Oberskills provides advanced agent orchestration for Claude Code, enabling operations teams to debug workflows and plan tasks. It infers symptoms, dispatches agents for logs/code, synthesizes evidence, and proposes root causes. Integrates with Claude agents for enhanced automation.
git clone https://github.com/ryanthedev/oberskills.gitOberskills is a skill suite built to improve Claude Code's performance in prompt engineering, agent orchestration, and skill development. It includes five core skills: prompt (adversarial auditing and design with cited principles), agent (dispatch guidance and delegation contracts), skill-craft (end-to-end skill creation with evaluation gates), write (AI-detection resistant prose in edit or review modes), and web-research (parallel search with verified source URLs). The suite bundles a Bun/TypeScript MCP server for skill evaluation, running live Claude sessions to validate structure, test triggers, measure description quality, and grade evaluations. Teams automate workflow debugging, task planning, and agent coordination while maintaining quality gates throughout the development pipeline.
Install via /plugin marketplace add ryanthedev/rtd-claude-inn, then /plugin install oberskills@rtd. Run /reload-plugins to activate the skill-eval MCP server. Optionally allow mcp__plugin_oberskills_skill-eval__* in settings to skip permission prompts.
Adversarially audit and refine prompts for Claude agents with structured verdicts
Dispatch subagents with cost gates, delegation contracts, and debiased verification
Create and evaluate Claude Code skills with automated validation and benchmarking
Conduct web research across multiple dimensions with synthesized, sourced results
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/ryanthedev/oberskillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
I'm debugging a workflow for [COMPANY] in the [INDUSTRY] sector. The issue is [DESCRIBE SYMPTOM]. I need your help to: 1) Infer the root cause, 2) Identify the relevant logs/code to examine, and 3) Propose a solution. Use Oberskills to orchestrate agents for this task.
# Debugging Workflow Analysis ## Symptom Inference Based on your description, the workflow is failing during the data processing stage, likely due to incorrect data formatting. ## Recommended Agents 1. **Log Agent**: Retrieve logs from the data processing module (last 24 hours). 2. **Code Agent**: Fetch the data validation script (version 1.3.2). ## Evidence Synthesis The logs show multiple 'InvalidFormat' errors. The code agent reveals the script expects CSV format but receives JSON data. ## Root Cause Proposal The root cause is a mismatch between the expected data format (CSV) and the actual input (JSON). This discrepancy occurs because the upstream data source was recently updated without modifying the validation script.
AI assistant built for thoughtful, nuanced conversation
IronCalc is a spreadsheet engine and ecosystem
ITIL-aligned IT service management platform
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan