av/skills

1

bugbash Systematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issue…

av/skills

19

2

timeboxed-iterating Use when the user specifies a task and a duration, and the work should be done iteratively by subagents over that tim…

av/skills

19

3

tinygrad Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and mult…

av/skills

19

4

run-llms Comprehensive guide for setting up and running local LLMs using Harbor. Use when user wants to run LLMs locally, set …

av/skills

18

5

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

av/skills

15

6

preact-buildless-frontend Build-less ESM frontends that run directly in the browser without bundlers. Use this skill when creating static front…

av/skills

13

7

anneal Use when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallow…

av/skills

12

8

bughunt Fully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage…

av/skills

12

9

discipline Bulletproof agent operating protocol. 15 failure-prevention rules distilled from 120+ real sessions and 10 agent defi…

av/skills

12

10

ideate Timeboxed ideation on a topic using propose-and-critique subagent pairs. Use when the user wants to brainstorm, explo…

av/skills

12

11

boost-modules Create custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use …

av/skills

8

12

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

av/skills

8

13

workgraph Orchestrate work as a cyclic directed graph of subagent-executed nodes with transition criteria on edges, budgeted cy…

av/skills

4

14

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

av/skills

3

15

use-coding-agents How to use the coding agents installed on this machine (claude, codex, droid, grok, hermes, opencode, copilot, pi) as…

av/skills

3

16

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 fac…

av/skills

2

17

make-video Build a HyperFrames video composition from a brief/script autonomously. Uses separated builder and critic subagents —…

av/skills

2

18

pull-llamacpp-model Use when pulling or downloading a new llamacpp model. The active ROCm image (kyuz0/amd-strix-halo-toolboxes) fails to…

av/skills

2

19

mosaic-writing Assemble a finished piece from human-written fragments via an orchestrated two-loop pipeline - an assembly loop (asse…

av/skills

1