query config, Docker Compose, K8s manifests, GitHub Actions workflows, package.json, filter data.

Build and run evals for LLM and agent systems: golden datasets, LLM-as-a-judge with bias control, trajectory/step/outcome scoring, adversarial refuters, and CI regression gates. Triggers on: eval, evals, eval harness, golden dataset, golden set, LLM-as-a-judge, judge rubric, judg

Deep explanation of complex code, files, or concepts. Dispatches skill-preloaded agents, uses structural search, generates mermaid diagrams. Triggers on: explain, deep dive, how does X work, architecture, data flow.

Comprehensive ffmpeg/ffprobe media processing: transcode, cut/trim/concat, color grading, loudness normalization, subtitles, GIFs, HLS packaging, hardware encoding, and quality gates (VMAF). Triggers on: ffmpeg, ffprobe, transcode, compress/convert video, extract audio, color gra

Router and composition workflows for Figma via the official Figma MCP: which Figma skill/tool for which job, capture-to-canvas (screenshots or shotcraft crops into a Figma file), moodboard and reference-board composition (grid, plus, loose-plus arrangements with a deterministic l

Modern find-and-replace using sd (simpler than sed) and batch replacement patterns. Triggers on: sd, find replace, batch replace, sed replacement, string replacement, rename.

Landing discipline for parallel work: sequential test-gated landing queue, pre-land scrub, auto-rebase of in-flight lanes, fleet status, one-shot revert. Native primitives spawn; fleet-ops lands. Triggers: landing queue, land branches, merge queue, test gate, fleet status, land a

Generative art programming - three.js scenes, p5.js sketches, SVG generation, GLSL shaders, procedural algorithms, and color for creative coding. Use for: generative art, creative coding, three.js, p5.js, SVG, GLSL, shader, noise, perlin, simplex, flow field, particle system, SDF

Git + worktree orchestrator: status survey, per-worktree triage, commits, PRs, branches, releases, rebases — reads inline, writes to a background agent. Triggers on: git status, anything to commit, anything to push, commit, push, create PR, rebase, release, tag, changelog, worktr

GitHub remote operations and README authoring: repo creation, metadata, releases, issue/PR management with preview-before-send, README as a landing page (badge row, features-as-benefits, screenshots, Recent Updates), and read-only security auditing. Triggers on: write a README, i

Go development patterns, concurrency, error handling, testing, and project structure. Use for: golang, go, goroutine, channel, context, errgroup, go test, go mod, go build, interface, generics, table-driven tests, worker pool, sync.Mutex, sync.WaitGroup, pprof, go vet, golangci-l

Hono on Cloudflare Workers - composition, middleware, typed bindings, validation, RPC, streaming, testing. Use for: hono, hono middleware, app.route, hono rpc, c.env bindings, onError, zValidator, vitest-pool-workers, spa fallback worker.

Source, vet, normalize and ship SVG icons for web UI - set selection, licence and trademark traps, currentColor theming, sprite/inline delivery, and accessibility. Triggers on: icon, icons, svg icon, find an icon, add an icon, icon set, icon library, iconify, lucide, heroicons, p

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}}

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.