v1truv1us-ai-eng-system
claudeCurated collection of engineering tools, agents, and workflows. Comprehensive system for AI-assisted software engineering and DevOps.
128 skills
Manage GPU VRAM sharing across services (Ollama, Whisper, ComfyUI) with OOM retry logic and auto-unload patterns.
Plugin lawless-m-claude-skills-1 from marketplace cascade-code-devops-misc-2 in joshuarweaver/cascade-code-devops-misc-2. Commands read from the repo's manifest — 1 month ago.
docsdocs (living docs people share, comment on and edit; use only when the user asks for one: names a doc, document, page, memo, spec, PRD, runbook or write-up, asks for somewhere to share or keep editing something, or says yes to your doc offer; a plan, comparison, summary or notes asked in chat stays
pdfUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, ext
import-memoryImport a memory export from another AI assistant into Claude's memory — conversationally, additively, and with the content treated as data.
morningRender the user's morning brief as a styled HTML artifact, or set it up as a recurring weekday task. Use only when the user explicitly asks to run, see, or set up their morning brief, or if they invoke /morning by name. A question about their day, schedule, or calendar is not by itself a request for
xlsxUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spr
pptxUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations as PowerPoint (.pptx) files; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be u
skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better t
docxUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, page nu
Anthropic-Rate-LimitsAnthropic API rate limit handling - retry logic, backoff, throttling for batch workloads against Claude models
Blog ManagementUse when creating, editing, publishing, or deleting posts on Cyril's Workshop blog or the steponnopets.net devblog.
boofuzzUse when writing or contributing a boofuzz network-protocol fuzzer in this repo — layout, formatting rules, and reading results.
BrowserBridgeUse when a task needs real-time control of a connected browser via the Browser Bridge Broker — submit JS jobs over HTTP that browsers eval and return.
CSharpenerUse when you need to find unused methods in a C# solution, trace who calls a method, assess removal impact before refactoring, or generate call-graph documentation/diagrams for C# code.
Character LoRA on RunPodUse when training a character LoRA (Chroma/Flux or Pony/SDXL) on a RunPod GPU and wiring it into the ComfyUI + pony_web render stack.
Creating SkillsUse when writing a new skill or revising an existing one — format, trigger descriptions, and what content belongs in a skill.
DCG-Grammar-CompanionUse when planning a new parser or lexer for a published language spec, validating parser correctness, or fuzz-testing a parser — build a Prolog DCG grammar companion alongside the hand-written parser.
DatabasesUse when querying or writing any RI database — Exportmaster (DBISAM sem01/sem04), PostgreSQL x3rocs, X3/Sage1000 SQL Server, keycloak MySQL, or Parquet. DuckDB is the primary read path.
Dotnet 8 to 9Use when migrating a project from .NET 8 to .NET 9, or preparing .NET 8 code for that migration with only the .NET 8 SDK available (e.g. Claude for Web).
DuckDB-ExtensionsUse when building, debugging, or deploying a DuckDB loadable extension — version matching, "not a DuckDB extension" errors, install paths, auto-loading.
ElasticsearchUse when searching, indexing, bulk-loading, or rebuilding indices on RI's Elasticsearch cluster (locked at 5.2) via ServiceLib.Elasticsearch.
EmailUse when sending email from RI C# services — notifications, daily reports, or log files as attachments.
Finding UnknownsUse when starting ambiguous or high-stakes work, or when the user says "blind spot pass", "interview me", "what am I missing", or asks for an implementation plan.
Flowstone DocsUse when writing Flowstone-compatible project or hub notes — small Markdown notes with [[wiki-links]] so the knowledge graph stays connected; never touches repo READMEs.
GogsGitea issue tracker on dw.ramsden-international.com - the triage/plan/execute plan/fixed label workflow, plus creating, querying and commenting on issues via the REST API
Image FilesUse when resizing, converting, optimizing, or batch-processing images with ImageMagick — especially when the magick command isn't found on PATH on Windows.
JSharpenerUse when finding dead JS/TS code, tracing callers (call graphs), or analyzing module and circular dependencies in a JS/TS project.
LoggingUTF-8 file logging with automatic date-based filenames and thread-safe operations for RocsMiddleware services
NawinUse when working on the Nawin .NET 9 codebase or connecting to 9front/Plan 9 over 9P2000 — file serving, CPU shell, FUSE/ProjFS mounts, auth.
