Agent skill

ironbee-analyze

Run IronBee session analysis with semantic interpretation of verification metrics, issues, and fixes

View SKILL.md on GitHub Repository
Stars 136
Forks 3

Install this agent skill to your Project

npx add-skill https://github.com/ironbee-ai/ironbee-cli/tree/main/src/clients/cursor/commands/ironbee-analyze

SKILL.md

IronBee Session Analysis

Run ironbee analyze --json --detailed via terminal to get raw session metrics, then provide a semantic analysis.

Steps

  1. Run ironbee analyze --json --detailed (all sessions) or ironbee analyze <session-id> --json (specific session) via terminal
  2. Parse the JSON output
  3. Analyze and interpret the results:

Time Analysis

  • Is the coding:verification:fix ratio healthy? (High fix% = inefficient coding)
  • Is time to first verification reasonable? (Too long = agent coding without testing)

Verification Quality

  • What is the first-pass success rate? Why might it be low?
  • Are enough pages and checks being tested? (Low numbers = superficial testing)

Code Changes

  • Which files are hot files? Are they expected to change frequently?
  • Which files are problematic? What might be causing repeated fixes?
  • Is there edit churn? (Same file in multiple fix cycles = root cause not resolved)

Fix Effectiveness

  • Are fixes working? (Low fix success rate = agent not understanding the problem)
  • Is re-fail rate high? What patterns do you see in the issues?

Semantic Analysis (LLM-powered)

  • Group similar issues from verdict data into categories (e.g., "contrast issues", "event handler bugs", "API errors")
  • Identify recurring patterns across sessions
  • Suggest root causes for frequently failing files

Scoring

  • Interpret the efficiency, quality, and confidence scores
  • Compare with project averages if cross-session data is available

Output Format

Provide a structured report with:

  • Executive summary (1-2 sentences)
  • Key findings (bullet points)
  • Recommendations (actionable next steps)
  • Risk areas (files/patterns to watch)

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

ironbee-ai/ironbee-cli

ironbee-verify

Trigger browser verification of code changes. Args: (default), full, visual, functional

136 3
Explore
davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore
davila7/claude-code-templates

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

23,776 2,298
Explore
davila7/claude-code-templates

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

23,776 2,298
Explore
davila7/claude-code-templates

Claude Code Guide

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

23,776 2,298
Explore
davila7/claude-code-templates

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results