GitHub collection

ahundt/autorun

Imported from GitHub — is this yours?

19 skills imported from this repository.

Claude Skill

autorun-maintainer

Expertise in maintaining, debugging, and deploying the autorun hook system across Claude Code, Codex CLI, Gemini-family CLIs, Google Antigravity, Qwen Code, ForgeCode, custom harnesses, and desktop app integrations. Use when the user asks to "fix hooks", "deploy autorun", "debug

LLM Mart

Claude Skill ar

ar

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.

LLM Mart

Claude Skill ar

ai-skill-builder

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

LLM Mart

Claude Skill ar

cache

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

LLM Mart

Claude Skill ar

commit

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 jarg

LLM Mart

Claude Skill ar

function-signature-and-parameter-guidance

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, mutatio

LLM Mart

Claude Skill ar

marketplace-test

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 re

LLM Mart

Claude Skill ar

mermaid-diagrams

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

LLM Mart

Claude Skill ar

parallel-subagent

Eliminate a stubborn configuration bug by testing 8-10 fundamentally different fixes in parallel instead of one at a time. Use when the root cause is ambiguous and asked to "fix this stubborn bug", "we've tried everything", "run approaches in parallel", "use parallel subagents",

LLM Mart

Claude Skill ar

philosophy

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

LLM Mart

Claude Skill ar

plannew

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.

LLM Mart

Claude Skill ar

planprocess

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.

LLM Mart

Claude Skill ar

planrefine

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.

LLM Mart

Claude Skill ar

planupdate

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.

LLM Mart

Claude Skill ar

streamline-text

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/typ

LLM Mart

Claude Skill ar

tabs

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.

LLM Mart

Claude Skill ar

tabw

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.

LLM Mart

Claude Skill ar

tmux-automation

Drive CLI tests inside isolated tmux/byobu sessions with ai-monitor integration. Use when asked to "test this CLI", "run it in tmux", "automate a terminal session", "capture the output of an interactive command", "send keystrokes to a session", or to exercise a plugin or terminal

LLM Mart

Claude Skill pdf-extractor

pdf-extractor

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

LLM Mart

Commands (58)

  • /a — Allow all file creation (short for /ar:allow) source
  • /afa — Set AutoFile policy to allow-all mode (full file creation permissions) source
  • /afj — Set AutoFile policy to justify-create mode (require justification for new files) source
  • /afs — Set AutoFile policy to strict-search mode (only modify existing files) source
  • /afst — Show current AutoFile policy and settings source
  • /allow — Allow all file creation - full permission to create and modify files source
  • /ar-allow — Set AutoFile policy to ALLOW — permit creation of new files without justification source
  • /ar-commit — Refresh git commit guidelines before staging changes source
  • /ar-find — Set AutoFile policy to FIND — restrict edits to existing files only source
  • /ar-go — Start an autorun task with three-stage verification (initial → critical review → final verification) source
  • /ar-ph — Refresh the universal system design philosophy before designing or reviewing code source
  • /ar-st — Show the current AutoFile policy and any active autorun state source
  • /autoproc — Start autoproc - procedural autonomous workflow (legacy command) source
  • /autorun — Start autorun - autonomous task execution (legacy command) source
  • /blocks — Show active session-level pattern blocks and allows source
  • /cache — Cache-miss / compaction protection gate (disabled by default) source
  • /claude-code-plugin-help — Reference the supported Claude Code command, skill, plugin, and hook surfaces source
  • /clear — Clear all session-level pattern blocks and allows source
  • /estop — Emergency stop - immediately halt all autonomous operations source
  • /extract — Extract text from PDF files or directories to markdown source
  • /f — Find existing files only - no new file creation (short for /ar:find) source
  • /find — Find existing files only - prevents new file creation (strictest mode) source
  • /gc — Git commit requirements - the 17-step process, short for /ar:commit source
  • /gemini — Use gemini CLI for any combination of: superior vision for analysis of images, diagrams, screenshots, PDFs, documents, video, and audio; code review with detailed citations and cross-referencing patterns; Google search; and multi-model workflows; all for planning, feedback, and getting unstuck. source
  • /globalclear — Clear all global pattern blocks and allows source
  • /globalno — Block a command pattern globally (persists across sessions) source
  • /globalok — Allow a blocked pattern globally (persists across sessions) source
  • /globalstatus — Show active global pattern blocks and allows source
  • /go — Start autorun - autonomous task execution (short for /ar:run) source
  • /gp — Start autoproc - procedural autonomous workflow (short for /ar:proc) source
  • /help — List every autorun command with what it does, in this harness's spelling source
  • /j — Require justification for new files (short for /ar:justify) source
  • /justify — Require justification before creating new files source
  • /no — Block a command pattern in this session source
  • /ok — Allow a blocked pattern in this session source
  • /pe — Plan export status and settings [on|off|globalon|globaloff|dir <path>|pattern <template>|rejected [on|off|dir <path>]|reset] source
  • /ph — Universal System Design Philosophy - the 17 core principles, short for /ar:philosophy source
  • /planexport — Plan export status and settings [on|off|globalon|globaloff|dir <path>|pattern <template>|rejected [on|off|dir <path>]|reset] source
  • /pn — Create a structured plan, short for /ar:plannew source
  • /pp — Execute an approved plan step by step, short for /ar:planprocess source
  • /pr — Critique and improve an existing plan, short for /ar:planrefine source
  • /proc — Start autoproc - procedural autonomous workflow source
  • /pu — Sync an existing plan with the codebase, short for /ar:planupdate source
  • /reload — Force-reload all integration rules from config files source
  • /restart-daemon — Restart the daemon for the current autorun install/source tree source
  • /run — Start autorun - autonomous task execution source
  • /sos — Emergency stop - immediately halt all actions (short for /ar:estop) source
  • /st — Show current AutoFile policy status (short for /ar:status) source
  • /status — Show current AutoFile policy and settings source
  • /stop — Graceful stop - finish current task then stop autorun source
  • /task — Inspect tasks or configure pause, prompts, recovery, and ignore behavior source
  • /tasks — Plural alias for task status, pause, prompts, recovery, and ignore source
  • /test — Verify that the autorun plugin command surface is loaded source
  • /tm — Tmux session management - create, list, cleanup isolated sessions, short for /ar:tmux source
  • /tmux — Tmux session management - create, list, cleanup isolated sessions source
  • /tt — CLI testing in isolated tmux sessions, short for /ar:ttest source
  • /ttest — CLI testing in isolated tmux sessions source
  • /x — Graceful stop - finish current task then stop (short for /ar:stop) source