Claude Skills by ahundt

autorun control commands, stated as prose after $ar: status; allow/justify/find file-creation policy; ok/no/blocks/clear command guards; global variants; stop/estop; task tracking and pause; cache-miss gate; planexport settings; reload; help lists everything.

Guides creation, audit, and improvement of portable Agent Skills using the shared

Use before writing any git commit message or reviewing one, and when the user asks for "commit requirements", "commit message guidelines", "/ar:commit", or "/ar:gc". Carries the 17-step pre-commit analysis, the concrete-subject rules that ban vague verbs and session-internal jargon, and the checks that keep a message reviewable from the repository alone.

Design and review caller-facing names and contracts: functions, tools, commands, CLI flags, parameters, config keys, env vars, profiles, event types, and node/edge identifiers. Check names, descriptions, help, docstrings, schemas, defaults, bounds, units, errors, outputs, mutation, and whether values reach behavior. Use when asked to "name a parameter", "parameter naming", "name this tool or command", "choose a flag, option, or config key", "design an options object", "one tool or two", "bool...

Use when the user asks to "test the marketplace plugins", "run marketplace tests", "check every installed plugin", or "/ar:marketplace-test". Walks the installed marketplace plugins, finds each one's test suite, runs them from the plugin's own directory, and reports per-plugin results.

Use when the user asks for the "system design philosophy", "design principles", "/ar:philosophy", or "/ar:ph", and before major feature work, an architecture decision, or a pull-request review. Lists the 17 universal system design principles, ordered from most fundamental to most specific, with concrete examples where a principle is easy to misread.

Use when the user asks to "make a plan", "plan this out", "/ar:plannew", or "/ar:pn", or starts multi-step work that needs tracked steps. Creates a structured plan with checkbox steps, the evidence each step must produce, and the wait process between them.

Use when the user asks to "execute the plan", "run the plan", "/ar:planprocess", or "/ar:pp". Executes an approved plan step by step with the wait process, task tracking, and verification before each completion claim.

Use when the user asks to "refine the plan", "critique the plan", "/ar:planrefine", or "/ar:pr". Critiques an existing plan against the actual code, records a change ledger, and iterates until a full pass finds no new material issue.

Use when the user asks to "update the plan", "sync the plan with the code", "/ar:planupdate", or "/ar:pu". Reconciles an existing plan with the current codebase and marks what already shipped.

Edit prose for brevity and scanability without losing facts. Use for requests to "revise", "rewrite", "edit", "polish", "clean up", "clarify", "simplify", "condense", "tighten", "shorten", "streamline", "de-fluff", remove bloat/repetition or unnecessary newlines, fix spelling/typos without changing meaning, make text concise/compact/skimmable, or finalize drafts, messages, notes, docs, reports, issues, or reviews. Activate for "too verbose", "very verbose", or "remove unnecessary newlines", a...

Use when the user asks to "list my claude sessions", "which windows are waiting", "/ar:tabs". Discovers Claude sessions across tmux windows and reports which need attention.

Use when the user asks to "continue every session", "send this to all windows", "/ar:tabw". Acts on Claude sessions across tmux windows; destructive to in-flight work, so it states what it will do before doing it.

This document is the "Source of Truth" for maintaining and debugging the clautorun hook system. It covers the architectural "Invisible Failures," strict schema requirements for Claude Code and Gemini CLI, and the mandatory synchronization workflow. ---

Search, recover, and analyze AI session histories across Claude Code, AI Studio, and Gemini CLI. Use when user asks to "find that file from last week", "search sessions", "recover context after compaction", "what did the AI do", "export session to markdown", "find corrections", "analyze session quality", "improve CLAUDE.md from past mistakes", or "turn AI mistakes into rules". Contains session search, file recovery, correction detection, self-improvement workflow.

Expertise in maintaining, debugging, and deploying the autorun hook system for Claude Code and Gemini CLI. Use when the user asks to "fix hooks", "deploy autorun", "debug hook errors", "update autorun version", or when troubleshooting "invisible failures" where safety guards appear inactive, piped commands are blocked, or work appears to have "reverted" after a session.

Use this skill when the user asks to "enable cache protection", "block on cache miss", "avoid cache expiration cost", "/ar:cache", "protect against compaction", "cache pressure guard", "cache hit ratio threshold", or "set cache-miss threshold". Covers the /ar:cache slash command family for blocking tool use when the Claude Code prompt cache is cold or context is near compaction.

(Renamed) Search, recover, and analyze sessions from Claude Code, AI Studio, and Gemini CLI — use /ar:ai-session-tools (this is an alias that redirects there).

Guides creation and improvement of Claude Code skills using Anthropic's official

Create demo videos for CLI and TUI tools. Use when user asks to "record a demo",

Render Mermaid diagrams to SVG using beautiful-mermaid and bun. Use when the user asks to "render mermaid", "generate diagram", "create flowchart", "update diagrams", "render SVG from mermaid", "beautiful-mermaid", "regenerate diagrams", or needs to convert Mermaid diagram syntax into styled SVG files. Supports all Mermaid diagram types with 15 themes including tokyo-night.

Systematically eliminate configuration bugs by testing 8-10 fundamentally different solutions in parallel. When root cause is ambiguous, this methodology finds the fix in hours instead of days through comprehensive parallel exploration. Build minimal test harness, evaluate all approaches simultaneously, identify winners, and understand WHY they work. Transforms guesswork into systematic discovery.

Complete CLI testing automation using tmux/byobu sessions with ai-monitor integration. Create automated workflows for testing plugins, CLIs, and terminal applications. Includes session management, keystroke control, output capture, and autonomous monitoring capabilities.

This skill should be used when the user asks to "extract text from PDF", "convert PDF to text", "parse PDF", "read PDF contents", "extract data from documents", "batch PDF extraction", "PDF to markdown", "OCR PDF", "get text from PDF files", "I have a PDF", "can you read this PDF", "what's in this PDF", "summarize this PDF", "open PDF file", "extract from [filename].pdf", or needs to process PDF documents for data extraction. Handles single-file extraction, batch processing, and OCR for scann...