urmzd

Write or rewrite text in ASD-STE100 Simplified Technical English (STE): the approved-word dictionary discipline, controlled verb forms, sentence and paragraph limits, procedural vs descriptive rules, and safety-instruction structure. Use when the user asks for Simplified Technical English, STE, ASD-STE100, controlled language, or aerospace-style technical writing, or when authoring procedures, maintenance instructions, or safety warnings that must be unambiguous. Do NOT use for general documentation cleanup (use clean-docs), README structure (use write-readme), or ordinary prose style.

House doctrine for designing LLM agent systems: safety enforced by the harness and tools rather than model goodwill, tools that execute and return results, minimal loop code, interface-first component seams, typed config, deterministic evals over LLM judges, and POC scope discipline. Use when designing or reviewing any agent, tool-use loop, eval harness, or agent-backed CLI, in any framework. Do NOT use for Pydantic AI framework mechanics (use building-pydantic-ai-agents), generic design principles (use review-design), or Go agent-loop implementation details (use agent).

Operate the detect-secrets pre-commit hook correctly: update the baseline with the right flags, break the "baseline file was updated, please git add" commit loop, allowlist false positives, and audit real findings. Use when a commit fails on detect-secrets, the .secrets.baseline keeps changing, or a false positive blocks a push. Do NOT use for storing or injecting secrets via 1Password (use manage-secrets) or repo-wide leak scanning with gitleaks and trufflehog (use audit-security).

Run a project's own eval suite end to end without babysitting: locate the harness, launch it in the background, monitor to completion, parse the report into a normalized summary (pass rate, latency percentiles, tokens, cost), and diff against the previous run with per-case regressions explained. Use when asked to "run the evals", re-run after a change, or score a new dataset in any repo with an eval harness. Do NOT use for the GAP benchmark suite (use run-evals), SAIGE provider-boundary checks (use verify), or designing new eval sets (that is authoring work, not a run).

Playbook of known failure modes in this dotfiles stack: pipx "bad interpreter" after Python rebuilds, gpg commit-signing failures, direnv/nix shellHook running bash instead of zsh, Powerlevel10k instant-prompt warnings, and Neovim plugin errors from removed Lua APIs. Use when a shell startup error, git signing failure, broken CLI shim, or nvim stack trace appears on this machine. Do NOT use for generic runtime debugging in projects (use diagnose-runtime), chezmoi naming and templating conventions (use dotfiles), or authoring pinned installers (use setup-devenv-with-chezmoi).

Clean and modernize documentation in place. Enforce no em dashes, readable structure, proper Markdown formatting, accurate commands, current examples, resolved internal links, and user-focused guidance. Use when the user invokes /clean-docs, asks to clean docs, make docs up to date, improve README/AGENTS prose, remove AI-looking punctuation, or make docs easier for users to act on.

Create well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality.

Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec.

Build streaming LLM agent loops in Go with typed deltas, tool execution, context compaction, sub-agent delegation, and RLHF feedback. Use when building AI agents, integrating LLM providers, or implementing tool-use patterns.

Build and query knowledge graphs with PostgreSQL + pgvector. Ingest episodes, extract entities/relations via LLM, and search facts by semantic similarity or keyword. Use when working with knowledge graphs, entity extraction, or graph storage.

Build multi-modal RAG pipelines with graph-enhanced retrieval in Go using saige/rag. Covers chunking, multi-retriever fusion, reranking, HyDE, evaluation metrics, and PostgreSQL + pgvector storage.

Reference for the file formats, locations, and discovery conventions agentspec manages across AI coding tools (skills, agents, AGENTS.md, CLAUDE.md, llms.txt, instruction files, plans, memories, sessions, MCP, permissions, hooks, plugins). Use when you need to know where a resource lives, what format it uses, how agentspec discovers it, or how it maps into the ~/.agents canonical store.

Demonstrates the minimal agentskills.io format.

Cuts releases and validates changelogs across the workspace. Use when preparing or auditing a release.

Generate polished resumes (PDF, DOCX, Markdown) from JSON data. Installs the incipit CLI, provides the resume schema, and uses templates for rendering. The agent writes JSON directly — no AI subcommands needed.

Play terminal chess against an AI opponent with minimax alpha-beta pruning. Use when launching, debugging, or developing the chess game.

Run Linear Genetic Programming experiments — train agents on CartPole, MountainCar, or Iris classification with optional Q-Learning and hyperparameter optimization. Use when running LGP experiments, tuning hyperparameters, analyzing results, or extending the framework with new problem domains.

Run or regenerate the GAP eval set after the Go/SAIGE migration. Use when validating the eval corpus, regenerating SAIGE observations, or scoring committed GAP metrics offline.

Embed source files into documents using comment markers. Use when syncing code snippets into README, docs, or any text file that references external source files.

Release-state reconciler — declarative change + release management. Single binary, one global version per repo, typed publishers (cargo/npm/docker/pypi/go), no user shell hooks.

Generate a complete communication-focused language guide for travelers. Creates all 11 chapter files following the project's system prompt and checklist.

AI-native smart home skill — gives agents direct Zigbee device control tailored to user preferences. Use whenever the user wants to manage lights, pair devices, adjust settings, or interact with their home naturally — even casual requests like 'turn off the bedroom light' or 'make it cozy in here'.

Streaming video analysis with GStreamer and OpenCV in Rust. Use when working on video pipelines, frame processing, or codec integration.