query-result-cap

Flags accessibility misses as Claude writes UI: images without alt, unlabeled buttons, clickable divs.

Unlock achievements as you work: first commit, 100 green test runs, a week-long streak and more.

A heat map of when you use Claude Code, by hour and weekday.

Ready-made subagents for focused jobs: debugger, test writer, doc writer and migrator.

Writes every action Claude takes to an append-only JSONL audit log.

Snapshots your work tree before every editing turn and lets you /rollback to any checkpoint.

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

The official CCXT MCP server plus the ccxt-mcp usage skill — market data, balances and opt-in trading across 100+ crypto exchanges and prediction markets, with keys kept local.

1 MCP server

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents