yzmir-pytorch-engineering

Use when drafting, revising, critiquing, or planning prose fiction or creative nonfiction, especially when author voice, continuity, genre expectations, or truth claims need deliberate treatment.

1 skill · 3 commands · 11 agents

Use when documentation accuracy, executable procedures, institutional register, sensitive information, or source-to-document traceability needs deliberate review.

2 skills · 4 commands · 5 agents

Use when reconstructing an existing codebase: source-linked architecture, dependency and risk findings, coverage limits and incremental refresh.

1 skill · 5 commands · 4 agents

Use for Rust-specific ownership/API, async cancellation, unsafe/FFI soundness, feature/toolchain compatibility, diagnostics, packaging or profiling problems in a real crate.

1 skill · 5 commands · 3 agents

Use when an organization explicitly selects a software governance profile requiring lifecycle evidence, traceability, risk decisions or measurement.

5 skills · 4 agents

Use when test reliability, isolation, coverage gaps, performance experiments, resilience, or release evidence needs investigation or a concrete verification strategy.

1 skill · 5 commands · 3 agents

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Install the "AAS Security Engineer" editorial skill bundle for Claude Code.

12 skills

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents