/self-eval

Run post-output self-evaluation scoring on correctness, clarity, actionability, and conciseness

Boost this command

coco-research@coco-research

GitHub

From plugin

coco

38641 skills53 agents41 commands

Install

$ npx -y skills add coco-research/coco --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/self-eval

Context preview

What this command does when you run it.

Run post-output self-evaluation scoring on correctness, clarity, actionability, and conciseness

Command definition

self-eval.md

description: "Run post-output self-evaluation scoring on correctness, clarity, actionability, and conciseness"
allowed-tools:
  - Read
  - Bash
  - Glob
  - Grep

/self-eval — Agent Output Quality Scoring

Evaluate the most recent agent output or deliverable across four quality axes.

Usage

/self-eval              # Evaluate last output in current session
/self-eval --file <path>  # Evaluate specific file/deliverable
/self-eval --team         # Evaluate last /team pipeline output

What It Does

1. Collects original request + final output + verification evidence 2. Scores each axis (correctness, clarity, actionability, conciseness) 1-5 3. Generates improvement instincts for the learning system 4. Flags scores ≤2 on correctness for automatic re-execution offer

When to Run

After any `/team:*` command completes
After `/gsd-execute-phase` finishes
When user asks "how did that go?" or "evaluate this"
Before marking a phase as complete in GSD workflows

Read it on GitHub ↗

Ships withcoco

CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 226 skills, 386 commands, persistent state. Local. Open-core — MIT core; Super Intelligence is proprietary, own-use.

Get the whole plugin

Stats

JavaScript React HTML CSS Bash

+7 tags

Rust C#Git GitHub Anthropic OpenAI MCP

287

Stars

Forks

Active

Maintenance

HTML

Language