av/skills

A library of agent skills by @av for Claude Code, Codex, OpenCode, Cursor and other coding agents — autonomous orchestration, code quality, local LLMs, and writing pipelines.

Install

npx skills add av/skills --skill <name>

Skills are plain folders containing a SKILL.md, so you can also just copy one into .claude/skills/ (or your agent's equivalent) by hand.

Skills

26 skills. Install any of them with npx skills add av/skills --skill <name>.

Orchestration & autonomous work

 workgraph — Orchestrate work as a cyclic directed graph of subagent-executed nodes with transition criteria on edges, budgeted cycles, and per-node gates (runtime verification, metric, or artifact).

 workmachine — Run work as an explicit event-driven state machine executed by subagents.

 timeboxed-iterating — Run a task iteratively over a user-specified duration by dispatching subagents.

 use-coding-agents — How to use the coding agents installed on this machine (claude, codex, droid, grok, vktr, hermes, opencode, copilot, pi) as plain sub-agents in orchestrated workflows: one headless…

 sandcastle — Orchestrate AI coding agents (Claude Code, Codex, OpenCode) in isolated sandboxes using the @ai-hero/sandcastle SDK.

 autoresearch — Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of karpathy/autoresearch.

 ideate — Timeboxed ideation on a topic where lens-driven proposers generate structurally different ideas, blind critics cull them, and pairwise judges rank the survivors on a tournament ladder…

Code quality & testing

 anneal — Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced…

 bugbash — Systematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issues, and edge cases.

 bughunt — Fully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage each finding, fix confirmed issues with subagents, then audit all…

 agent-integration-testing — Use when the user requests integration testing, feature validation, or test plan execution

Writing & research

 article-factory — Produce a researched long-form article from a topic prompt via an orchestrated pipeline - research agent (first-person sources, working-definition gate), narrative-architecture outline,…

 mosaic-writing — Assemble a finished piece from human-written fragments via an orchestrated two-loop pipeline - an assembly loop (assembler + cold reviewer) that sequences the fragments into a draft, then…

 catalog-deslop — Catalog-then-fix slop removal on an existing prose draft.

 factual-communication — Restate content as a flat list of atomic facts in the style of av/facts fact sheets.

 timeframe-research — Build a timeframe-bounded research dossier by decomposing a topic into year orchestrators and month-level research passes that each write one condensed paragraph plus sources directly into…

 make-video — Build a HyperFrames video composition from a brief/script autonomously.

Local LLMs

 run-llms — Set up and run local LLMs with Harbor.

 pull-llamacpp-model — Use when pulling or downloading a new llamacpp model.

 boost-modules — Create custom modules for Harbor Boost, an optimizing LLM proxy.

Agent craft

 discipline — Bulletproof agent operating protocol.

 improve-skill — Improve an existing agent SKILL.md through one gated cycle: select the target (default this skill), snapshot the committed baseline, diagnose against skill-design-principles plus four…

 superclaude — Configure and operate the Claude Code harness for large codebases.

Frameworks & tools

 preact-buildless-frontend — Build-less ESM frontends that run directly in the browser without bundlers.

 tinygrad — Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and multi-device support.

 turso-db — Install, configure, and work with Turso DB — an in-process SQLite-compatible relational database engine written in Rust.