av
UserAgent skills for Claude Code, Codex, OpenCode & Cursor — autonomous orchestration, code quality, local LLMs (Harbor), and writing pipelines
Categories
Indexed Skills (25)
agent-integration-testing
Use when the user requests integration testing, feature validation, or test plan execution
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 architectural decay — over a specified duration
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, writer/cold-reviewer loop with an explicit ACCEPT/REVISE verdict contract, then a catalog-deslop pass with a regression gate. The orchestrator dispatches subagents only; the writer never judges its own draft. Use when the user says "article factory", "write an article about X", "run the article pipeline", or asks for a researched long-form piece produced end-to-end. For essays and micro posts in the user's own voice without a research stage, use the prose skill instead.
autoresearch
Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of karpathy/autoresearch. Use when the user says "autoresearch" (optionally with a focus, e.g. "autoresearch the optimizer"), asks to run experiments on a repo overnight, to hill-climb or optimize a metric autonomously, or points at a repo with a karpathy-style program.md.
boost-modules
Create custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.
bugbash
Systematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issues, and edge cases. Produces a structured report with full reproduction evidence (exact commands, inputs, logs, and tracebacks) for every issue.
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 fixes against repo constraints and target platforms. Runs end-to-end without user interaction.
catalog-deslop
Catalog-then-fix slop removal on an existing prose draft. Parallel catalog subagents inventory four slop categories (theatrics, overwrought register, corrective antithesis, dramatic short sentences), fix subagents repair only what a catalog names, mechanical lint + frequency analysis bracket the run, and a regression gate (lint delta, word count, cold meaning check) decides whether the result ships. Use when the user says "deslop this draft", "catalog deslop", "strip the AI patterns from this file", or as the final stage of the article-factory and mosaic-writing skills. For writing or redrafting prose from scratch, use the prose skill instead - this skill only repairs an existing draft in place.
discipline
Bulletproof agent operating protocol. 15 failure-prevention rules distilled from 120+ real sessions and 10 agent definitions. Covers fabrication, constraint tracking, verification, scoping, retry discipline, and communication. Load before any task to prevent the most common agent failure modes.
factual-communication
Restate content as a flat list of atomic facts in the style of av/facts fact sheets. Use when the user says "just facts", "facts only", "as facts", "give me the facts", or replies with a bare "facts" / "facts?" to a previous message — then the scope is that message's content.
ideate
Timeboxed ideation on a topic using propose-and-critique subagent pairs. Use when the user wants to brainstorm, explore ideas, discover features, generate options, or think through possibilities for a specified duration. Triggers on requests like "brainstorm X for 30 minutes", "ideate on X", "spend an hour thinking about X", "what features should we build", "explore options for X".
make-video
Build a HyperFrames video composition from a brief/script autonomously. Uses separated builder and critic subagents — builders never review their own work. Quality decisions are grounded in project context (identity, audience, goals) and established visual/motion design principles. Measurable criteria (text size, contrast, overflow) are verified with tooling, not visual judgment. Use when the user says "make this video", "implement this brief", "build this composition", or provides a video script/brief to implement.
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 a polish loop (polisher + cold reviewer), then frequency analysis and a catalog-deslop pass with a regression gate. Two modes with opposite fidelity contracts - stitch mode preserves the author's exact wording, narrative mode preserves every idea but may rewrite freely. Use when the user says "mosaic", "assemble my fragments", "stitch these notes into a post", or provides a fragments file to turn into a finished piece. For writing from a topic with research, use article-factory; for prose from scratch, use the prose skill.
preact-buildless-frontend
Build-less ESM frontends that run directly in the browser without bundlers. Use this skill when creating static frontends, SPAs without build tools, prototypes, or when the user explicitly wants no Vite/Webpack/bundler. Covers import maps, CDN imports, cache-busting, hash routing, and performance patterns.
run-llms
Set up and run local LLMs with Harbor. Use when the user wants to run models locally, install Harbor, start Open WebUI, llama.cpp, Ollama, vLLM, Docker Model Runner, MLX, or oMLX, pull GGUF or HuggingFace models, add SearXNG web search, Speaches TTS/STT, or Open Terminal code execution, launch Codex/Claude/Grok/OpenCode against a Harbor backend, or troubleshoot GPU, VRAM, and service startup.
sandcastle
Orchestrate AI coding agents (Claude Code, Codex, OpenCode) in isolated sandboxes using the @ai-hero/sandcastle SDK. Use when the user needs to (1) run agents AFK in Docker/Podman containers, (2) build multi-agent pipelines with plan-execute-review patterns, (3) run parallel agents on separate worktrees, (4) create iterative agent loops with maxIterations, (5) extract structured output from agent runs, (6) set up sandcastle in a new or existing project, or (7) write prompt files with template args and shell expressions.
