MadAppGang

Use when starting isolated feature work or before executing implementation plans. Manages full worktree lifecycle from creation through cleanup with safety checks and error recovery.

Configuration reference and troubleshooting for the statusline plugin — sections, themes, bar widths, and script architecture

Common agent patterns and templates for Claude Code. Use when implementing agents to follow proven patterns for Tasks integration, quality checks, and external model invocation via claudish CLI.

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI…

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI…

Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities. Use when conducting design reviews, accessibility audits, or design system validation.

Use when deciding whether to launch an agent, selecting which agent to use, or coordinating multiple agents. Covers delegation criteria, external-model patterns, task isolation, and agent selection strategies.

Use when debugging failures, errors, or unexpected behavior. Covers root cause investigation, data flow tracing, hypothesis-driven debugging, and fix verification to prevent trial-and-error approaches.

Authors, runs and debugs madbench benches natively — bench YAML, checks, metrics with module/, red-state testdata, the two controls, exit codes; drafts an upstream issue instead of a wrapper. Use when writing, reviewing or debugging any bench.

Creates, runs, debugs and migrates madbench benches. Checks the installed madbench against these skills first, then routes the request. Use when the user types /madbench or asks to create, run, fix or migrate a bench.

Brings a madbench Bench or Experiment written for madbench v0.41.0 or later to the installed madbench, applying the changes `changes.md` records between the two versions. Use when a bench no longer loads after an upgrade.

Runs models through the claudish MCP tools — team, create_session, run_prompt — and resolves model IDs against the live catalog. Use when the user mentions claudish, OpenRouter, or external AI models.

Runs a multi-model review gate to a verdict: start the claudish team panel with input_file only, poll until settled, read every ballot, apply the minimum ballot count, log every skip. Use at any plan-review, code-review, verify or fix gate.

Runs the same task across multiple AI models in parallel and aggregates verdicts. Use when the user wants a second opinion, multi-expert validation, or consensus from Grok, Gemini, GPT, or Kimi.

Merges independent reviews of one target into one report with a consensus tag per finding and a verdict from supplied thresholds; also synthesises research findings. Use when several reviews or votes must become one file a gate reads.

Creates, uses and cleans up git worktrees with safety checks. Use before isolated, risky or parallel feature work, or on mention of worktree, experiment or prototype.

Reference for generating and editing images across Google, OpenAI and ByteDance through one CLI. Use when generating or editing images, picking an image model, or resolving an image API key or provider error.

Final Cut Pro FCPXML reference — project structure, timelines, clip references, effects, transitions. Use when generating or reading FCP projects.

Provides Whisper transcription patterns — model selection, SRT/VTT/JSON, timing sync, diarization. Use when transcribing audio or video, or generating subtitles.

Provides FFmpeg patterns — trim, concat, convert, extract, codec selection, filter chains. Use when planning or executing video or audio processing tasks.

Release one or more Magus plugins. Infers the version bump from git history, bumps plugin.json and marketplace.json, commits, and after the PR merges tags the merge commit with one explicit ref per tag; CI gates the PR and publishes the dist repos. Use…

Specifies the markdown format of image style templates in styles/. Use when creating, updating or validating a style file, or when the user mentions style templates, art direction, or a reusable look.

Writes and reviews SKILL.md files for this repo — a description that triggers, a body that fits, and a visibility choice that does not starve a preload consumer. Use when adding, editing or auditing any skill. Not for commands or agents.

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI…

Runs models through the claudish MCP tools — team, create_session, run_prompt — and resolves model IDs against the live catalog. Use when the user mentions claudish, OpenRouter, or external AI models.

How to load secrets and environment variables from 1Password programmatically using the official @1password/sdk (JavaScript/TypeScript). Use this skill whenever code needs to read a 1Password secret, resolve an op:// reference, fetch many secrets at once,…

Write GitHub PR comments in Jack's voice. Use whenever writing, drafting, or posting PR comments — review feedback, thank-you notes, merge comments, close explanations, or change requests. Also use when the user asks to "comment on PR", "review PR", "thank…

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI…

Automated LSP hover validation for Dingo transpiler. Use when testing hover functionality, validating position mappings, checking for hover drift, or debugging LSP issues after sourcemap changes.

Choose optimal external AI models for code analysis, bug investigation, and architectural decisions. Use when consulting multiple LLMs via claudish, comparing model perspectives, or investigating complex Go/LSP/transpiler issues. Provides empirically…

Write a structured experiment journal article after completing an experiment iteration. Use this skill whenever the user finishes running an experiment, wants to document results, says 'write journal', 'document this experiment', 'save experiment results',…

Render beautiful terminal tables, bar charts, and leaderboards for experiment results using tools/table.ts. Use when the user asks to display data, render a table, show results, create a leaderboard, make a chart, visualize experiment output, or print…

AgentBench evaluation harness for claudemem. Covers pre-indexed repos, experiment conditions, running benchmarks, analyzing results, and managing index archives. Use when working on eval infrastructure, running experiments, or interpreting benchmark results.

Drive tmux from the command line to manage terminal sessions, windows, and panes — split the current pane, run a command in a new pane, capture output, send keystrokes, resize/navigate panes, or spin up a fully isolated background tmux server for sandboxed…

Write a structured experiment journal article after completing an experiment iteration. Use this skill whenever the user finishes running an experiment, wants to document results, says 'write journal', 'document this experiment', 'save experiment results',…