SkillsAdd

zereight/skill · Archived

harness

Pi-native evaluate→improve→persist harness. Provides a systematic loop for generating candidates, judging them against rubrics, and accumulating knowledge as playbooks. Use for iterative output improvement, not for one-off edits (use continuity) or single PR review (use zereight-review).

First seen Jun 23, 2026

Installation

$ npx skills add zereight/skill --skill harness
View on skills.sh ↗ GitHub repository ↗

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

zereight-review Same source · more installs
zereight/skill

zereight-review — an installable skill for AI agents, published by zereight/skill.

11 installs
zereight-react-native-optimizer Same source · more installs
zereight/skill

React Native performance review checklist for code reviews. Use when reviewing RN code to detec…

11 installs
zereight-react-native Same source · more installs
zereight/skill

Gateway skill for React Native development. Routes tasks to the right specialist skill — basics…

10 installs
zereight-react-native-testing Same source · more installs
zereight/skill

Write tests using React Native Testing Library (RNTL) v13/v14. Covers render, screen, queries, …

7 installs

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

browser-harness Similar name
browser-use/browser-harness

Control a real browser via CDP: clicking, typing, navigation, logged-in sessions, JS-rendered o…

8 installs
eval-harness Similar name
affaan-m/ecc

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD)…

9.2K installs
healthcare-eval-harness Similar name
affaan-m/ecc

Patient safety evaluation harness for healthcare application deployments.

7.1K installs
gan-style-harness Similar name
affaan-m/ecc

GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomou…

7K installs
harness-writing Similar name
trailofbits/skills

Designs and improves fuzzing harnesses for C/C++ and Rust. Covers mapping raw bytes onto a targ…

4.6K installs
harness-creator Similar name
walkinglabs/learn-harness-engineering

>- Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md…

2K installs

Also in this package

Other skills from zereight/skill · top by installs.

npx skills add zereight/skill
zereight-review 11 zereight-react-native-optimizer 11 zereight-react-native 10 zereight-react-native-testing 7 zereight-learning 2 mcporter-mcp-first 2 ljg-push 2 zereight-goal 1 ljg-writes 1 ljg-word-flow 1

Browse all from zereight/skill

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,034 B
  • docs SUMMARY.md 307 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

harness (Pi-native evaluation loop)

Builds on autoctx (judge/improve core) + Pi tools to provide a coherent harness.

Stack

Layer Source Role
Extension ~/.pi/agent/extensions/harness/index.ts Tools + TUI + lifecycle
Judge engine autoctx (via pi-autocontext dep) LLM-based evaluation
Skill .agents/skills/harness/SKILL.md Usage guide + routing

Tools

Tool Description
harness_solve Full loop: generate → judge → improve → persist playbook
harness_knowledge Read/write/list playbooks (knowledge/<scenario>/playbook.md)
harness_status Recent runs, scores, and scenarios overview

Usage

# Solve a task with rubric-driven improvement
goal: "Improve zereight-review checklist for RN PRs"
rubric: "Actionable findings, Effect anti-patterns, security when relevant"
→ Best output + playbook saved to knowledge/<scenario>/

# Check previous runs
→ Recent runs with scores and scenarios

# Browse accumulated knowledge
action: list → all scenarios with playbooks
action: read, scenario: zereight-review → full playbook

When to use

Need Use
Systematic output improvement harness_solve
Review accumulated lessons harness_knowledge read
Check past run history harness_status
One-off judge/improve autocontextjudge / autocontextimprove (pi-autocontext)

Cost

  • harness_solve consumes Pi provider quota per generation round.
  • Start with gens: 1 to calibrate rubric, then increase.
  • harnessknowledge and harnessstatus are zero-cost.