LLM Mart Basic
@llm-mart · Joined Jun 2026
Maintain or assess Workflow Foundation-based solutions on .NET Framework, especially where long-lived process logic or legacy designer artifacts still matter.
Build and modernize WPF applications on .NET with correct XAML, data binding, commands, threading, styling, and Windows desktop migration decisions.
Write, run, or repair .NET tests that use xUnit. Use when a repo uses `xunit`, `xunit.v3`, `[Fact]`, `[Theory]`, or `xunit.runner.visualstudio`, and you need the right CLI, package, and runner guidance for xUnit on VSTest or Microsoft.Testing.Platform.
Use when writing, reviewing, or refactoring C/C++ code, especially on 32-bit ARM embedded targets. NOT for formatting-only changes, simple file reads, non-embedded C/C++ (desktop/server), or C#/Java despite the 'C' in the name.
Use when debugging embedded firmware issues — analyzing crash logs, investigating state machine lockups, tracing sensor/signal anomalies, or performing structured root-cause analysis after a crash has been located. For fault-register and stack-frame triage, load hardfault-triage
Use when writing or reviewing embedded C firmware, FreeRTOS tasks, ISR handlers, NVM/flash storage, or sensor driver state machines. NOT for documentation-only RTOS references, conceptual RTOS discussions, or bare-metal projects without an RTOS or sensor subsystem.
Use when reviewing design documents, architecture specs, technical proposals, or plans that make claims about API names, file paths, enum values, counts, or mechanism feasibility — a lightweight claim-by-claim check against the codebase with evidence. Built into embedded-workbenc
Use when triaging processor exception crashes — HardFault, MemManage, BusFault, UsageFault, data/prefetch abort, illegal instruction, or watchdog timeout. Covers fault-register interpretation, stack-frame extraction, PC-to-source resolution, and root-cause classification.
Use when building, flashing, or packaging firmware with Keil MDK (UV4 CLI, ARMCLANG), analyzing .map files for ROM/RAM optimization and memory budget, or diagnosing Keil-specific build failures. NOT for non-Keil build systems (Makefile, CMake, IAR, GCC-only). For crash triage see
Use when reviewing or fixing async protocols, retries, ACK/NACK handling, pending flags, timeout logic, or state-machine lockups in embedded firmware. NOT for generic network protocol design (TCP/HTTP/MQTT) unless targeting embedded firmware stack.
Use when developing Go applications, implementing job schedulers or cron (netresearch/go-cron, ofelia), Docker API integrations, LDAP/AD clients, building resilient services with retry logic, setting up Go test suites (unit/integration/fuzz/mutation), or running golangci-lint.
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.
Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.
/resolve-finding
Resolve finding
Resolve a Blumira finding with the appropriate resolution type and notes
/security-posture
Security posture
Overall security posture review including open findings by severity, agent coverage, and trends
/offboard-user
Offboard user
Run the complete CIPP M365 offboarding workflow for a departing user — capture audit state, revoke access, handle mailbox, reclaim licenses
/secure-score-report
Secure score report
Generate a portfolio-wide M365 security posture report — Secure Score equivalents, MFA enrollment, conditional access coverage, and domain authentication across all managed tenants
/standards-drift
Standards drift
Find tenants that have drifted from the MSP's configured CIPP standards baseline — missing standards, standards in Report-only mode, recent compliance failures
/tenant-health
Tenant health
Quick health snapshot for a single tenant — BPA failures, conditional access enforcement, MFA gaps, domain authentication, standards compliance
/log-time
Log time
Log a time entry (billable activity) against a Clio matter
/matter-summary
Matter summary
Consolidated view of one Clio matter — contacts, open tasks, recent activities, recent communications, and bills
/search-contacts
Search contacts
Search Clio contacts by name, company, or email
/search-matters
Search matters
Search or list Clio matters by name/client and status
/capacity-check
Capacity check
Capacity forecast for cloud resources, scoped to a resource type or covering everything connected
/cost-report
Cost report
Cloud cost anomaly and reclaimable-spend report for a given window
/network-sweep
Network sweep
Full network health sweep across all connected network-monitoring tools — devices down, degraded links, and topology changes
/drift-report
Drift report
Report control and configuration drift since the last known-good baseline for a client or the whole portfolio
/evidence-pack
Evidence pack
Build a source-cited compliance evidence package for a client against a named framework
/questionnaire
Questionnaire
Draft evidence-backed answers to the standard cyber-insurance questionnaire for a client
/list-computers
List computers
List computers in ConnectWise Automate with optional filters
/run-script
Run script
Execute a script on an endpoint in ConnectWise Automate
/create-quote
Create quote
Create a ConnectWise CPQ quote by copying a template or an existing quote
/get-quote
Get quote
Get a ConnectWise CPQ quote with its tabs, line items, customers, and terms
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…
0 views 0 likesAn AI Agent that lives in your pocket. Local-first and privacy focused.
1 views 0 likesUnofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
3 views 0 likesAdaptive Test-time Learning and Autonomous Specialization
2 views 0 likesPrediction-market trading engine — Wang Transform pricing on 291K+ contracts; paper-traded across Kalshi · Polymarket · Solana DFlow (Jito bundles) · 633 tests
2 views 0 likesKnowledge Management for Humans and Agents
2 views 0 likesOpen-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…
3 views 0 likesDeepAgent Code: AI coding agent with persistent memory and control plane
2 views 0 likes