LLM Mart Basic

Author and validate Terraform / OpenTofu IaC with plan-before-apply discipline. Use for infrastructure changes and reviews.

Generate and run unit, API, and E2E tests (including Playwright) that match project conventions. Use when adding coverage or reproducing a bug with a failing test first.

Map the attack surface and build a STRIDE threat model - trust boundaries, data flows, entry points, assets, and prioritized threats with mitigations. Use for /threatmap, architecture security reviews, or "what could go wrong?" planning.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Verify and install missing CLI tools on demand - scanners, linters, runtimes - without root, using uvx, npx, or static binaries in ~/.local/bin. Use at the start of any audit, scan, or build when a needed tool may be absent.

Run the Navin Trading Agent OS. Use when the user wants a programmable investment agent, paper portfolio, market scan, debate, risk limits, backtest, or /trading.

Translate and localize between French, English, and Arabic - adapting idioms, register, formats, and cultural context, not just words. Use for any cross-language content.

Default web UI/UX design intelligence for Navin. Design-system generator (84 styles, 192 palettes, typography, landing patterns, UX rules) plus mandatory framer-motion for all web sites. Use when building, designing, scaffolding, or reviewing any website, landing page, dashboard,

One-time setup wizard for the navin upgrade skill. Triggers: setup update, configure update, 切设置更新, 初始化更新.

Value / quality screen for the Trading Agent OS. Prefer cash-generative names with reasonable debt and a margin of safety.

Generate short videos with the generate_video tool (Veo, Sora, Hailuo) - scripts, storyboards, scene-by-scene AI generation, and ffmpeg assembly. Use for social clips, product demos, and ads.

Hunt for concrete, exploitable vulnerabilities - OWASP Top 10 patterns, hardcoded secrets, vulnerable dependencies and CVEs, SSRF, path traversal. Use for /probe, dependency audits, or "find the flaws" requests.

Get current weather and forecasts (no API key required).

Turn websites into clean Markdown or structured JSON for RAG, migrations, or analysis. Use when the user needs scraped content, tables, or documentation corpora - not full browser testing.

Detect changes in price, content, tenders, or availability and alert only on meaningful deltas. Use with cron or .navin/HEARTBEAT.md for recurring checks.

Run a project's engineering decisions as a living log — MADR-lite ADRs (supersede, never delete) for decisions expensive to reverse, issues for the work (and its cheap-to-reverse choices), research artifacts, an optional PRD, a project constitution, and living Mermaid architectur

Author and validate knowledge as OKF (Open Knowledge Format) bundles — a directory of markdown files with YAML frontmatter, where every concept is one .md file with a REQUIRED `type` field, reserved index.md/log.md files, bundle-relative cross-links, and a permissive conformance

Organize, format, and index research as OKF-conformant knowledge bundles — dated, sourced, append-only snapshots of the external evidence behind a decision (technology evaluations, library comparisons, industry-practice surveys). Use when recording research output, structuring a

Add a new declarative attribute to the better-data library (e.g. #[ArrayOf], #[Default], domain hint). Attributes live in src/Attribute/ as final readonly classes with constructor-promoted public properties — pure data carriers, never business logic. The failure mode that catches

Compose better-data DTOs with the better-route library — use BetterRouteBridge::{get, post, put, patch, delete} to register a REST route that hydrates the request into a DTO, validates, calls the handler with (DataObject, mixed $request), and presents returned DataObject values t

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.

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.

Audit infra security: secrets, deps, CI/CD, webhooks, AI/skill files

Audit Solana program code for exploitable bugs and write a findings report

Compare per-instruction CU with the stored baseline to catch regressions

Build the web client (Next.js, Vite, React) and check env, types and bundle

Build Solana programs (Anchor, Pinocchio, native), incl. verifiable builds

Build the Unity project in batchmode for WebGL, desktop, Android or PSG1

Turn a solana-ai-kit fork into a project: set up CLAUDE.md, remove kit files

Un-ignore and commit the kit config dir, instruction file, .mcp.json and .gitmodules

Replay a user's failing transaction on forked state and map the error to source

Deploy a program to devnet, or to mainnet after the user's explicit go-ahead

Review the branch diff for Solana security issues, CU waste and AI slop

Read-only check of toolchain and kit config, with one fix-it command per failure

Consolidate MEMORY.md and Project Learnings: dedupe, resolve conflicts, prune

Explain Solana code with a diagram and a step-by-step walkthrough

PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstre…

An AI Agent that lives in your pocket. Local-first and privacy focused.

Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.

Adaptive Test-time Learning and Autonomous Specialization

Prediction-market trading engine — Wang Transform pricing on 291K+ contracts; paper-traded across Kalshi · Polymarket · Solana DFlow (Jito bundles) · 633 tests

Knowledge Management for Humans and Agents

Open-source Claude Cowork / Codex / WorkBuddy alternative — a local-first AI office agent that turns one request into real PPTX, DOCX, XLSX and HTML files. Runs…

DeepAgent Code: AI coding agent with persistent memory and control plane

Awesome Jev — evidence-graded index of TypeSafe System One: SDKs, MCP tools, agents, apps and open models. 20 languages, rebuilt every 2 hours.

CLI for Telegram — agent-friendly, daemon-based, with webhook event push.

AI deep-research agent that turns any question into a cited report: plans searches, reads real sources, verifies evidence. Self-hosted, multi-provider, Docker-r…

Event-stream AI Agent framework for building your persona bot 🍊

Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops t…

Local Emperor-style AI agent with Vue WebUI, multi-provider LLMs, streaming chat, tools, skills, memory, and token telemetry.

Open-source AI reverse-engineering agent platform and MCP server for Ghidra, Frida, x64dbg and Rizin — automated PE/APK/binary analysis, CTF and malware researc…

"Never send a human to do a machine's job" - Open Source AI hacking agent

Prismer Cloud

My Personal Blog (Robotics)

Tau Coding Agent - like Pi, but twice as much

Open-source alternative to OpenAI Dots: self-hosted AI chat, tools, approvals, connectors, and computer tasks.