superclaude
Configure and operate the Claude Code harness for large codebases. Builds CLAUDE.md hierarchies, scoped test/lint commands, file exclusions, codebase maps, hooks, skills, subagent strategies, and LSP/MCP wiring. Use when setting up Claude Code for a new repo, auditing an existing configuration, onboarding a team, or scaling from single-developer to org-wide deployment. Triggers on "set up Claude Code for this repo", "optimize my Claude Code config", "audit my CLAUDE.md", "make this codebase navigable", "configure hooks/skills/plugins".
timeboxed-iterating
Run a task iteratively over a user-specified duration by dispatching subagents. The orchestrator stays strictly linear and time-checked, but each iteration fans out MULTIPLE subagents in parallel over independent units (and those subagents may fan out further). Shared state — a compact progress digest and a growing environment cheatsheet — lives on disk and is passed to every subagent BY REFERENCE, killing the per-subagent rediscovery tax. Every subagent first reads an initialiser preamble that points it at that shared state and makes it write findings back, so the cheatsheet populates itself; role prompts are produced ONCE on the filesystem by a single scaffold command and dispatched by path, never re-typed per dispatch. Subagents persist their results to disk and return only a tiny status, so the orchestrator's context stays small and lasts. The orchestrator classifies the goal as FINITE or OPEN-ENDED: finite lists may finish early; open-ended goals use the full duration, never idle, never manufacture busyw
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 a target file. Use when the user asks for a dossier, timeline, chronology, release history, or month-by-month research bounded by specific years or months. Not for timeless explainers or single-document summaries with no temporal scope.
tinygrad
Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and multi-device support. Use when writing neural networks, training models, implementing tensor operations, working with UOps/PatternMatcher for graph transformations, or contributing to tinygrad internals. Triggers on tinygrad imports, Tensor operations, nn modules, optimizer usage, schedule/codegen work, or device backends.
turso-db
Install, configure, and work with Turso DB — an in-process SQLite-compatible relational database engine written in Rust. Use when the user needs to (1) install Turso DB, (2) create or query databases with the tursodb CLI shell, (3) use Turso from JavaScript/Node.js via @tursodatabase/database, (4) work with vector search or embeddings in Turso, (5) set up full-text search with FTS indexes, (6) configure transactions including MVCC concurrent transactions, (7) enable encryption at rest, or (8) use Change Data Capture (CDC) for audit logging.
use-coding-agents
How to use the coding agents installed on this machine (claude, codex, droid, grok, hermes, opencode, copilot, pi) as plain sub-agents in orchestrated workflows: one headless invocation, one prompt in, one result out. Deliberately ignores each CLI's own orchestration features (droid --mission, codex multi_agent, hermes delegation/moa/kanban, grok --agents, opencode personas). The orchestrator is whatever session is running the skill; the CLIs are interchangeable workers. Use when the user asks "which agent should run this", "fan out workers", "run X headless", or when a lifeos skill (overnight, timeboxed-iterating, workgraph, gauntlet, bughunt, dark-factory) needs to launch an agent CLI.
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). Use when the user says "workgraph", "run this as a graph", "graph this work", or when a goal has parallel branches, feedback loops, or mixed gate types that a linear loop cannot express. For chain-shaped work use timeboxed-iterating, autoresearch, or dark-factory instead.
workmachine
Run work as an explicit event-driven state machine executed by subagents. The orchestrator is the runtime from the canonical loop — `state, effects = init(machine); execute(effects); while state is active: event = nextEvent(); state, effects = transition(machine, state, event); execute(effects); return state.output`. All routing judgment is authored ONCE, at plan time, into a machine file (states, event alphabet, transition table, budgets, final states); at runtime the orchestrator does pure table lookups and dispatches effects — it never decides, never authors, never ingests artifacts. Subagent/sync protocol is the timeboxed-iterating one: role prompts scaffolded once to disk and dispatched BY PATH, an initialiser preamble every subagent reads first, a self-populating cheatsheet, per-unit files, tiny structured returns, independent measurement gate. Use when the user says "workmachine", "run this as a state machine", "state-machine this", or when a goal has a small number of clearly named phases with explici
pull-llamacpp-model
Use when pulling or downloading a new llamacpp model. The active ROCm image (kyuz0/amd-strix-halo-toolboxes) fails to start in the ephemeral pull container without ROCm device access. Must temporarily switch to the standard CPU image.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.