fernandoxavier02

Self Eval

Name: Self Eval
Author: fernandoxavier02

Data community

SOURCE https://github.com/fernandoxavier02/Pipeline-Orchestrator/blob/main/commands/self-eval.md

Description

--- description: "Self-improvement loop. After a pipeline run, reviews how faithfully it executed step-by-step (from the deterministic e2e-eval), then for each execution glitch PROPOSES a fix — nothing is applied without your approval (approve → fix, reject → record). Accumulates a cross-run evaluation dataset to improve the agents and the plugin over time. The Stop hook auto-invokes this when a run closes with glitches; you can also run it manually for the latest run." allowed-tools: Task, Read

Installation

Installs to ~/.claude/skills/fernandoxavier02-pipeline-orchestrator-self-eval/SKILL.md

Terminal

mkdir -p ~/.claude/skills/fernandoxavier02-pipeline-orchestrator-self-eval && curl -fsSL https://raw.githubusercontent.com/fernandoxavier02/Pipeline-Orchestrator/HEAD/commands/self-eval.md -o ~/.claude/skills/fernandoxavier02-pipeline-orchestrator-self-eval/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.