Results for “claude-artifact”

5 skills

denissergeevitch

repo-task-proof-loop

Provides a repeatable, auditable workflow for large coding tasks by initializing repo-local task artifacts, installing subagent templates, and running a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.

More results

chrome-mcp-troubleshooting

Diagnose and fix connectivity issues with the Claude in Chrome MCP extension, including native host conflicts between Claude.app and Claude Code CLI.

A collection of 800 curated Claude Code skills covering Azure SDK, engineering, language specialists, product, testing, security, DevOps, ML, and creative workflows.

Sets up Claude Code for a project by analyzing the tech stack, installing relevant skills from skills.sh, generating custom skills, and configuring MCP servers.

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in...