Liu39924

Skill Conductor — Testing skill for Claude Code

Testing community

Architecture-first skill lifecycle for AI agents.

How to install Skill Conductor

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Liu39924/skill-conductor and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Skill Conductor does

Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.

Alternatives in Testing

Flow Spec — NLSpec authoring — use when you need a structured specification from multi-AI research and consensus 2.8k ★
Grill — Sharpen a fuzzy idea into §G/§C before spec 1.1k ★
Robotics Agent Skills — Agent skills that make AI coding assistants write production-grade robotics software 170 ★

README

Skill Conductor

A skill that creates, evaluates, and improves other skills. Meta-level.

[![Release](https://img.shields.io/github/v/release/smixs/skill-conductor)](https://github.com/smixs/skill-conductor/releases) [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE) [![Install](https://img.shields.io/badge/install-npx%20skills%20add-black)](https://skills.sh) [![Claude Code](https://img.shields.io/badge/Claude%20Code-plugin-d97757)](https://code.claude.com/docs/en/plugins)

Architecture-first skill lifecycle: **design → build → test → evaluate → package**.

Most skill tools jump straight to "write SKILL.md." Conductor makes you choose the architecture first — because rewriting a wrong pattern costs more than writing it right.

Install

# skills.sh — installs into ~/.claude/skills
npx skills add smixs/skill-conductor

# Claude Code plugin
/plugin marketplace add smixs/skill-conductor
/plugin install skill-conductor@smixs

v3.2.0 — Evidence-based upgrade: form-matching, judge calibration, pressure testing

Principle #10: Match the form to the failure — classify the baseline failure before writing a rule; prohibitions bulletproof discipline failures but measurably backfire on shaping failures (obra/superpowers wording tests + Guardrails polarity data). Plus: no nuance clauses, exemption clauses don't scope.
Critique-before-verdict judges — all three eval agents (grader, comparator, bineval) now write the detailed evidence critique BEFORE committing to the 1/0 verdict, with a borderline few-shot example in each (Hamel Husain's judge methodology).
Threshold-blind judging — the BinEval judge no longer computes the overall score or the GATE; the orchestrator aggregates. A judge that knows the bar is biased toward it.
**Automatic cross-family judge calibrati