Parquet FilesThis describes how to create Parquet files in C#, including updating and multi threaded creation
PostgreSQLPostgreSQL database operations using PgQuery tool for DDL execution, schema management, and query operations
Python JSONUse when reading or writing JSON in Python on Windows to avoid CP-1252 mojibake — the convention here is to copy this skill's json_io.py into the project and always open JSON as UTF-8.
Qwen-OllamaUse when a task needs local LLM inference via the on-box Ollama server (Qwen 2.5) instead of a cloud API.
Reverse Proxy DeploymentUse when deploying behind the Apache reverse proxy on rivsprod01, writing a ProxyPass config in /etc/apache2/proxy-conf.d/, or fixing 404s under a path prefix.
Roo-VMSAlpine and Debian QEMU VMs for protocol testing, fuzzing, and network experiments
RustUse when starting or writing Rust projects — and especially this environment's v4l2 video I/O, RGB-to-YUYV conversion, and frame-timing patterns.
ScryQLUse when asked "why isn't <record> in this query result", to trace a row through joins, or to decompose WHERE/JOIN-heavy SQL into per-step pass/fail attribution — generates ScryQL rules.pl + queries.sql.
SharePointUse when uploading/downloading files to RI's SharePoint Online sites, updating Excel tracker cells, or normalizing pasted share links.
Suno-AutomationUse when asked to make or generate a song on Suno, automate Suno, or fill the suno.com create form programmatically — drives a logged-in browser via the Browser Bridge.
Vram-GPU-OOMUse when GPU services (Ollama, Whisper, ComfyUI/Flux, OCR) contend for VRAM on the RTX 3090 and hit CUDA OOM.
web-frontendUse when building an elaborate multi-component claude.ai HTML artifact needing state, routing, or shadcn/ui — not for simple single-file artifacts.
Whisper-TranscriptionUse when transcribing audio to text via the local whisper.cpp server (large-v3, CUDA) — POST an audio file, get JSON back.
Windows ServersUse when running commands on RI's Windows servers RIVSPROD02 (prod), RIVMIS01 or RIVSIS02 — remote PowerShell as mh.admin, or when the user says "on prod2", "on sis", "on mis".
X3 SOAP Web ServicesUse when building, deploying, or calling Classic SOAP sub-program web services on Sage X3.
auto-testingUse when building an automated test → issue → fix loop with Claude Code and GitHub issues — overnight auto-fixing, regression loops, self-healing CI.
chestnutUse when told to "use /chestnut for logging", or when adding structured logging to, or converting the logging of, an RI CGI program or scheduled task — the Chestnut JSON Lines standard, library, Vector shipping and dashboard. Also for Chestnut tracing and verification work — trace events, CGILOG_TRA
ri-service-toolkitUse when building a .NET 9 service from RI's shared components (ExportKing, KdbxCredentials, OhSheet, Anthea) deployed as a TinyWeb CGI, or registering a URL on the dw portal page.
google-workspaceRead this before the first Google Drive, Docs, Sheets or Slides connector call whenever the task creates or changes a Google file. Use this skill whenever the user wants to create or change a Google Doc, Sheet or Slides file in their Google Drive. Triggers include: a request that names Google Docs,
task-loopDo the next unblocked task from tasks/. Exactly one slice, then stop. Use when the user says "do the next task"; /tasks repeats it to drain the queue.
Curated collection of engineering tools, agents, and workflows. Comprehensive system for AI-assisted software engineering and DevOps.
128 skills
Claude Code skill for managing Red Hat Developer Hub plugin lifecycle including deployment and configuration.
61 skills
A full-stack development framework and toolkit for building scalable applications with integrated deployment and infrastructure management.
61 skills
Tech-agnostic development workflow automation spanning the complete lifecycle from project initialization through deployment.
50 skills · 8 MCP servers
Claude Code plugins for Git, GitHub, Google Workspace, Slack, Go, and Terraform automation supporting development workflows.
53 skills
Integration skills for Tencent Cloud infrastructure and services within Claude Code workflows.
34 skills
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance.
21 skills
GPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.
98 skills
SkyPilot agent skill for launching cloud VMs, Kubernetes pods, and Slurm jobs across 25+ clouds
1 skill
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered workflows.
1 skill
Run a GPU job under a hard dollar cap and collect the files it writes.
1 skill · 1 MCP server
AKS operational skills for troubleshooting, advanced cost-efficiency analysis, known issues, GPU inference, and packet capture.
6 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.