Overview
agent-evaluation-reporting is an open-source workflow skill for Claude Code and compatible agents, published by sickn33. Its author describes it as: “Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.”. The project has 47k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add sickn33/agentic-awesome-skills`.
What agent-evaluation-reporting does
Turn raw agent evaluation runs into a decision-ready report without hiding failures or overstating capability. Keep outcome populations, denominators, latency populations, and experiment conditions explicit so readers can reproduce every headline number.
What’s inside
The SKILL.md for agent-evaluation-reporting is organised into these sections:
- Overview
- When to Use This Skill
- How It Works
- Step 1: Freeze the comparison contract
- Step 2: Build a mutually exclusive outcome ledger
- Step 3: Lock each metric to a denominator
- Step 4: Keep latency and cost populations honest
- Step 5: Quantify uncertainty and comparability
- Step 6: Map evidence to predeclared decision gates
- Example
- Best Practices
- Limitations
Installation
Add agent-evaluation-reporting to your agent with:
/plugin marketplace add sickn33/agentic-awesome-skillsReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — ships a claude code plugin marketplace
- Codex — declared in the repository topics
- Cursor — declared in the repository topics
- Antigravity — declared in the repository topics
License
agent-evaluation-reporting is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in sickn33/agentic-awesome-skills, an established project with 46,693 GitHub stars
- Works with Claude Code, Codex, Cursor, Antigravity
- Actively maintained — repository updated in the last 30 days
- Its repository gained 1,598 GitHub stars over the last 34 days
Author
Topics
Frequently asked questions
- What does agent-evaluation-reporting do?
- Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
- How do I install agent-evaluation-reporting?
- Run /plugin marketplace add sickn33/agentic-awesome-skills in your agent, then reload your skills. Review the source at https://github.com/sickn33/agentic-awesome-skills before installing.
- Is agent-evaluation-reporting free to use?
- Yes. agent-evaluation-reporting is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does agent-evaluation-reporting work with?
- agent-evaluation-reporting lists Claude Code, Codex, Cursor, and Antigravity — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does agent-evaluation-reporting come from?
- agent-evaluation-reporting ships inside sickn33/agentic-awesome-skills, a repository that contains 70 catalogued skills in total. The repository's 46,693 GitHub stars apply to that whole collection, not to this skill on its own.